SAP Community - Joule

Trust but Verify - Validating SAP Joule Agents with Int4 Suite

2026-02-08T07:49:35.236000+01:00

In my previous posts, I explored why enterprise AI needs a "reality check" through Secret Agent Shoppers and how the role of SAP Functional Consultants is shifting in a world where system configuration is no longer strictly deterministic.

Today, I want to get a bit more practical. How do we actually validate an SAP AI Agent to ensure it’s doing what it says it’s doing? Specifically, we will look at how to automate this validation using Int4 Suite.

Figure 1 - Int4 Suite validating SAP Joule Agent

The Scenario: From Email to Sales Order

Let’s imagine an AI Agent designed to handle Sales Orders. The workflow looks like this:

The Trigger: A customer sends an email requesting to post an order.
The Agent: SAP’s AI Agent receives the mail, interprets the intent, extracts the data, and posts the Sales Order into SAP S/4HANA.
The Completion: The customer receives a notification that their order has been processed.

On the surface, this looks great. But in an enterprise environment, "looks great" isn't enough. We need to validate two specific areas:

Soft Rules: Was the agent’s response professional? Did it include the order number? Was the language correct?
DB Validations: Did the agent actually post the data correctly in S/4HANA? We need to compare the database entries (customer numbers, material indices, quantities) against a reference document to ensure the AI didn't hallucinate or miss a field.

Configuring Validation in Int4 Suite: A 3-Step Guide

Here is how you set up this automated "reality check" within Int4 Suite.

Step 1: Create the Automation Object

First, we create a new automation object. This serves as our "Secret Shopper," simulating the customer by sending the initial email to the SAP AI Agent.

Figure 2 - Int4 Suite Automation Object for sending the email and validating the work of the AI Agent

Step 2: Define Content and "Soft Rules"

Next, we update the object with the email content. This is where we define our "Soft Rules." The beauty of Int4 Suite is that these rules can be written in natural language. There is no coding required to tell the system what a "good" AI response should look like.

Figure 3 - Soft Validation rules within Int4 Suite

Step 3: Set S/4HANA Database Validation

Finally, we configure the DB validation. This is the most critical step. We don't want an AI agent pretending it finished a task when the database tells a different story. We set up ABAP rules to check the newly created order directly inside the S/4HANA database.

Figure 4 - Database validation rules in SAP S/4HANA

The Moment of Truth: Running the Test

When we trigger the validation from Int4 Suite, we get a comprehensive look at the agent's performance.

In our test run, the Soft Rules passed. The AI Agent replied politely and confirmed the order was placed. However, we aren't done yet.

Figure 5 - Soft validation rules correctness

The Final Validation compares the new Sales Order against a "Golden" reference document created with the same input. Only when every field in the S/4HANA database matches the reference exactly can we mark the test as a success.

Figure 6 - SAP S/4HANA Database validation result - comparison with the reference document

Why This Matters

AI models are not static. LLM providers update their models, and "temperature" settings can lead to different outputs for the same input. By using Int4 Suite, you can run these tests daily to ensure that a change in an underlying LLM doesn't silently shift your business processes.

Full Scenario

Video showing how Int4 Suite tests the SAP Joule Agent

Important note:

The aim here is not to question the reliability of SAP AI, but to ensure that changes in the evolving LLM landscape never interfere with the stability and consistency of your production environment.

Setting Up Document Grounding with Cloud Integration Automation service: Making Joule context-aware

2026-02-09T08:07:07.162000+01:00

While Document Grounding has been used to make Joule context-aware with specific business data, the latest development is that integrating Document Grounding with Joule is now fully automated by Cloud Integration Automation service.

In this blog you will find how Cloud Integration Automation service completely automates the integration of Document Grounding with Joule and SharePoint as the data source, hence making Joule context aware.

For more information regarding Document Grounding refer the blogpost : Joule – Getting Started with Document Grounding

Setting up Document Grounding using Cloud Integration Automation service

To set up Document Grounding, you would need to configure many steps as explained in Blog, however, lets now discover how Cloud Integration Automation service can simplify the whole process.

Prerequisites:

Joule instance should be available in one of the SAP BTP subaccounts
You have prepared SharePoint as mentioned in this Blog step “6. Prepare SharePoint Integration “.

Note: You will use SharePoint details later in the Cloud Integration Automation service workflow

Step 1: Subscribe Cloud Integration Automation service via BTP service marketplace. More details can be found : What is Cloud Integration Automation Service? | SAP Help Portal.

Step 2: Once subscribed, launch Cloud Integration Automation service application and click on “Plan for Integration”

Image 1

Step 3: Search for “Document Grounding” scenario

Image 2

You can view scenario related details such as “Description”, “Scenario Entities”, “Scenario Tasks”.

Image 3

Step 4: Click on “Select Systems”.

Image 4

Step 5: Provide system details and “Generate Workflow”

Provide SAP BTP system details

Image 5

2. Click on Generate workflow ->Background Execution

Image 6

Note: In the above step, Cloud Integration Automation service will generate a fully automated workflow, and users just need to provide few information to complete the integration.

Click on Next step

Select SharePoint as the data source as highlighted in the below screen shot.

Image 8

Click on Next Step

Image 9

Note: In this step Cloud Integration Automation service will create Share point destination, hence you will use share point information such as Share Point client ID, Share Point Client Secrete, SharePoint Tenant ID, Site URL from the Share Point application that you are using as the data source. You can fetch SharePoint details by referring to the screen shots.

Client ID:

Image 10

Client Secrete:

Image 11

Tenant ID:

Image 12

SharePoint URL:

Image 13

Once you provide all the task parameters click on Next step

Image 14

Click on Confirm

Image 15

Image 16

Step 7: Navigate to Scenario Monitoring to check the workflow status.

Image 17

Here you can observe that all the tasks that are needed for this integration are listed and implemented sequentially.

Task list:

Task Name	Task Status
Assign Entitlement for Document Grounding Service	Automated
Create Grounding Service Instance with a Service Key	Automated
Create Cloud Identity Service Instance with a Service Key	Automated
Create Destination Service Instance with a Service Key	Automated
Create Destination in BTP for Existing SharePoint	Automated
Create Destination in BTP for Existing SAP Document Management Service	Automated
Create Pipeline for SharePoint	Automated
Create Pipeline for SAP Document Management Service	Automated

Upon implementation of all the tasks, Document Grounding is fully integrated with Joule and is context aware with SharePoint as the data source.

Step 8: Go to BTP subaccount to check the following:

1. Instances (groundigcli, grounding Des, identityService) are created along with their service keys

2. Document Grounding destination (docu-grounding-dest-sh) is created

Image 19

Step 9: Launch Joule and ask Joule questions. You can now get context-aware answers and with links to its document sources.

Image 20

Useful Links

What is Cloud Integration Automation Service? | SAP Help Portal

Joule provisioning with SAP S/4HANA Cloud Private using Cloud Integration Automation service

SAP UX Q1/2026 Update – Part 4: SAP SuccessFactors (AI, Joule and More)

2026-02-09T10:23:23.505000+01:00

This fourth post in my series gives an overview of user experience innovations in SAP SuccessFactors. The major UX highlight is the new home page design. Beyond that, we’ll look at examples of good UX in applications, new Joule, AI, and analytics capabilities helping users become more effective, and enhanced integration into Microsoft Teams.

Before reading this, do read the first blog post introducing the series and providing general information about Joule, SAP Build Work Zone and SAP SuccessFactors Work Zone, and SAP Mobile Start, along with links to all the published parts of this blog post series:

SAP UX Q1/2026 Update – Part 1: AI, Joule, SAP Build Work Zone, SAP Mobile Start.

Also, if you missed it, do have a look at the many UX innovations which already came out with the SAP SuccessFactors 1H2025 release:

SAP UX Q3/2025 Update – Part 4: SAP SuccessFactors (AI, Joule and More).

Our strategy for user experience has three aspects for helping users save time and effort, and helping their business run better:

Enjoyable: providing a modern, accessible user experience, consistent and integrated, with good usability.
Better: helping users achieve better outcomes with AI and embedded analytics.
Together: helping users work together in teams.

In this post, I have picked the following highlights from the latest SAP SuccessFactors 2H2025 release showcasing each of these aspects:

Enjoyable: design and usability enhancements
o. New Home Page design (web and mobile) and WalkMe update.
o. Examples of good UX in Workforce Management.

Better outcomes with AI and Analytic
o. Career and Talent Development for employees and managers: skills, succession.
o. Performance and Goals: Joule agent, AI and analytics for managers.
o. Additional Joule support for employee self-services

Together: supporting collaboration in teams
o. Joule integration into Microsoft Teams.
o. AI-assisted quick writing available im Microsoft Teams

Enjoyable: Design and Usability Enhancements

The new home page design for the product will benefit all users. When it comes to specific applications, the 2H2025 release has a huge number of great enhancements, so it wasn’t easy to pick ones to highlight. I have chosen to include some of the innovations in Workforce Management. At the end of the blog post you’ll find links to all the news for the 2H2025 release.

New Home Page Design (Web)

The new Home Page design not only looks better, it also gives users tangible benefits, by becoming more intuitive and efficient, streamlining navigation and supporting personalization.

As you can see in Figure 1, the new design is cleaner and more attractive. The top navigation row contains Quick Actions, more compact than before. Below that the greeting section is new, with quick links and cards featuring timely and relevant information going beyond the user’s workflow actions and to-dos.

Figure 1: New Home Page for SAP SuccessFactors. Alt Text: Screenshot showing all the sections described in the text.

As you can see in Figure 1, we have separated Quick Actions and the Quick Links: the Quick Actions row at the very top allow users to quickly make updates or look at information while staying on the home screen: clicking on one of the Quick Actions opens a pop-over in which the user can do the action. Figure 2 shows two examples, where the user has chosen the Manage My Team and Give Feedback Quick Actions.

Figure 2: Quick Actions in the new home page. Alt Text: two screenshots each showing pop-overs for quick actions for (1) Manage My Team, with a list of team members on the left and two columns with links to actions, in groups “Change”, “View” and “Other actions”, (2) Give Feedback, with fields for the person, the topic and three questions (what went well, what to improve, additional comments).

Greeting Section: this section contains Quick Links on the left, that take you directly to the respective applications. On the right, the system displays cards featuring timely and relevant information that extend beyond the user’s workflow actions and to-dos.

Needs Attention: As before, tasks, to-dos, and workflow actions are available on the home page, but now with the improved design it is more intuitive and easier to use. The Needs Attention section provides a stack of cards for each type of task, to-do or action. They are displayed in just one row, within a carousel. If you have more than one card in the stack, the “View All” link opens a pop-over where you can see and interact with all the cards. Figure 3 shows an example, where the user has clicked on “View All (5)” in the leftmost card (shown in Figure 1) representing “Compensation Planning”.

Figure 3: Needs Attention “View All” example, showing all tasks of type “Remind a team member to complete pending tasks”. Alt Text: Screenshot of a pop-over showing a card for each of the five team members, each with the task type as title and a “Send Email” button.

Organizational Updates: This section is for links to organizational information, including custom cards for company initiatives or messages. As you can see, we have standardized the card pattern and display information using only the smaller-sized cards here.

Explore More: this is where customers have more freedome to place data visualization and banner cards. With the 2H2025 we provide two analytic cards that can be made available there: Time Sheet Status and Upcoming Absences. Find out more in the

Documentation: Analytical Cards on the Latest Home Page.

Personalization: at the very bottom of the home page (see Figure 1), you have a “Personalize your home page experience” button to do that, via a pop-over (Figure 4). You can personalize the selection of Quick Actions, Quick Links and also choose whether you want your name to appear in the Greeting section or not.

Figure 4: Personalization of the home page. Alt Text: A screenshot of the home page with a popover “Home Page Settings” with three tabs “Greeting”, “Quick Links” (selected), and “Quick Actions”, and a list of links to choose from (Time Sheet, Team Absence Calendar,…), all currently selected.

Watch it in action and find out more about the new home page for web and mobile here:

Video: Meet the New Homepage & Mobile Experience in SAP SuccessFactors – 2H 2025 Release (3:10 minutes)
SAP SuccessFactors HCM: Updated Home Page 2H 2025
More design backround: Exciting updates are coming to your SAP SuccessFactors home page!

New Home Page Design (Mobile)

We have also updated the SAP SuccessFactors mobile app correspondingly (Figure 5). You can see the Quick Actions along the top of the Home screen, above the Needs Attention section. To-Dos are on a separate screen, divided into two tabs Approvals and Other, with a section for each type of To-Do. Filters at the top of the screen let you quickly get to those To-Dos you are most interested in at the moment.

Figure 5: New Home and To-Do design for SAP Success Factors mobile app. Alt Text: Two mobile screens, on the left the Home screen, with Quick Actions at the top, then “Needs Attention” and “Featured” sections, each with a row of cards. On the right the To-Do screen, with Approve and Other tabs, above filters for “My Team”, “Learning Assignments”,…, and sections “My Team (7)” and “Learning Assignments (4)”, each with one row of cards.

Easy On-Boarding with WalkMe

The new home page is intuitive, so that most users should be able to adapt to it easily. To ensure that all users feel comfortable with it, we have adapted the WalkMe onboarding tour to explain how to use the new home page. The short video in Figure 6 shows what this looks like:

Figure 6: WalkMe for the new home page. Alt Text: A video showing WalkMe appearing as an overlay on the home page, starting with an “Explore updated home page” pop-over, followed by pop-overs next to each explained feature.

Examples of Good UX in Workforce Management

I’d like to highlight the new capabilities for workforce scheduing and geofencing for time tracking.

SAP SuccessFactors Workforce Scheduling

The brand-new shift scheduling solution SAP SuccessFactors Workforce Scheduling is for companies that need to plan their production workforce schedules. It enables demand-driven workforce planning, supporting both weekly and monthly shift plans that account for operational requirements, employee skills, and labor regulations.

As you can see in Figure 7, it makes it easy for users (schedulers) to get visibility into workforce availability, allowing them to minimize downtime, increase productivity, and better align labor supply with business demand.

Figure 7: Workforce scheduling. Alt Text. Screenshot of a schedule with a list of people on the left and a calendar on the right with rows corresponding to the people, showing who is allocated to which shift on which day. The screenshot shows a shift being assigned, with a date-picker popover.

Geofencing in SAP SuccessFactors Time Tracking

In this release, customers can leverage a new geofencing feature that helps ensure employees clock in and out only when physically present at their designated work location. Geofences can be defined for specific groups, with real-time visibility into proximity, helping to improve compliance with location-based policies and prevent time recording outside authorized areas.

Figure 8: Geofencing. On the left: defining the geofences. On the right: what it looks like for a user clocking time on a smart phone. Alt Text: Two screenshots: on the left the app Manage Geofences with a list of locations on the left, and on the right for the selected one a map with areas marked with a circle, a triangle and a polygon. On the right a mobile screen for clocking time, showing the user’s location within the marked circle on a map, and a “clock time” button.

Read more about these in this blog post:

Second Half 2025 Release: What's new in SAP SuccessFactors solutions for Workforce Management

Better outcomes with AI and Analytics

SAP SuccessFactors continues to invest heavily AI and analytics to help users work more effectively with a better overall experience. I have chosen to highlight how employees benefit when planning their careers and their further development, how employees and managers benefit when they need to evaluate performance and goals, and how Joule is making employee self-services easier:

Career and Talent Development for employees and managers: skills, succession
Performance and Goals: Joule agent, AI and analytics for managers
Additional Joule support for employee self-services

Career and Talent Development for employees and managers: skills, succession

Automatically Create Skills from Resume

A system, or for that matter a manager, can only help people grow in the direction they would like if they know what skills a person has, and what development goals they aspire to reaching. This means you need to have people’s skills maintained in SAP SuccessFactors in order for the system to guide employees and managers.

People often have a wide variety of skills, so manually maintaining the full list of their skills is time-consuming and can mean that people don’t bother – resulting in a lack of data in the system.

Now, the 2H2025 release uses AI to make this much easier: users can simply attach their resume, and the system will extract skills from there automatically. Figure 9 shows an example.

Figure 9: Using AI to extract skills from your resume. Alt Text: Screenshot of the Growth Portfolio app with an “Add from Resume” pop-over, showing the file name Resume.pdf and a list of 16 skill groups, such as “Agile Methodology”, “Communication Skills”, each with a check box for selecting to add or not.

Once the skills have been created, you will want to be able to easily search through them or filter them – which is why we have introduced search and filtering to the skills page, as shown in Figure 10.

Figure 10: Search and filter your skills. Alt Text: Screenshot of Growth Portfolio app with a filter bar at the top with a search field and filter fields for Proficiency Level, Categories, Tags, and Time Period. The page shows three rows of six cards, each representing a skill with a horizontal chart shosing the current level of proficiency on a 1 to 5 scale.

AI-Recommended Development Goals Based On Skills

Now that you have your full set of skills maintained in the system you can start using SAP SuccessFactors to guide your growth. This is an important enabler of our goal to empower employees to take control of their professional development.

After maintaining your development goals, the 2H2025 release of SAP SuccessFactors uses AI to make recommendations for suitable learning courses and available assignments relevant to achieving your goals. Figure 11 shows an example.

Also new: development goals can now be transferred between multiple jobs held by the same person, ensuring continuity in their growth within the company.

Figure 11: AI recommendations for learning and assignments based on skills and development goals. Alt Text: Screenshot of Goal Details, showing a card for Linked Assignments above the main section Opportunities to Grow, containing two cards: one for Learning, one for an Assignment. Each card has an image, title and a few details.

AI and Analytics for Managing Career and Talent Development

People Intelligence, our new people analytics application, is now generally available. It is built on SAP Business Data Cloud, and fully integrated in SAP SuccessFactors. It offers intuitive dashboards, AI-assisted insights supported by Joule, and hundreds of HR metrics. To help customers get started, the application includes nine pre-built use cases, each for a specific HR domain.

One of these pre-built use cases is Skills Insights. It helps to identify existing skill strengths and gaps in the organization, to compare current skills to target proficiency levels, and to align workforce capabilities with your organization’s priorities. Figure 12 shows an example of the overview page, from where you can drill down into further detailed views.

Figure 12: An example overview page of Skills Insights. Alt Text: Screenshot showing various charts (line chart, horizontal bar charts, heat map) for Skills Adoption Overview, Employees with Skills, Most Adopted Skills, Proficiency Overview.

Find out more about Skills Insights in:

Documentation: Skills Insights.

Career Development Insights is another of the pre-built use cases. Figure 13 shows an example of the development goals page that offers insights into participation rates, alignment with learning and critical skills, and organizational progress.

Figure 13: An example of the development goals within Career Development Insights. Alt Text: Screenshot showing a panel on the left with filters, on the right two sections: Summary, with numerical KPIs; Details, with four horizontal bar charts and a donut chart showing number of employees with goals, goal status, most and least popular skills.

Find out more about Career Development Insights in:

Documentation: Career Development Insights.

AI Successor Recommendation Based On Skills

Another example of how SAP SuccessFactors uses AI to give people a better user experience is the new skill-based successor recommendations capability. This uses AI to identify who would be best suited to be your successor, by matching skill sets and attributes to the specific role requirements. Figure 14 shows what it looks like.

By analyzing skill proficiency levels and internal work experience in the employee growth portfolio, it recommends potential successors who might have been overlooked using traditional metrics.

Figure 14: AI successor recommendation based on skills. Alt Text: Screenshot of Succession app showing org chart view for manager John Williams with 3 successors underneath his image. There is a pop-over for John, with details of the position, and a list of three other suggested successors. For the first one, Michael Pittman, a further pop-over “Role Readiness Explanation” is shown listing five matched skills and competencies and four unmatched ones.

Performance and Goals: Joule Agent, AI and Analytics for Managers

When the time arrives for managers to review the performance of their team members, they typically need to reserve a considerable amount of time in getting an overview of each person’s activities, achievements, and feedback they have received.

Now, managers can save a lot of time by using the new Performance and Goals Agent within the SAP SuccessFactors Performance and Goals solution. Using Joule, managers get AI-guided insights – for example, into their areas of strength, areas needing improvement, goal progress summaries, key accomplishments, and development recommendations. Figure 15 shows an example.

Figure 15: Performance and Goals Agent. Alt Text: Joule in full screen mode, with a prompt “I have to meet with Christine Dolan about her performance. What should I know about her areas of strength and what she needs to improve?”. Below that the reply in two sections “Areas of Strength” and “Areas Needing Improvement”, containing bullet points.

The UI for managers to enter their assessment is intuitive, as shown in Figure 16. Now, with the 2H2025 release, HR departments can define business rules that trigger actions for users based on what they have entered. For example, a rule might stipulate that a low rating requires a comment to be entered, resulting in the comment field only being exposed when a user actually gives such a rating.

Have a look at many more examples of how the agent helps managers:

Video: Introducing the Performance & Goals AI Agent in SAP SuccessFactors (3:27 minutes).

Also helpful for managers is the enhancement of the AI-powered Writing Assistant that is now available: they can use it to help formulate comments for performance ratings, as shown in Figure 16, and in the video linked above.

Figure 16: AI Writing Assistant for formulating comments when rating performance, embedded in the intuitive performance review UI. Alt Text: Screenshot of Performance feedback app, showing a list of goals with manager and employee rating, and a panel on the right with evaluation details for the goal “Ensure production documentation complies with standards”. The comments field is in focus, with a popover “Generate Comments” listing suggested texts – “Regularly review and update documentation” is highlighted.

Performance Insights

People Intelligence also comes with pre-built use cases for the performance and goals area, giving managers insights into performance metrics across the organization. Figure 17 shows an example of an overview.

Figure 17: Performance Overview in Performance Insights provided by People Intelligence. Alt Text: Screenshot with three sections Overview (showing KPIs), and Performance Distribution and Performance Rating Changes, containing a line chart, horizontal bar charts and a donut chart.

Find out more about what’s new for Performance and Goals here:

Additional Joule support for employee self-services

Employees typically only rarely interact with the HR system, so they are casual users, who especially need an easy to understand, intuitive user experience. Joule helps here enormously, since users can just state what they want and Joule will help.

With the 2H2025 release, we have added further Joule actions. Users can now upload files directly through Joule in the flow of supported Joule scenarios, view organizational information of themselves or others, view extended time-off data, and create half-day leave requests based on scheduled working time. Figure 18 shows examples for a half day leave request and for viewing time off guidelines.

The “explain my pay” feature, that I highlighted in my previous UX blog post on SAP SuccessFactors, is now also available for employees in Mexico and in Germany – in their respective languages (Spanish and German). Figure 18 shows an example for Mexico.

Figure 18: Further Joule actions available now. Alt Text: three images of Joule: 1) with prompt “I wann apply half day leave tomorrow morning”, with Joule showing time off request; 2) “what is the time off guideline”, with Joule summarizing time off types and purposes; 3) “Explique mis deducciones”, with Joule providing a pay explanation in Spanish.

Together: Supporting Collaboration in Teams

Users working with Microsoft Teams can chat directly with Joule from within Teams, as well as benefitting from AI-assisted quick writing directly in-place.

Joule integration into Microsoft Teams

Users can now access chat with Joule while using Microsoft 365 Copilot within Microsoft Teams, as shown in Figure 19.

Figure 19: Access Joule from Microsoft Teams via Microsoft 365 Copilot. Alt Text: A screen showing Copilot open in Teams, where the user has typed in “show my leave requests”.

AI-assisted Writing Available in Microsoft Teams

Furthermore, AI-assisted writing is now built into the SAP SuccessFactors quick actions that are available to users in Microsoft Teams, such as giving feedback or creating activities. This helps users communicate more clearly and consistently, and save them time in formulation too. Figure 20 shows an example for giving feedback directly from within Teams.

Figure 20: AI-assisted writing in Microsoft Teams. Alt Text: A screenshot of Microsoft Teams showing Quick Actions for SAP SuccessFactors behind a pop-over for giving feedback, with some text entered into the “What went well?” question and a context menu pop-over listing the writing assistant menu items, with “Enhance Writing” in focus.

Further Information on 2H2025 Release Highlights

These four assets give you an overview of the overall release highlights for 2H2025, in increasing level of detail:

The following posts give details of innovations in the 2H2025 release in these areas:

Finally, for all the details, have a look at the documentation:

SAP SuccessFactors What’s New Viewer.

Continue Reading

I hope you enjoyed this fourth part, covering SAP SuccessFactors, with great new user experiences helping employees and managers work more efficiently and effectively.

Here's a link to part five, covering latest UX innovations for managing your supply chain with SAP Integrated Business Planning:

SAP UX Q1/2026 Update – Part 5: Innovations in SAP Integrated Business Planning.

Part 1 of the series lists all the parts, and links to those parts that have already been published:

SAP UX Q1/2026 Update – Part 1: AI, Joule, SAP Build Work Zone, SAP Mobile Start.

Do keep posting your experiences and recommendations yourself in the SAP Community, with the SAP Fiori and/or the User Experience tag! In case you are wondering how to get a list of the most recent blog posts on SAP Fiori and User Experience in our new SAP Community, use these links:

Setup and Activation Guide: Joule in SAP S/4HANA Private Cloud

2026-02-10T11:22:05.957000+01:00

Prerequisites

SAP S/4HANA Cloud Private Edition 2021 or higher (2023 FPS01 recommended for full capabilities)
SAP BTP Global Account with Joule entitlements
SAP Build Work Zone, standard edition entitlements
Cloud Identity Services (IAS/IPS) setup
RISE with SAP contract (Joule is only available within RISE with SAP)
SAP-managed data center setup

Pre-Setup Checklist

Verify SAP S/4HANA Private Cloud Edition version compatibility (minimum 2021, recommended 2023 FPS01+)
Confirm system is registered in SAP BTP System Landscape
Ensure Cloud Connector connectivity is established
Validate minimum UI5 version requirements per your S/4HANA release
Verify Joule and SAP Build Work Zone entitlements in BTP Global Account
Confirm Identity Authentication Service (IAS) integration with S/4HANA system

Setup Steps

1. BTP Platform Configuration

Create a dedicated BTP subaccount in a Joule-supported data center
Enable Cloud Foundry environment and create organization/space ,
Add Joule (foundation plan) and SAP Build Work Zone entitlements to the subaccount
Add Cloud Identity Services (connectivity plan) entitlements ,

2. Trust and Security Setup

Configure Trust to the Identity Authentication tenant in BTP subaccount
Configure trusted domains in SAP BTP (add S/4HANA Fiori Launchpad URL)
Configure trusted domains in Identity Authentication Service
Disable default identity provider in BTP subaccount to avoid authentication conflicts

3. Content Provider Configuration

Expose SAP Fiori Launchpad content to SAP BTP
Set up SAP S/4HANA Cloud Private Edition as a content provider
Create SAP Build Work Zone application and service instance
Configure destinations for system connectivity

4. Joule Service Activation

Run the Joule Booster from BTP Global Account
Select the prepared subaccount and configure integration settings
Create Joule formation and select required Cloud Identity Services
Configure Identity Provisioning Service for user and role synchronization

5. Fiori Launchpad Integration

Access transaction /UI2/FLP in SAP S/4HANA system
Navigate to Launchpad App Manager (Cross Client)
Configure and activate Joule plug-in in target mapping
Set up Joule web client URL with proper application component (CA-FLP-EXT-JOU)

Post-Activation Validation

Verify Joule icon appears in Fiori Launchpad (diamond-shaped icon)
Test user authentication through configured Identity Authentication Service
Validate navigation capabilities to core SAP Fiori apps (Procurement, Finance, Sales, Service Management)
Confirm transactional capabilities like "show purchase orders" and "upload supplier invoice"
Check system performance and response times

Troubleshooting Common Issues

Issue Possible Cause Resolution

Joule icon not visible	Plugin not properly configured in target mapping	Verify target mapping configuration and URL setup
Authentication popup appears	Trust configuration mismatch between BTP and IAS	Check trust configuration and trusted domains setup
Navigation failures	Missing business roles or authorizations	Ensure users have appropriate SAP Fiori app roles assigned
Formation not working	System not added to Joule formation	Add S/4HANA system to Joule formation or run booster again

Best Practices

Ensure consistent Identity Authentication Service across all integrated SAP systems
Use technical users with comprehensive authorizations for system connectivity
Regularly update to latest S/4HANA releases for enhanced Joule capabilities
Implement proper role-based access control to maintain security
Monitor system performance after Joule activation

Next Steps

Navigate to Fiori Launchpad to access Joule web client and explore features ,
Train users on conversational patterns and available capabilities
Consider extending Joule capabilities through SAP Build tools for custom scenarios
Plan for ongoing maintenance and system updates

The Combined Power of SAP Joule and AI for the RISE with SAP Methodology

2026-02-11T08:00:00.018000+01:00

Part five of the five-part series, “RISE with SAP Methodology”

AI is everywhere right now. Not just in tech headlines or innovation labs, but also in boardrooms, architecture discussions, and project plans. And if you work with SAP solutions, you’ve likely noticed that most road maps now mention it, too.

Many of us have seen “the next big thing” come and go. New tools, new buzzwords, and big promises have often delivered limited practical impact. So, the real question isn’t whether AI exists. It’s “where will AI actually make a difference?”

Organizations want technology that helps people work better, make smarter decisions faster and cut through complexity in day-to-day work with real-world pressures and consequential deadlines. AI should not be treated as a standalone innovation topic, but as a capability embedded across products, processes and user experiences.

That’s exactly the direction SAP’s new strategy is taking. At the heart of this strategy sits a simple idea: bring applications, data, and AI together in SAP Business Suite, so intelligence becomes part of how work naturally happens, as shown in Figure 1.

Figure 1: The Future of AI in SAP Business Suite

Joule vs. AI Capabilities: Understanding the Difference

When people talk about AI in SAP environments, two concepts often get mixed together: AI capabilities and the Joule solution.

While connected, each one plays vastly distinct roles:

AI capabilities form the foundation and are the engine, quietly running in the background. Powerful, but often invisible, they analyze huge volumes of data, predict risks and generate recommendations. They include technologies such as machine learning, predictive analytics and automation embedded across SAP solutions.
Joule, on the other hand, is the interaction layer between people and AI and facilitates one-on-one conversations with the user. This is the moment when intelligence becomes accessible. Instead of searching through lots of guidelines, dashboards or compiling reports, users simply ask questions, such as “What should I focus on next in our transformation project?” or “Where are we off track?”. Users can even just say “Summarize the risks”. And in return, they get answers immediately and in context. (see Figure 2 below)

Together, AI capabilities and Joule form a complementary model where AI feels natural, not abstract. The experience is remarkably similar to talking to a knowledgeable colleague who already understands the system landscape. There’s deep intelligence behind the scenes and a simple, human interaction up front.

Figure 2: Interacting with Joule as the new AI user experience

Joule: A practical entry point to AI

As shown in Figure 2 above, one of SAP´s strategic priority is to offer a new AI user experience through Joule. This AI-enabled assistant introduces a simple, practical way to bring AI into transformation work.

While delivering many AI capabilities across the SAP solution portfolio, Joule goes beyond using AI as another analytics tool or dashboard by running an interaction layer that allows customers to work with AI through a single, conversational interface.

This changes how teams engage with information during transformation projects or in day-to-day business. Instead of navigating multiple tools, reports, or status decks, users can interact with Joule in natural language—asking questions, requesting summaries, or starting conversations on how to proceed with tasks alongside the transformation project. (see Figure 3)

Behind the scenes, Joule connects to relevant data across SAP solutions and presents answers in a way that is easy to understand and easy to act on. In practice, this lowers the barrier to insight. Instead of searching for information, teams start working interactively with it.

Figure 3: Using Joule interactively during your transformation work

Strategic enablers of the transformation journey

As mentioned before, AI is embedded directly into SAP solutions and workflows to help people navigate complexity. Users can surface relevant insights, identify patterns, and reduce manual effort.

Take, for example, transforming an ERP landscape. This project can easily become complex, depending on customer requirements. The volume of information that teams must use at the same time—including process data, system insights, project status, testing results, risks, and dependencies—often spread across tools and documents. Even with a clear methodology in place, the effort required to connect these dots manually has become a challenge of its own.

RISE with SAP Methodology already provides the structure needed by providing the integrated tooling, standardized framework, and expert guidance to support the proper execution discipline. However, embedding AI in the methodology adds a new layer of intelligence at the point of action, helping teams understand what matters where risks are emerging, and which decisions requires attention (see Figure 4).

In this case, AI reduces the load that comes with large-scale change. When applied correctly, it supports people in making better and faster decisions, especially when time and attention are limited.

Meanwhile, Joule is used whenever clarity is needed (see Figure 4). This opens up a new way of working with guidance, insights, and execution support throughout the transformation journey when using RISE with SAP Methodology, serving as an active companion.

Figure 4: Joule and AI as an integral part of RISE with SAP Methodology

Giving an end-to-end perspective alongside the transformation, Joule allows project teams to handle time-consuming and complex tasks faster and with greater ease. This includes searching for information and guidelines that can help them start and review extensive assessments and analyses.

As planning and design activities progress, Joule enables teams to stay oriented. It supports prioritization, highlights dependencies, and helps validate assumptions before decisions become difficult to reverse. AI does not replace workshops or experience, but it strengthens them with data-driven insight.

During execution, when the build and testing phases accelerate, Joule supports transparency and focus. AI capabilities detect patterns in defects, progress, and quality signals, while Joule summarizes what matters most. So instead of consolidating information manually, teams can react early.

Joule supports readiness discussions as go-live approaches. By correlating information across testing, migration, and operational checks, AI helps teams assess whether they are truly ready based on evidence, not gut feeling.

After go-live, AI continues to support continuous improvement. Usage patterns, incidents, and performance signals are analyzed in the background. Joule helps connect teams to those insights to understand where to improve next and how operational issues relate back to earlier transformation decisions.

Practical value over automation

The strength of AI in SAP transformations does not lie in automation alone.
It lies in reducing all the cognitive load that happens during the transformation project.

By combining all elements of the RISE with SAP Methodology:

a clear path (with the Standardized Framework)
Integrated tooling (with the Integrated toolchain)
End-to-end Execution support (with the Expert Guidance) and
AI-driven assistance through Joule and specific AI capabilities

customers are well equipped to move through their transformation with focus, confidence and consistency.

AI does not replace people or experience.
It supports both – at the right moment, in the right context.

To learn more about RISE with SAP Methodology, read our in-depth overview.

--------------------------------------------------------------------------------------------------------------------------------------------------

RISE with SAP Methodology - Blog-series

Discover the 5-part blog series:

Blog 1/5 (December 3rd, 2025)
RISE with SAP Methodology: A practical Guide to Modernizing with Confidence
Blog 2/5 (December 10th, 2025)
Deep Dive: Inside the framework of RISE with SAP Methodology
Blog 3/5 (January 14th, 2026)
The Integrated Toolchain in a Nutshell
Blog 4/5 (January 28th, 2026)
Expert Guidance: Your Guided Transformation Accelerator
Blog 5/5 (February 11th, 2026)
The Combined Power of SAP Joule and AI for the RISE with SAP Methodology

--------------------------------------------------------------------------------------------------------------------------------------------------

#clouderpprivate #s4hanacloud #sap #risewithsap #transformation #risewithsapmethodology

Managing Joule on SAP BTP: Roles, Analytics, Administration and Troubleshooting

2026-02-11T11:27:55.163000+01:00

Introduction

As SAP continues to roll out Joule integrations across multiple LoBs, with stronger and wider SAP and non-SAP ecosystem bringing the powerful AI-driven assistance, Agents, Agents to Agents, and many more functionalise to our business users. To ensure these functionalities run smoothly, every organization requires the right administrative setup and awareness of key configurations; at the same time it becomes increasingly important to understand how to manage, troubleshoot, understand the consumption patterns in your organisation with most frequently used questions driving your organizational process are some of the key features, and enhance the digital assistant’s functionality efficiently.

This blog aims to help administrators and support colleagues navigate the essential aspects of managing Joule service within an SAP Business Technology Platform environment. It walks through the available roles and role collections, their purposes, and how to configure them effectively.

The blog also focuses on troubleshooting best practices — highlighting the common checks, logs, and details that SAP Support typically requests during issue resolution. By following these guidelines, you can resolve common problems faster, share the right information upfront, and reduce back-and-forth communication with SAP.

Ultimately, this guide aims to make your Joule operations more efficient, your issue-handling more structured, and your collaboration with SAP smoother and quicker.

Before we get started, it’s important to understand the overall Joule integration for your organization. Please look at the blogs below:

This blog post is a series for Joule Activation:

SAP Business AI – Overview for all !!! (Includes information on Joule Supported Data Centers, Different scenarios during Joule setup, etc..)
Joule - Unified Setup: Bridging Simplicity and Performance (Demo Video to understand the Unified Setup, Joule basics & architecture, how to set up Joule, etc...)
Joule for SAP S/4HANA Cloud Private Edition - A Comprehensive Setup Guide
Joule Setup – End-to-End Setup Guide (for all Line of Business) Unified Approach
Joule for SAP S/4HANA Cloud Public Edition - Setup Guide
SAP Digital Supply Chain

Joule – Getting Started with Document Grounding - setup guide
Activate Joule with SAP Build Work Zone and SAP Mobile Start
Analytical Insights

Analytical Insights in Joule – Setup Guide

Joule Integration with SAP Ariba - Setup Guide
Joule Integration with SAP Concur - Setup Guide
Joule integration with SAP Signavio Process Transformation Suite – Setup Guide

👉Managing Joule on SAP BTP: Roles, Analytics, Administration and Troubleshooting - you are here

Blogs - Work in Progress (WIP):

SAP Digital Supply Chain (WIP)

SAP Asset Performance Management
SAP Product Lifecycle Management
SAP Digital Manufacturing

and more to be added towards General Availability

****************************************************************************

This blog explains the key features and administration aspects of Joule on SAP BTP.

Joule Features
- Downloading traces for debugging and SAP support
- Conversation search across chat history
- Version details, support components, and personalization settings
Roles and Access Management
- Available Joule roles in SAP BTP
- Creating and managing role collections
- Assigning roles to users and user groups
- End User access
- Tenant Admin and Joule Admin Center
- Extensibility Developer capabilities
Admin and Analytics Interfaces
- Joule Analytics Center for usage statistics and trends
Conversation History FAQs
- Active and expired conversations
- Retention limits and lifecycle behaviour

Disclaimer:
This blog is meant to provide a general understanding and practical guidance for working with SAP Joule based on common scenarios. For detailed and up-to-date information, please always refer to the Joule | SAP Help Portal.

1. General Features – Download Traces, Conversation Search, etc.

1. 1 Download Traces

One of the important things to make note of is that one can download traces which can be attached in case of any errors/support required from the team. This option enables the user to be quick in providing the information for debugging which would be required by the SAP Support teams. To download traces, just click on Settings, in the pop-up, go to About and click Download Traces.

Image 1

Another pop-up will come, where you can choose whether to include message history in the trace files. Once done, click on Download and you’ll have a .zip file downloaded. This file can be attached in the support ticket created to SAP in case of any errors faced while using Joule.

Image 2

The file downloaded can contain the following details

Joule version and environment details.
UI Logs and the most recent 5-10 HTTP requests.
Correlation IDs for the last 5-10 messages that can be used by SAP to fetch additional details logged by SAP.
Message history as a JSON file (included only based on user consent).

Find the support Components to which the ticket has to be created for specific joule issues in the below table.

CA-JOULE	Joule
CA-JOULE-CI	Joule Conversation Logging and Insights
CA-JOULE-CLI	Command Line Interface tool
CA-JOULE-CLT	Joule Messaging Client-related topics
CA-JOULE-CLT-COP	Specific for Joule x Copilot Integration
CA-JOULE-COMP	Joule Compiler
CA-JOULE-CONSULT	Joule Consulting
CA-JOULE-CR	Joule Conversational Runtime
CA-JOULE-PRV \|\| CA-JOULE-PRV-INT	Provisioning & Integrations with applications
CA-JOULE-TA	Tenant Administration - Joule Content Deployment related issues
CA-JOULE-TR \|\| CA-JOULE-PRV-ONB	Tenant Runtime (Bot-runtime), Joule Subscription, SPR, TO and Approuter issues
BC-CP-MP-FOR	Unified Customer Landscape (UCL)
BC-IAM-IDS	IAS

For further information, you can refer to the help portal - Monitoring and Troubleshooting | SAP Help Portal.

1.2 Conversation Search

Conversation search allows users to quickly find past conversations (including expired conversations) from their history.

From the side navigation panel, click on the search icon to access conversation search.

Image 3

Enter one or more keywords to search across your conversations.

Image 4

Search results are dynamically updated as you type. Matching strings are highlighted in the results obtained from the search. The results returned include both the conversations where the title may contain the search term as well as those where the search term is found in any of the messages in the conversation. Selecting a search result navigates you directly to the matched conversation and message.

1.3 Other features

User can also check the version of Joule and the Support Component to raise tickets for Joule in Setting > About.

Image 5

In Settings > Personalization, you can choose to disable streaming and whether to turn off animations.

Image 6

2. Joule Roles

Prerequisite: You should be a subaccount admin.

As an administrator, you’ll be able to view the available roles and role collections in your subaccount. Open the SAP BTP Cockpit and go to your global account and subaccount.

Choose Security > Roles
Search for “das” in the search bar.
You’ll see the list of the available roles for Joule under the Application Name das-application

Image 7

2.1 Create Role Collections, Assign Roles and Users

In order to assign the roles to users or user groups, we need to first add them into role collections as these roles are not part of any collection and cannot be assigned to users unless we create the collection. To create a role collection (screenshot attached),

Go to Security > Role Collections
Click on Create, enter a name for the role collection and click Create.

Tip: You can decide to create one common role collection for all Joule roles and assign them together or create separate role collection in case you want have better controls and maintain it individually.

Image 8

The new role collection will get listed in the page, now select the created role collection, and click on Edit.

Image 9

Now, under Roles, click on the textbox, a pop-up will appear.

Image 10

Search for “das-application” in Application Identifier. Select the appropriate option. You’ll see the Joule roles listed. Select the ones which must be added and click on Add.

Image 11

This helps us to create the Role collections which now can be assigned to the users.

To assign users, go to the users section under the role collection, enter the email-id and select appropriate identity provider. Now you can Save the role collection.

Image 12

Now let’s go to our joule and see what options are available as a user with the role “End User”.

2.1.1 End User (end_user)

This is the role which gives the user access to the standalone URL of your Joule tenant. For more on using the joule web client, refer Using the Joule Web Client | SAP Help Portal.

2.1.2 Tenant Admin (tenant_admin)

As a tenant admin, you can access the Joule Admin Center - a tenant specific user interface, offered for customizing respective Joule configurations. You can find more information here – Joule Admin Center | SAP Help Portal.

To access the Joule Admin Center:

Go to the BTP Cockpit and open your subaccount having Joule. Go to Subaccount Overview > Instances and Subscriptions.
Expand the Joule application subscription (das-application). Click Go to Application to fetch the Joule application URL.

Image 13

Get the Joule tenant URL and append "/admin" to form the admin center URL for the respective Joule tenant - <Joule tenant URL>/admin.

Image 14

You’ll get the below page for Joule Admin Center, given you have the role tenant_admin assigned to your user. Here you can find the list of assistants available in your Joule, and you can select each of them to see their system alias and destinations setup for each.

Image 15

Note: SAP team is actively working to add more details and features to this page, stay tuned for more updates. In your case you may only see the “sap_digital_assistant” with standard Joule integration.

2.1.3 Extensibility Developer (extensibility_developer)

This one is applicable to the customers/partners who would like to use Joule extensibility in your landscape. This role is required to build and deploy capabilities for Joule. For more information, refer Joule Development | SAP Help Portal.

In addition, this role provides Debug option which provides visibility into runtime execution through the Logs View, which helps administrators and developers monitor and troubleshoot custom capabilities effectively.

With this role, users can:

View end-to-end execution logs for Joule conversations.
Easily identify execution outcomes using visual status tags (Blue for success, Red for errors).
View Correlation IDs to trace requests across the complete conversation and use these as supporting information for issue analysis and support ticket creation.

Use log details as To use the Debug features, open the Joule conversation window, click on the Debug icon on the top right corner. A side window named “Request Logs” will appear, Here you can find the logs and trace the conversation.

Image 16

A side window named “Request Logs” will appear, Here you can find the logs and trace the workflow of the conversation in case you face any error or run into an issue. You can expand the log messages by clicking on the arrow beside the message to find further details.

Image 17

Now, let us see how to fetch the Correlation ID for a conversation in Joule. This ID must be shared with the support team for effective troubleshooting and error tracing.

Open the conversation for which you want to retrieve the Correlation ID. For messages generated by Joule, a debug icon is displayed in the top-right corner of the message. This icon will be blue if the response was generated successfully. In case the request ran into an error, the icon will be red.

Image 18

Click this icon to open a split view titled “Response Payload.” Scroll to the bottom of the payload, where you will find the correlationID field.

Image 19

Share this Correlation ID with the Joule support team to assist with issue investigation and analysis.

Note: For every conversation where Joule is not working as expected or run into any errors, the Joule Support team will be requesting the correlation ID or the conversation trace. Please ensure to have these information attached to the support ticket which you’ll be creating for the issues/troubleshooting.

2.1.4 Analytics Admin (analytics_admin)

Joule offers an analytical insight on the Joule usage with the analytics_admin role. You can find the official help page here – Joule Analytics Center | SAP Help Portal.

Go to the BTP Cockpit and open your subaccount having Joule. Go to Subaccount Overview > Instances and Subscriptions.

Expand the Joule application subscription (das-application). Click Go to Application to fetch the Joule application URL.

Image 20

Get the Joule tenant URL and append “/analytics” to form the Joule Analytics Center URL for the respective Joule tenant (your BTP subaccount) - <Joule tenant URL>/analytics.Image 21

You’ll get the below page of Joule Analytics Center. Click Acknowledge and continue to explore the analytical insights provided.

Image 22

You can view analytics across interaction types, products, scenarios, and client types for a selected time range, providing insights into overall Joule usage, adoption, and engagement.

The Summary section highlights key metrics, including total messages, total conversations, and the average messages per conversation, giving a quick snapshot of overall interaction volume and conversation depth.

Image 23

We have 2 sections, Messages and Conversation - each representing a different level of interaction. A message is an individual request or response generated within Joule and is counted across all conversations. A conversation represents a single, distinct interaction thread initiated by a user, identified by its conversation topic name. Each conversation can contain one or more individual messages exchanged within that thread.

The Messages section breaks down message activity by product, scenario, and interaction type, helping you identify which products and scenarios are most frequently used and how users interact with Joule across different interaction types.

Image 24

The Product Usage graph clearly shows which products are using Joule most actively. From the sample data in the screenshot below, SAP S/4HANA Public Cloud has the highest usage, followed by SuccessFactors and SAP Analytics Cloud / Just Ask, while products such as IBP and IPD show comparatively lower message volumes. This view helps identify where Joule adoption is strongest and enables easy comparison of usage across different products.

Image 25

The Scenario Usage graph shows how frequently different scenarios are used in Joule. From the data, scenarios such as “ESH_U_SALESORDER” and “purchase order–related scenarios” have higher usage. Other scenarios, including employee views, feedback, and scheduling workflows, show comparatively lower usage. This view helps identify the most actively used scenarios and supports prioritization of monitoring and optimization efforts for high-impact workflows.

Image 26

The Interaction Type Usage graph illustrates how users engage with Joule across different interaction types. The data shows that scenario-based interactions account for most of the usage, followed by direct responses and slot filling, while information retrieval and file uploads contribute only a small portion. This view helps understand preferred interaction patterns when interacting with Joule.

Image 27

You can also find weekly statistics of messages and conversations.

The Message Count Over Time graph shows how the total number of messages sent to Joule varies over the selected time range. From the sample view, you can see clear peaks and drops, indicating periods of higher and lower activity. This helps administrators and the organization to identify usage trends, understand peak activity periods, and correlate spikes with specific events, releases, or user activity.

Image 28

The Conversation Count Over Time graph displays how the number of unique conversations changes over time. In the sample screenshot, you can observe days with higher conversation counts, indicating increased user engagement, followed by periods of lower activity. Comparing this graph with the message count helps distinguish between longer conversations and an increase in the number of users or sessions, providing better insight into overall usage behavior.

Image 29

You can also find Product Usage and Scenario usages under the Conversations showing which product/scenario generate the most conversations.

Image 30

Additionally, there is a Client Type Usage graph which shows the number of conversations across different client types, such as Desktop, Mobile, and Copilot, helping you understand how conversations are distributed by access channel.

Image 31

Overall, these graphs make it easy to visually identify where usage is highest, compare adoption across products, scenarios, and interaction types, and gain actionable insights for monitoring and operational analysis.

3. FAQs on Joule Conversation History

Adding, deleting, and renaming conversations
- Create a new conversation by selecting the "New Conversation" option from the side panel menu.

Image 32

When a new conversation is created, a conversation title is automatically generated based on the first user request–response in the conversation thread.
You can rename a conversation at any time by hovering over the conversation in the side panel and selecting "Rename" from the conversation menu, or by selecting Rename from the conversation header.

Image 33

To delete a conversation, hover over the conversation in the side panel or open the action menu from the conversation header, then select Delete. A pop-up will appear, confirm by clicking “Delete”

Image 34

Image 35

Active conversations
- A maximum of 10 active conversations can be maintained at any time. This helps users keep conversations segregated and organized, for example by using separate conversations for different applications such as SAP S/4HANA and SuccessFactors, or by specific business scenarios like leave requests, travel requests, and other workflows.
- Conversations are sorted with the most recently active on top.
- Switch between conversations to continue engaging in a different conversation.

Image 36

Image 37

Expired conversations
- A conversation expires after 8 hours of inactivity. Upon expiration you'll be notified and provided with an option to trigger a new conversation.
- Conversations are sorted by the creation date of the thread with the newest at the top.
- Conversations are deleted automatically 7 days after the date of creation.
- Expired conversations cannot be continued. They can only be referenced for past interaction history.

Image 38

As Joule adoption grows across products and scenarios, effective administration becomes the backbone of a reliable user experience. With a clear understanding of Joule roles, analytics, and troubleshooting tools, administrators can proactively monitor usage, resolve issues faster, and support business users more efficiently.

Credits & Special thanks to RIG Team (Nagesh Caparthy & Naga Swathi T J) for supporting this blog post.

Until the next update — stay tuned and happy learning!!!

Best Regards,
Amrita Varshini E R
SAP Business AI RIG Team

Creating a ‘Hello World’ Joule Agent

2026-02-11T11:55:37.566000+01:00

Building on Michael Ameling's excellent Agent Builder in Joule Studio announcement and The Joule Studio Learning Series, this post will guide you through building your first Joule Agent.

I'll walk you through the steps to build a "Hello, World" agent. Along the way, you'll get familiar with the basic workflow in SAP Build, explore the UI, avoid at least one common pitfall, and have your agent up and running in just a few minutes. By building the simplest possible agent, you'll gain the confidence that building agents is easy, and creating more sophisticated ones will feel like a natural next step. Let's get started.

Setup and Prerequisites

The setup of SAP Build Apps, the activation of Joule, and the SAP Agent Builder are described in these two blog posts:

I'll assume that's done, and we'll start our journey in the lobby of SAP Build Apps.

Creating a Project

Click on the "Create" button, and select "Joule Skill":

Enter a name and a description:

Creating the Joule Agent

You'll be forwarded to the overview of your project where you can create the Joule Agent:

Again, enter a name and a description. A proposal for the identifier will be generated automatically:

On the details page of your Hello World Agent, you could fill in the fields manually, but let's use Joule to create a proposal. In the top left, click on the Joule icon to open the Joule sidebar. Enter a prompt like this:

"Can you please update our existing Hello World agent by filling in the expertise, instructions and additional context? The agent should respond to every prompt with "Hello, World!"."

As a result, Joule updates the agent, and we're almost done. We just need to add a placeholder tool, for example the calculator, because Joule Studio does not allow an agent to be saved without a tool assignment:

Now you can save the agent, and we can move on to testing the functionality we've just implemented.

Testing the Joule Agent

When you click on the "Test" button (just above the "Save" button), you'll be asked which environment you'd like to test in. Select the environment associated with your email address.

If your email address doesn't appear in the dropdown, you need to activate your private environment first. To do so, click on the SAP Build icon in the top left corner, click on "Control Tower" in the left-hand menu, and then click on the "Environments" tile:

On the Environments screen, click the button to activate your private environment:

Afterwards, you can resume testing and your private environment should appear in the dropdown as described above.

Now we're ready to test the agent, for example with a prompt like "Let's test the agent".

As we can see, the agent correctly responds with "Hello, World!" 😅

To end the test session, just click on the "Stop Testing" button.

Deploying the Joule Agent

To get our agent out of the testing environment, we need to deploy it to a real environment.

Let's create a Hello World environment. Navigate to the Control Tower, select the Environments tile, and click on "Create". Enter a name and description for the environment. The proposal for the identifier will be generated automatically.

Your user will be automatically added to this new environment. If you see a blank screen when you want to view the environment details, just try refreshing the page in the browser. It may take a little while to generate.

Once the environment is active, we can deploy our agent. Click on the "Release" button in the agent overview.

In the subsequent pop-up, enter a release note and click on "Release".

Once released, switch to version 1.0.0 at the top of the screen by clicking on the dropdown next to the title.

In the released version, there is a "Deploy" button instead of the "Test" and "Release" buttons. Click on the "Deploy" button, select the Hello World environment, and click on "Deploy".

After a few moments, the status of agent version 1.0.0 will change to "Deployed and Active".

Testing the Deployment

As a final step in this tutorial, let's test our deployed agent in the Hello World environment.

Open the Hello World environment via the Control Tower and view the environment details by clicking on it in the list. There, you will see the deployment of the Hello World agent we just made.

To test it, open the Joule tab for this environment. Depending on your screen resolution, this may be hidden in the "More" drop-down. On this tab, click the "Launch" button.

Joule will open in a new tab and we can prompt it to test the agent, for example like this: "Run the Hello World agent."

To confirm that Joule actually called the agent, you can investigate the log by clicking on the icon in the top right of the title bar.

Conclusion

Congratulations, you just implemented your first Joule agent! As intended, the overall result is "just" a Hello World agent, but this is an important first step in your journey to becoming a Joule agent builder. You familiarized yourself with the UI and performed the full workflow from start to finish, including creating a project, creating an agent, testing, and deploying it. Along the way, we also used Joule itself to fill in the agent's configuration details.

From here, there are many more topics worth exploring, like Joule skills, MCP integration, or agent-to-agent communication. However, for me, it's always important to build a Hello World example first without getting lost in the details. With more complex starter scenarios, it's easy to get stuck on technical details and lose sight of the big picture. Now that you've completed your "Hello World", you can iteratively add more features and build more sophisticated agents. What's the first use case you're going to tackle?

SAP Joule for Consultants (J4C): A Strategic Overview

2026-02-11T13:56:47.976000+01:00

SAP Joule for Consultants (J4C): A Strategic Overview

SAP Joule represents a significant advancement in SAP’s generative AI strategy, offering a suite of role-based variants including those for end users, developers, and specific line-of-business processes. Among these, Joule for Consultants (J4C) is uniquely engineered for SAP delivery organizations and system integrators. Operating as a standalone capability within SAP Business AI and powered by SAP BTP, J4C is designed to address the historical fragmentation of SAP knowledge by providing a centralized, conversational interface for expert-curated content.

Positioning of Joule for Consultants within the SAP Business AI ecosystem.

Figure 1: Positioning of SAP Joule for Consultants

Core Differentiators and Technical Grounding

Unlike generic AI tools, J4C is trained and grounded in SAP’s authoritative, non-public knowledge assets. This ensures that recommendations remain aligned with "clean core" principles and current product roadmaps.

Exclusive Knowledge Base: J4C utilizes terabytes of gated content, including SAP Notes, Knowledge Base Articles (KBAs), and SAP Activate implementation guides.
Methodological Context: The system natively understands consulting terminology, such as SAP Activate phases and Fit-to-Standard constructs.
Code Intelligence: It leverages a fine-tuned ABAP model trained on millions of lines of code to explain legacy logic and identify dependencies during system conversions.

The J4C reasoning layer integrates diverse SAP data sources to support consultant prompts.

Figure 2: J4C knowledge flow

Strategic Benefits and Implementation Considerations:

Integrating J4C into delivery methodologies offers several measurable advantages, though it requires careful organizational planning.

Key Benefits:

Accelerated Delivery: Reduces the time required to locate authoritative answers during discovery and design.
Risk Mitigation: Grounding responses in SAP best practices minimizes the likelihood of design deviations and subsequent rework.
Scalability: Acts as a continuous enablement layer, allowing junior consultants to access senior-level insights without constant escalation.
Standardization: Ensures a consistent interpretation of SAP guidance across global engagements.

Critical Considerations:

Commercial Readiness: Deployment requires specific SAP AI Unit entitlements and technical BTP configuration.
Accountability: J4C serves as a guide; final design decisions and project governance remain the responsibility of the consultant.
Dynamic Coverage: While extensive, the depth of information may vary by specific solution area and release version.

SAP J4C in action:

Log on to SAP J4C as shown:

Figure 3: Login

Ask relevant query:

Figure 4: Query

The answer as shown:

Figure 4: Response

Grounded in SAP Data:

Figure 5: Guardrails and Grounding

Future Evolution

The roadmap for J4C focuses on transitioning from a conversational assistant to an agentic consulting copilot. This evolution includes automated guidance for SAP Activate deliverables and proactive design validation.

In summary, J4C is an essential tool for the modern SAP consultant, providing a structural advantage in speed, quality, and consistency for complex enterprise transformations.

Unlock the Power of People Management with Joule

2026-02-13T03:05:34.326000+01:00

In the modern workplace, managers face growing challenges in fostering team development, improving performance, and identifying future leaders. SAP’s Joule introduces the People Manager Assistant—a role-specific AI tool designed to empower managers to efficiently support their teams.

The People Manager Assistant goes beyond typical management tools. It uses intelligent analysis of employee data, feedback, and performance reviews to pinpoint areas for improvement. By providing proactive insights on development goals, personalized growth plans, and succession planning timelines, this assistant helps managers streamline the talent development process. Imagine being able to foster employee growth with precision while saving valuable time to focus on strategic leadership.

Whether creating clear development roadmaps or analyzing workforce performance, the People Manager Assistant turns complex people-related decisions into actionable intelligence. It's not just about managing teams—it's about empowering them. With Joule managers can inspire growth, prioritize team alignment, and drive performance like never before.

Let’s look at an example of an AI Assistant in action:

Disclaimer: The names used in the following story are fictional, and any resemblance to actual persons is purely coincidental.

Christine’s potential needed direction, so her manager, Alex, tapped the People Manager Assistant for insights. The assistant identified key growth areas and crafted actionable goals. Later, Tara was assessed for succession, revealing promise with development needs. In minutes, structured plans were created, ensuring growth and leadership continuity for the organization.

Summary:

• Joule empowers faster decision-making and streamlines workflows using harmonized data and trusted architecture.
• Role-specific AI assistants offer tailored support to handle complex tasks efficiently in various business functions.
• The People Manager Assistant analyzes employee data to develop growth plans, identify successors, and enhance team performance.
• Joule Agents deliver measurable improvements, optimizing productivity across areas like HR Operations and Accounts Receivable Management.

AI’s Role in Organizational Change Management

2026-02-13T16:32:59.319000+01:00

Let's be honest: most change managers spend more time maintaining spreadsheets than having the conversations that matter or leveraging their empathy and personal skills. AI won't replace OCM—but it can handle the pattern-heavy work, freeing you for strategy, coaching, and navigating organizational dynamics. This post explores how AI augments the six core OCM dimensions in SAP transformations, based on our real project experience.

As part of the OCM Digital Change and Adoption team within SAP’s Consulting Services organization, we lead SAP Organizational Change Management in various SAP transformations. We recognize that Artificial Intelligence (AI) is reshaping also our work —introducing new opportunities and challenges across how we plan, lead, and sustain change. This post explores how AI could influence our Organizational Change Management (OCM) approach in SAP transformations and beyond.

Importantly, these are practitioner perspectives—not product announcements. Our intent is to share how we see the six OCM dimensions evolving, based on our project experience. To keep the focus on opportunities, we deliberately set aside topics such as GDPR[1] and AI ethics here—though they remain essential considerations in practice.

As OCM practitioners, we advise our customers throughout their transformation journeys. Our approach is aligned to the SAP Activate methodology and addresses six core dimensions, underpinned by data-driven solutions.

Below, you’ll find each dimension, how we apply it today, and how AI could augment it. For clarity, we’ve included a graphic of the six OCM dimensions here.

Impact key:

🟩 Medium: Broader acceleration and decision support
🟦 Medium to High: Significant scaling and personalization potential
🟪 High: Step-change in effectiveness and proactivity

🟦 Change Strategy sets direction, aligns stakeholders, and prioritizes the people side of the transformation.
Today: We tailor the change approach to your program context, define scope and outcomes, map stakeholders, and plan governance, milestones, and enablement strategies using SAP good practices.
With AI: We auto‑draft change strategies, stakeholder snapshots, and governance calendars from your business case, project charter, and discovery notes; synthesize interview transcripts into themes and risks; and run scenario comparisons to test plan options. AI also generates first‑cut decks and exec summaries that consultants refine with context.
Impact: Faster strategy and planning cycles, clearer stakeholder alignment early on, and fewer mid‑stream rework loops.

🟩 Change Leadership helps sponsors and managers lead with clarity, consistency, and credibility.

Today: We align leadership on vision and roles, map stakeholders, and equip sponsors with engagement plans, talking points, and routines that sustain momentum.
With AI: We analyze stakeholder networks and sentiment to identify influencers and resistance patterns, recommend an optimal change network for your context, and generate sponsor briefings tailored by audience and region. AI also suggests targeted outreach sequences and tracks follow‑through.
Impact: Faster stakeholder mapping, higher sponsor visibility and touchpoints, earlier detection of at‑risk groups. Which can improve confidence and speed of leadership action.

🟪 Change Communication helps you keep stakeholders informed, engaged, and aligned throughout the transformation.

Today: We craft communication plans, key messages, and stakeholder-specific content based on persona analysis and project milestones.
With AI: We can generate personalized newsletters, FAQs, and leadership talking points in multiple languages and formats, whatever fits the project. E.e. leverage transcripts of AMA Sessions to create a blog in your sharepoint incl a Q&A list. AI analyzes and summarizes sentiment from your employee feedback channels to adjust messaging before resistance escalates.
Impact: Faster and more personalized content creation, higher engagement rates, real-time neutral sentiment tracking.

🟩 Change Realization turns strategy into targeted actions that move people from current to future ways of working.

Today: We assess process, role, and location impacts; prioritize change measures; and coordinate workshops to translate findings into concrete action plans.
With AI: We accelerate impact analysis from design assets and process maps, cluster similar impacts across your units, and auto‑draft tailored action plans and playbooks fitting for your project—reducing reliance on lengthy manual workshops while preserving expert review.
Impact: Faster impact‑to‑action cycle, fewer workshop hours, clearer prioritization across roles and regions. So that the projects change activities translate into visible progress sooner.

🟦 Change Enablement equips teams and end users with the skills and confidence to adopt new solutions and processes.

Today: We design learning strategies, build curricula, and deliver role‑based training, job aids, and hypercare support aligned to milestones.
With AI: We generate role‑specific learning paths, adapt content to proficiency and language, create just‑in‑time guidance, and use usage data to recommend next‑best learning, tailored to your needs, for this you can use SAP’s Learning Needs Analysis (LNA) microapp. AI generates drafts automatic from sources such as Signavio, SAP Best Practices or CALM. In the flow of work, you can combine this with WalkMe Learning Arc (where available) to deliver in‑app, role‑aware walkthroughs and micro‑learning that reinforce new behaviors at the point of need. AI also drafts quizzes, simulations, demos, exercises and scenario‑based practice from source materials and managed via Prompts.
Impact: Faster content creation, easier content updates, higher course completion and satisfaction, reduced time‑to‑competence post go‑live. This can improve the adoption where it matters most in the project.

🟪 Change Effectiveness ensures change activities deliver outcomes and remain sustainable over time.

Today: We define KPIs, collect feedback, run health checks, and apply corrective actions based on adoption, performance, and sentiment trends.
With AI: We combine digital adoption checks, benchmarks, and pattern detection to spot emerging risks, forecast slippage, and recommend targeted interventions before issues escalate. AI evaluates and summarizes your feedback channels and explains variance across different sites or roles in your company.
Impact: Risks identified several weeks earlier before they impact your project value, fewer late‑stage escalations, continuous, fact based adoption insights with numbers.

With these six dimensions, you can transition from the status quo to future-ready ways of working more smoothly —so you can realize the full value of your SAP solutions. AI doesn’t replace the human side of change; it amplifies it. It can free consultants and customers to focus on higher-value activities: judgement, alignment, personalization and leadership.

This post reflects our experience and practitioner view of where AI can deliver value today.Agentic AI might even bring more oppportunities.While we intentionally focus on possibilities here, topics such as GDPR, security, and responsible AI are non‑negotiable in delivery and must be addressed in any implementation.

In our next blog post, we’ll dive deeper into the AI × OCM opportunities from a change manager’s perspective, sharing concrete use cases and practical recommendations.

Let us know what you think—we’d love to hear your perspective and experiences.

[1] GDPR: General Data Protection Regulation (DSGVO in German)

POV on How to Approach Custom Agents in the Enterprise - Blog Series

2026-02-14T00:45:50.136000+01:00

You've invested in AI agents across your enterprise - some from SAP, others from your broader tech stack. But as your AI ecosystem grows, so does a critical question: how do I approach my use cases strategically across this diverse landscape?

This blog addresses that question by addressing several POVs on how you can approach your AI agentic use cases both with SAP and non-SAP.

The POVs I will focus on are:

Read BEFORE the POVs:

You first need to understand when you would require a custom agent as there is always additional governance and build effort associated with maintaining an agent’s lifecycle.

SAP recommends that custom agents or agent extensions should only be created when your prioritized use case does not already exist out-of-the-box (OOTB). How would you know if it exists OOTB? Easy! Our SAP Discovery Center contains an AI Catalog that you can filter by solution and/or business area to see what Agents and Embedded AI capabilities are available for out-of-the-box use.

Image taken from AI Catalog

If the agents meet partial or no requirements, then it is safe to say you can create a custom agent extension.

What will you get out of this Blog Series?

By the end of this blog, you'll understand how to approach your AI agent strategy - from leveraging existing SAP capabilities to building custom solutions that integrate and orchestrate collaboration between SAP and non-SAP agents across your enterprise landscape.

Click to begin reading POV 1 - Creating Custom Agents in SAP.

POV 1: Create Custom Agents in SAP (Part 1/4)

2026-02-14T00:46:44.476000+01:00

This Blog is Part 1 of a Blog Series (4 Parts!). Click on the following to navigate back to the main menu of POV on How to Approach Custom Agents in the Enterprise - Blog Series.

POV 1: Create Custom Agents in SAP

If your business requirements cannot be fulfilled with the out-of-the-box SAP Joule Agents and you wish to use SAP data for your custom agent, then SAP Build's Joule Studio Agent Builder is the recommended solution.

In Joule Studio Agent Builder, you can use no-code/low-code as well as natural language prompting (through embedded Vibe Coding) to create custom Joule skills and Joule Agents. As a reminder, Joule skills are deterministic meaning they will be able to complete a specific task relatively quickly. Joule agents, on the other hand, reason and problem solve across multi-step scenarios within a defined business domain.

Image taken from Joule Studio Agent Builder; showcasing embedded Vibe Coding used to create a custom Restocking Agent. Source

Why would you want to create SAP agents within SAP?

SAP knows SAP best - Joule is the agent orchestrator that allows it to be proactive and is deeply connected to business context and deep domain knowledge. SAP's business context is the "magic" of joule that helps determine the sequence and which agents or tools to use. SAP Agents will always have the business context to understand what is being asked of them and how to answer, therefore resulting in more reliable and relevant responses.
Controlled Enterprise-wide Governance - Joule is strictly role based. Meaning it is tightly integrated across the SAP security landscape through BTP's Cloud Identity Service (CIS) - which manages user authentication and access between your apps and Joule. For example, if Joe with US specific Finance roles & authorizations (R&A) is given access to a custom agent containing world-wide Finance info, Joe will only see financial data/information relevant to the US as per his assigned R&A. Similarly, Joe will be able to prompt Joule regardless of the SAP cloud application, if he has access. For example, if he has access to S/4HANA Cloud, SuccessFactors, and Work Zone - he will be able to use any app’s Joule interface to prompt it. Joule’s security landscape results in responsible responses across the SAP landscape. Please see the Architecture Diagram for detailed architecture of Joule Studio and CIS.
Connect non-SAP data - Joule allows you to connect non-SAP data sources using APIs, as well as grounded external/internal documents allowing you to blend non-SAP and SAP data with your grounded policies and documentation.

In short, creating an SAP Agent outside of SAP will result in additional effort to rebuild business context and security.

Next POV?

To check out Part 2 of the Blog Series click: POV 2 - Agent to Agent Collaboration with SAP and non-SAP Agents.

Or click on the following to navigate back to the main menu of POV on How to Approach Custom Agents in the Enterprise - Blog Series.

Source: Blog by Michael on Joule Agent Builder

Source: Blog by Amit Bangora on Joule Skill Build

POV 2: Agent to Agent Collaboration with SAP and non-SAP Agents (Part 2/4)

2026-02-14T00:55:30.928000+01:00

This Blog is Part 2 of a Blog Series (4 Parts!). Click on the following to navigate back to the main menu of POV on How to Approach Custom Agents in the Enterprise - Blog Series.

POV 2: Agent to Agent Collaboration with SAP and non-SAP Agents

*A2A Interoperability Coming Soon in 2026

In some cases, you may want to leverage your non-SAP Agents with SAP agents. As discussed in POV 1, bringing SAP data outside of SAP will result in challenges in security, governance, and business context - compromising the agent’s responsibility, relevance, and reliability.

This is a great opportunity to combine the best of both worlds - SAP & non-SAP Agents through Agent-to-Agent collaboration.

How? The A2A open protocol, developed by Google, handles inter-agent communication allowing agents, regardless of their vendor, to communicate complex tasks. Many of you may have already heard of MCP (Model Context Protocol), however if you would like a refresh – check out this blog by Pramod. It is important to note that A2A does not replace MCP but rather works alongside it. Think of A2A as the communication handler between agents where one agent assigns a subtask to another and the MCP enables the agents with the right tooling to complete the task. Using A2A with MCP enables autonomous AI agents regardless of if they are SAP or non-SAP.

From SAP the key orchestrator of agent collaboration is Joule, as discussed in POV 1, where it orchestrates the sequencing of tasks and workflows using deep domain knowledge and business context. What does this mean in terms of what autonomous agent-to-agent collaboration can achieve between SAP and non-SAP?

Agents are Discoverable - AI Agents will have discoverable endpoints that will be captured in the SAP AI Agent catalog acting as an adapter between SAP and non-SAP agents. As per the diagram below there will be an auto-assigned ORD (capture agent metadata) to ensure the Agent is discoverable. Through this, Joule will know what the agents can do to ensure the right one is selected to complete a task. (see architecture diagram below)
Delegate tasks/artifacts - There are 2 types of agents to facilitate A2A communication: a client agent and remote agents where the client agent sends the task (eg. prompt or system triggered) and the remote agent receives the task, matches the tools, and executes the task. A2A is designed to be task-oriented and with the combination with its discoverable endpoints and deep domain knowledge, business context, Joule will understand how to orchestrate internally and with external agents.
Operate securely and interoperable across systems - As per the diagram below, all external agents will be routed through the Agent Catalog making them discoverable and preventing direct exposure of SAP Agents to external agents. In addition, Agents will have a secure tool layer (Tool catalogue) where agents will have access to tools within trust boundaries that respect security policies.
Scale your enterprise – rather than operating agents in silos, you can now have a connected interoperable agentic ecosystem with distributed functionality/tasks making it easier to scale.

The above image shows A2A Architecture with SAP. For example, a customer service rep receives a billing inquiry in their email. The service rep initiates a dispute resolution process through Joule and engages with a Google Agent (e.g. BigQuery data Source) that retrieves the required data and shares it back to Joule - collaborating to generate insights and resolution recommendations. To see this lab preview A2A scenario in action, check out this github.

Therefore, you can leverage all your investments, SAP & non-SAP, to have a connected Agent ecosystem.

Next POV?

To check out Part 3 of the Blog Series click: POV 3 - Using Integration Suite as Your Governed MCP Server Platform.

Or click on the following to navigate back to the main menu of POV on How to Approach Custom Agents in the Enterprise - Blog Series.

Source: A2A Blog by Google

Source: SAP A2A Architecture

POV 3: Using Integration Suite as Your Governed MCP Server Platform (Part 3/4)

2026-02-14T01:04:11.131000+01:00

This Blog is Part 3 of a Blog series (4 Parts!). Click on the following to navigate back to the main menu of POV on How to Approach Custom Agents in the Enterprise - Blog Series.

POV 3: Using Integration Suite as Your Governed MCP Server Platform *Coming Q2/2026

If you didn't have a chance to tune in to SAP Tech Ed's IN200v | Empower your agents to be responsible (2025) then it is notable that in Q2/2026 SAP Integration Suite's API Management will allow you to apply additional security policies to APIs in your MCP servers and publish your secure APIs with MCP documentation for Agent consumption via the API and MCP Gateway.

Why is this important?

MCP allows agents to access external information for systems, APIs, documents all while reducing agent complexity. In summary, agents with a MCP client will rely on the MCP server to provide structured metadata to the APIs/Protocols. However, these APIs within the MCP server will likely not meet all security requirements and pose some security risk.

With SAP Integration Suite's API and MCP gateway, you will be able to apply additional API Policies around multi-protocol connectivity, routing, transformations (eg. JSON to XML), mapping, traffic management, and security requirements to further secure, monitor and govern your APIs being leveraged as part of your MCP. This will be incredibly powerful for both SAP Agents and non-SAP agents.

Image taken from SAP Tech Ed's IN200v | Empower your agents to be responsible (2025)

How is this relevant to on-premise users?

Users that are on-premise (eg. ECC, S/4HANA on-prem) can leverage Integration Suite to create custom APIs through OData Services or modify prebuilt S/4HANA APIs (see Business Accelerator Hub) and apply additional API policies to reduce security risk. These APIs can then be leveraged in SAP as well as non-SAP agents. However, it is important to consider the rebuild effort of business context and security when accessing SAP data outside of Joule agents (as described in POV 1).

Where else can Integration Suite and SAP help in my Agent Build?

SAP Business Data Graphs! Within Integration Suite you can explore, design, and extend Graph APIs (Odata V4 or GraphQL) for agent consumption.

Think of this as a semantic layer (connecting multiple entities) that sits on top of the API that allows your agent to receive a mix of entities from one central entity - removing the Agent’s effort to combine the entities together.

Graphs are powerful because the projections between data sources (entities) are automatically created between SAP data as SAP leverages the One Domain data model. However, there are also capabilities for developers to extend to non-SAP. Therefore, allowing you to have a simplified semantically rich API ready for Agent consumption with the bonus to apply additional API policies on top of it, resulting in a secure Graph API. For more information on Graph APIs please check out this blog on an Intro to SAP Graphs & Graph in Integration Suite Blog.

An example of this can be seen in the image below that summarizes the demo shown at SAP Tech Ed's IN200v | Empower your agents to be responsible session. You can see that a user prompts an Agent that leverages MCP API tools with additional governance policies applied to the Graph API. This showcases secure and semantically connected data across SAP Risk assessment, Supplier Plant, and Supplier plant materials entities - resulting in higher performing responsible, relevant and reliable AI Agent response.

Source: Graph – SAP Help

Source: Watch Tech Ed sessions on-demand

Next POV?

To check out Part 4 of the Blog Series click: POV 4 - Putting it all Together Across Your Enterprise.

Or click on the following to navigate back to the main menu of POV on How to Approach Custom Agents in the Enterprise - Blog Series.

POV 4: Putting it all Together Across Your Enterprise (Part 4/4)

2026-02-14T01:13:05.033000+01:00

This Blog is Part 4 of a Blog Series (4 Parts!). Click on the following to navigate back to the main menu of POV on How to Approach Custom Agents in the Enterprise - Blog Series.

POV 4: Putting it All Together Across Your Enterprise

Keeping in mind POV 1, 2, and 3 - POV 4 focuses on bringing your enterprise-wide agents together with an additional layer of security and governance.

As discussed, Integration Suite will allow you to create custom APIs - SAP and non-SAP- including Business Data Graph APIs. These can then be further consumed, whether it’s a custom API through SAP or non-SAP or an API that’s part of a MCP server. In other words, both Joule and non-SAP agents will be able to leverage secure governed APIs and MCPs in an interoperable agentic ecosystem.

In simpler words: Integration Suite and Joule Studio will be the key to unlocking secure, governed, and business context rich agent ecosystems.

In Summary

We opened with a critical question: How do you approach your use cases strategically across your diverse AI landscape? The answer lies in three integrated capabilities:

SAP Joule provides the foundation for responsible, reliable and relevant custom agents with Joule through its deep domain knowledge, rich business context, and secure governance capabilities.
Joule can be used for both SAP specific use cases as well as non-SAP Agent collaboration - bringing the best of both worlds together.
Finally, Integration Suite's API management and MCP Gateway capabilities will be key to unlocking an additional powerful security and governance layer for your agents across your enterprise.

This concludes the Blog Series: POV on How to Approach Custom Agents in the Enterprise.

Joule A2A: Connect Code Based Agents into Joule

2026-02-16T14:35:31.791000+01:00

Many organizations began early by developing their own AI agents and assistants, frequently using frameworks such as LangChain and LangGraph. This post demonstrates how a custom-built AI agent can be integrated into the Joule ecosystem by using the recently introduced pro-code extensibility features together with the A2A integration.

For the demonstration, a minimal ReAct agent implemented in Python with LangGraph is used.

The A2A Protocol (Agent2Agent Protocol) is an open standard developed to enable seamless communication and collaboration between autonomous AI agents built by different vendors and on different frameworks. It defines a common interaction model that allows agents to discover each other’s capabilities, exchange structured messages and tasks, and coordinate actions securely without exposing internal state or proprietary logic.

The protocol uses standardized components such as Agent Cards for capability discovery and supports multiple transport bindings including HTTP(S) and JSON-RPC 2.0. A2A is designed with enterprise requirements in mind, supporting asynchronous task workflows, secure communication, and interoperability across diverse agent ecosystems. Find details here.

Many practitioners in the community have already experimented with Joule Studio as the low-code environment for extending Joule. Joule now also provides pro-code extensibility. This expands the addressable scenarios beyond classic skills, enabling more complex logic, deeper structures, richer response shaping, and integration with remote agents via A2A.

Overview of Joule Capabilities

Within the pro-code model, developers define capabilities. A capability groups the "skills" Joule can invoke in response to a user request.

Two concepts are central: scenarios and functions.

A scenario acts as the entry shell of a skill. It contains a name, a description, and a set of input parameters. During skill selection, Joule evaluates the scenario description of the available list of scenarios to pick one. The scenario itself then declares which function should run and which parameters will be filled by Joule.

A function represents the executable logic. It is composed of smaller actions, for example, calling an API, sending or formatting messages, or—now newly—invoking another remote agent.

From an engineering perspective, these artifacts are authored as YAML projects and then deployed to a Joule instance.

To support this workflow, two primary tools are available: the Joule Studio Code Editor extension for Visual Studio Code, and the Joule Studio CLI. The example here focuses primarily on using the CLI.

Now let's go step by step:

Setup

For this exercise, there are two prerequisites:

First, you need to have an instance of Joule base instantiated on one of your BTP Subaccounts. If you do not yet have one, I recommend checking out our great mission around Joule Studio that includes a step to set up a minimal setup of Joule. Ideally, your company already enabled Joule for some of the Cloud applications, and you can utilize that instance. In the mission, they explain how to set up your user with the "enduser" role in BTP. For this exercise, we need some additional roles ("capabilityadmin", "extensibility_developer") as depicted below:

Second, to engage in the Pro-Code extensibility, you want to have the Joule CLI installed. Here I recommend checking out the newly released Joule Developer documentation on help.sap.

To log in against your Joule application, there are some additional steps necessary. We need to collect a set of client credentials. Since Joule is based on the new Cloud Identity Services flow, this involves a few extra steps.

On your BTP Subaccount where you set up Joule, you trusted an IAS tenant—found under Trust Configuration. You will need to navigate to its Admin Panel by appending /admin to the tenant URL.

2. Create new Application:

In the IAS admin panel, navigate to "Application & Resources" > "Applications". In there, you see a full list of all registered applications on that IAS tenant. Now we need to create a new one by hitting "Create" (highlighted in red). In the pop-up, we give it any name, select OpenID Connect, and leave the rest of the fields as is.

3. Add Joule application as a dependency:

Once the Application is created, we need to add a Dependency to that Application. For that purpose, we select the newly created application and navigate to "Dependencies". By clicking on "Add" we will be able to add a new one. In the pop-up, we need to give it the name "CLI2Joule". This name is mandatory. Next, we select the Joule application—you will recognize your subaccount name after the "das-ias". Finally, we can select the API and hit "Save".

4. Create Client Secret:

The following step will be to navigate to "Client Authentication", still under your own created app. We want to add a new Secret by clicking "Add". Giving it an arbitrary name and ticking all the boxes will lead to its creation:

Now with that, we have all the necessary details to log in to Joule:

joule login -a https://.accounts.cloud.sap --apiurl https://.eu10.sapdas.cloud.sap -c  -s  -u  -p  --store-password

Note: The Authentication URL is the Domain of your IAS tenant, so you can easily copy it from the admin panel's URL. While the API URL is the URL of Joule, so when opening up your Joule application from the BTP, you can copy that one:

1. Building the Agent with LangGraph

The first step in this journey is to build an AI agent and expose it via an A2A server. For this purpose, I am using the samples provided directly by the A2A project on GitHub.

Since LangGraph is a popular framework, I am using the LangGraph sample code here. However, you could replace it with any framework you prefer. Similarly, the programming language is flexible: A2A only defines the endpoint structure and schema. You can expose A2A servers using any technology you like. Sample code is available for a variety of languages, including Node.js and Java. For my demonstration, I am using Python deployed on SAP Cloud Foundry.

My project structure, adapted for deployment on Cloud Foundry, looks like this:

app/
├── agent.py
├── agent_executor.py
├── app.py
├── manifest.yaml
├── requirements.txt
├── runtime.txt
└── test_client.py

First, let's look at the heart of our project—the agent.py:

import os
from collections.abc import AsyncIterable
from typing import Any, Literal
import httpx
from langchain_core.messages import AIMessage, ToolMessage
from langchain_core.tools import tool
from genaihub.proxy.langchain.openai import ChatOpenAI
from genaihub.proxy.core.proxyclients import getproxy_client
from langgraph.checkpoint.memory import MemorySaver
from langgraph.prebuilt import createreactagent
from pydantic import BaseModel


proxyclient = getproxy_client('gen-ai-hub')
memory = MemorySaver()


@tool
def getexchangerate(
    currency_from: str = 'USD',
    currency_to: str = 'EUR',
    currency_date: str = 'latest',
):
    """Use this to get current exchange rate.


    Args:
        currency_from: The currency to convert from (e.g., "USD").
        currency_to: The currency to convert to (e.g., "EUR").
        currency_date: The date for the exchange rate or "latest". Defaults to
            "latest".


    Returns:
        A dictionary containing the exchange rate data, or an error message if
        the request fails.
    """
    try:
        response = httpx.get(
            f'https://api.frankfurter.app/{currency_date}',
            params={'from': currencyfrom, 'to': currencyto},
        )
        response.raiseforstatus()


        data = response.json()
        if 'rates' not in data:
            return {'error': 'Invalid API response format.'}
        return data
    except httpx.HTTPError as e:
        return {'error': f'API request failed: {e}'}
    except ValueError:
        return {'error': 'Invalid JSON response from API.'}


class ResponseFormat(BaseModel):
    """Respond to the user in this format."""
    status: Literal['inputrequired', 'completed', 'error'] = 'inputrequired'
    message: str


class CurrencyAgent:
    """CurrencyAgent - a specialized assistant for currency conversions."""


    SYSTEM_INSTRUCTION = (
        'You are a specialized assistant for currency conversions. '
        "Your sole purpose is to use the 'getexchangerate' tool to answer questions about currency exchange rates. "
        'If the user asks about anything other than currency conversion or exchange rates, '
        'politely state that you cannot help with that topic and can only assist with currency-related queries. '
        'Do not attempt to answer unrelated questions or use tools for other purposes.'
    )


    FORMAT_INSTRUCTION = (
        'Set response status to input_required if the user needs to provide more information to complete the request.'
        'Set response status to error if there is an error while processing the request.'
        'Set response status to completed if the request is complete.'
    )


    def init(self):
        self.model = ChatOpenAI(
            proxymodelname='gpt-4o-mini', 
            proxyclient=proxyclient,
            temperature=0            
        )
        self.tools = [getexchangerate]


        self.graph = createreactagent(
            self.model,
            tools=self.tools,
            checkpointer=memory,
            prompt=self.SYSTEM_INSTRUCTION,
            responseformat=(self.FORMATINSTRUCTION, ResponseFormat),
        )


    async def stream(self, query, context_id) -> AsyncIterable[dict[str, Any]]:
        inputs = {'messages': [('user', query)]}
        config = {'configurable': {'threadid': contextid}}


        for item in self.graph.stream(inputs, config, stream_mode='values'):
            message = item['messages'][-1]
            if (
                isinstance(message, AIMessage)
                and message.tool_calls
                and len(message.tool_calls) > 0
            ):
                yield {
                    'istaskcomplete': False,
                    'requireuserinput': False,
                    'content': 'Looking up the exchange rates...',
                }
            elif isinstance(message, ToolMessage):
                yield {
                    'istaskcomplete': False,
                    'requireuserinput': False,
                    'content': 'Processing the exchange rates..',
                }


        yield self.getagentresponse(config)


    def getagentresponse(self, config):
        currentstate = self.graph.getstate(config)
        structuredresponse = currentstate.values.get('structured_response')
        if structured_response and isinstance(
            structured_response, ResponseFormat
        ):
            if structuredresponse.status == 'inputrequired':
                return {
                    'istaskcomplete': False,
                    'requireuserinput': True,
                    'content': structured_response.message,
                }
            if structured_response.status == 'error':
                return {
                    'istaskcomplete': False,
                    'requireuserinput': True,
                    'content': structured_response.message,
                }
            if structured_response.status == 'completed':
                return {
                    'istaskcomplete': True,
                    'requireuserinput': False,
                    'content': structured_response.message,
                }


        return {
            'istaskcomplete': False,
            'requireuserinput': True,
            'content': (
                'We are unable to process your request at the moment. '
                'Please try again.'
            ),
        }


    SUPPORTEDCONTENTTYPES = ['text', 'text/plain']

In this code snippet, several key elements are visible. First, the a2a-sdk is heavily utilized, providing the base class for the AgentExecutor. This serves as the main interface for exposing an agent through the A2A SDK. Its primary method is execute, which receives a task from the A2A client, including context and task details, passes it to the agent, and processes the response. The SDK also handles sending intermittent updates and requesting user input as needed.

Finally, there is the transport layer. The app.py file exposes the Agent Card at the well-known endpoint and manages incoming requests. Here, the transport protocol can be chosen, with the default set to JSON-RPC.

import httpx
import os
from a2a.server.apps import A2AStarletteApplication
from a2a.server.request_handlers import DefaultRequestHandler
from a2a.server.tasks import (
    BasePushNotificationSender,
    InMemoryPushNotificationConfigStore,
    InMemoryTaskStore,
)
from a2a.types import (
    AgentCapabilities,
    AgentCard,
    AgentSkill,
)
from agent import CurrencyAgent
from agent_executor import CurrencyAgentExecutor

Get host and port from environment variables (Cloud Foundry sets PORT)
HOST = os.getenv('HOST', '0.0.0.0')
PORT = int(os.getenv('PORT', 10000))

Create agent capabilities and card
capabilities = AgentCapabilities(streaming=True, push_notifications=True)
skill = AgentSkill(
    id='convert_currency',
    name='Currency Exchange Rates Tool',
    description='Helps with exchange values between various currencies',
    tags=['currency conversion', 'currency exchange'],
    examples=['What is exchange rate between USD and GBP?'],
)


agent_card = AgentCard(
    name='Currency Agent',
    description='Helps with exchange rates for currencies',
    url=f'http://localhost:443', # is ignored by the Joule A2A integration - instead the URL from the destination is taken
    version='1.0.0',
    defaultinputmodes=CurrencyAgent.SUPPORTEDCONTENTTYPES,
    defaultoutputmodes=CurrencyAgent.SUPPORTEDCONTENTTYPES,
    capabilities=capabilities,
    skills=[skill],
)

Create request handler and server
httpx_client = httpx.AsyncClient()
pushconfigstore = InMemoryPushNotificationConfigStore()
push_sender = BasePushNotificationSender(
    httpxclient=httpxclient,
    configstore=pushconfig_store
)


request_handler = DefaultRequestHandler(
    agent_executor=CurrencyAgentExecutor(),
    task_store=InMemoryTaskStore(),
    pushconfigstore=pushconfigstore,
    pushsender=pushsender
)


server = A2AStarletteApplication(
    agentcard=agentcard, 
    httphandler=requesthandler
)

Export the ASGI app for uvicorn
app = server.build()

Again, this is mostly boilerplate code provided by the A2A SDK. We populate the Agent Card with the specific information for our use case and ensure that requests are handled appropriately. To do this, we instantiate the DefaultRequestHandler.

Finally, let's look at the files that enable deployment. The manifest.yaml facilitates deployment by providing configuration settings and the startup command:

applications:
  - name: currency-agent
    memory: 512M
    disk_quota: 1G


    buildpacks:
      - python_buildpack


    env:
      # Add your SAP AI Core credentials here
      AICOREAUTHURL: ""
      AICORECLIENTID: ""
      AICORECLIENTSECRET: ""
      AICORERESOURCEGROUP: ""
      AICOREBASEURL: ""


    command: uvicorn app:app --host 0.0.0.0 --port ${PORT}

I am using the python_buildpack in conjunction with a specific Python version specified in the runtime.txt. Since we are utilizing the foundation models of the generative AI hub of AI Core, we also ensure to pass on our credentials via environment variables.

runtime.txt:

python-3.13.9

This is necessary because the dependencies only support Python versions greater than 3.12, while Cloud Foundry currently uses an earlier version by default.

With this structure in place, the agent can be deployed to Cloud Foundry. Alternatively, it can be hosted in any other environment of your choice. Ensure to update the Agent Card with your specific URL.

2. Building the Joule Pro-Code Capability

For this example, I prepared a minimal directory and code structure that you can utilize:

currencyagentcapability/
├── functions/
│   └── currencyagentfunction.yaml
├── scenarios/
│   └── currencyagentscenario.yaml
└── capability.sapdas.yaml

Let's start with capability.sapdas.yaml. It describes the overall capability with some descriptions, defines the version of the design-time artifacts, and lets us configure the Destination mapping against the system alias.

schema_version:  3.27.0   # be aware of the minimum version for agents


metadata:
  namespace: joule.ext    # very important to be in the "joule.ext" namespace for capabilities
  name: currencyagentcapability
  version: 1.0.0
  display_name: Currency Agent Capability
  description: Capability containing the currency agent


system_aliases:
  CURRENCY_AGENT:
    destination: CURRENCY_AGENT # this is referencing the destination name

For our example, it is important to use version 3.27.0 onwards, since this is the minimum version for the Agent integration. In addition, we specify the namespace. Here we need to use the extension namespace joule.ext; other namespaces will fail.

At the bottom, we register a system alias and map it to a destination—both of which I call CURRENCY_AGENT. The destination will be named accordingly in the subsequent step in BTP.

Next, we introduce the scenario for our agent.

currencyagentscenario.yaml

description: The Currency Agent supports converting between different currencies.
target:
  name: currencyagentfunction
  type: function

It basically consists of the description and the target—in this case, the currencyagentfunction. Additionally, one could maintain parameters that would be collected by the Joule Orchestrator. For our particular case, for example, we could maintain a currency pair and an amount to convert. In addition, if your agent is handling multi-turn conversations, you might want to pass the conversation ID to it via the context.

Finally, the function:

currencyagentfunction.yaml

action_groups:
  - actions:
      - type: agent-request   # This action type allows the agent to trigger an agent
        systemalias: CURRENCYAGENT # The system alias is defined in the capability.sapdas.yaml file and points to the destination of the agent
        agent_type: remote # remote for code based agents
        result_variable: "apiResponse" # response of the agent - can be used in subsequent actions by referring to the variable name   
      - type: message
        message:
          type: text
          content: "<? apiResponse.body.artifacts[0].parts[0].text ?>"  # extracting textual response from the agent

In here, we define actions, and the most important one is the agent-request. It will invoke the Agent via the A2A integration. We specify the system alias, the type as remote, and which variable should hold the response.

Note: The response from the agent now needs to be "formatted" in this function.

In this super minimalistic case, I just output the result body in a static message sent to the user.

Understanding the Joule Agent Result Variable

When working with the agent-request action, the result_variable is the connection between the output of the agent and the formatting of the response to Joules Webclient. In that result variable we have the following:

Key Components of the Response

* Body: The core container for the task data. * History: A log of the conversation turns between the user and the agent. * Artifacts: The final, structured answers or generated content. * Status: The current state of the task (e.g., completed).

Example

Below is a sample JSON payload returned by a Joule agent after a currency conversion request:

{
  "headers": {},
  "body": {
    "kind": "task",
    "contextId": "98fa8d22-0e99-4efe-a1a9-fff535e7db9d",
    "history": [
      {
        "role": "user",
        "kind": "message",
        "parts": [{"kind": "text", "text": "Please convert 10 USD to euros"}],
        "messageId": "eb8b5afa-63cb-4cc5-9b24-38f85e782c95"
      },
      {
        "role": "agent",
        "kind": "message",
        "parts": [{"kind": "text", "text": "Looking up the exchange rates..."}]
      }
    ],
    "id": "f0d78896-0eab-472f-8a85-73050948c0a2",
    "artifacts": [
      {
        "name": "conversion_result",
        "parts": [
          {
            "kind": "text",
            "text": "10 USD is approximately 8.43 EUR based on the current exchange rate."
          }
        ],
        "artifactId": "b8d6c02b-1646-4676-969b-ca07f7df2af0"
      }
    ],
    "status": {
      "state": "completed",
      "timestamp": "2026-02-16T11:45:20.883269+00:00"
    }
  }
}

Extracting Specific Information

Developers can use simple dot-notation scripting to drill down into this variable and extract specific data for the UI.

Example: To grab the final conversion text from the JSON above, you would navigate the path:

apiResponse.body.artifacts[0].parts[0].text

This allows you to bypass the background "thought" process or status updates and display only the exact information the user is looking for in a clean, conversational message.

3. Destination Creation

To bridge Joule with our remote Python agent, we need to establish a connection via the SAP BTP Destination Service. This follows the standard procedure for creating an HTTP destination within your BTP Subaccount.

In the BTP Cockpit, navigate to Connectivity > Destinations and create a new destination with the following details:

Name: CURRENCY_AGENT (This must match the system alias we defined in our capability YAML).
Type: HTTP
URL: The base URL where your agent is hosted (e.g., your Cloud Foundry app URL).
Proxy Type: Internet
Authentication: For this demonstration and to keep things simple, I have selected NoAuthentication.

The A2A integration handles the heavy lifting of discovery. When Joule triggers the agent request, it uses the URL provided in this destination to locate the well-known.json path (the discovery endpoint) of your agent.

From there, Joule retrieves the Agent Card, identifies the specific communication URL defined within that card (+ preferred protocol), and subsequently initiates A2A-compliant messaging to send tasks and receive responses from your agent.

4. Deploy the Joule Capability

Now that the Joule capability is built and the destination is configured to point toward our agent on Cloud Foundry, we can bring everything together. To do this, we will use the Joule CLI to deploy the capability to our instance.

Deployment Workflow

The Joule CLI handles the lifecycle of your capability through three main phases:

Authentication: Use joule login to authenticate with the specific Joule instance where you want to deploy.
Compilation: The source files must be compiled into a .daar file (Design-time Artifact Archive), which is the deployable format Joule requires.
Deployment: The archive is uploaded and registered to the assistant.

Compile and deploy can be combined with the following command:

joule deploy -c -n ""

-c (Compile): Tells the CLI to first package your YAML files into the .daar format.
-n (Name): By specifying a bot name, you are creating a standalone assistant for testing purposes.

Sample Output:

joule deploy -c  -n "currencyagenttest"
✔ Building designtime artifact (currencyagentcapability)
✔ Trigger compilation (C:\Github\joule-code-based-agent-sample\currencyagentcapability)
✔ Compiled (C:\Github\joule-code-based-agent-sample\currencyagentcapability)


Detailed logs:
WARNINGS:
Message:             DTA did not define an optional i18n folder
Path:
Category:            I18N
Severity:            LOW


✔ Downloaded runtime artifact (joule.extcurrencyagentcapability1.0.0.daar)
✔ Building runtime artifact
  > joule.extcurrencyagentcapability1.0.0.daar added to the RTA
✔ Triggering deployment (currencyagenttest)
✔ Your digital assistant (currencyagenttest) deployed successfully

That would have deployed my currencyagenttest assistant that I can then launch.

Note: Test Assistant vs. Production Update

By default, Joule uses the sap_digital_assistant for live enterprise scenarios. (Also when opening Joule with /joule) When you are first developing, using joule deploy -n allows you to test your logic in a isolated "sandbox" assistant without affecting the standard content.

Once you are ready to move your capability into the main environment alongside SAP's standard content, you would typically use:

joule update "sapdigitalassistant" --capability-file capability.sapdas.yaml

This command pushes your capability into the existing sapdigitalassistant rather than creating a new standalone bot.

Launching the Assistant

After a successful deployment, the CLI will provide a URL to access your new assistant. When you open this link, you will see the assistant name reflected in the URL path.

joule launch "currencyagenttest"
✔ Launching: https://joule-pro-code-9r3t5r7a.eu10.sapdas.cloud.sap/webclient/standalone/currencyagenttest

From here, you can begin interacting with your custom LangGraph agent directly through the Joule interface.

Conclusion

Finally, we can test our agent directly from within Joule. For this example, I am using a standalone Joule instance. With the necessary end-user role assigned to my user, I can open the Joule web client and ask Joule for a currency conversion:

As you can see, the scenario is selected, the function is executed, and the agent request action delegates the call to my LangGraph agent deployed on Cloud Foundry. The response is generated there and sent back to Joule. Find the full code on Github.

Nice! This opens up plenty of possibilities for extending Joule with custom-built agents.

I hope you found this insightful. Since this blog covered only a very minimal example, stay tuned for additional posts. There are many topics to dive deeper into, such as authentication flows toward SAP systems via principal propagation, managing the agent context across multi-turn conversations, and response formats beyond simple text.

Reference architectures for developing custom AI solutions in SAP BTP

2026-02-17T16:00:00.044000+01:00

AI is powerful. Architecture makes it scalable.

In our live session, “Reference architectures for developing custom AI solutions in SAP Business Technology Platform,” we’ll cut through the noise and focus on what matters:

AI capabilities across SAP
SAP Business AI and Joule in action
Custom AI development options
Proven reference architectures and use cases

The thing is, customers don’t just want AI features. They want outcomes, automated processes, smarter decisions, measurable impact. And that starts with the right foundation in SAP BTP.

If you’re driving sales, shaping solutions, or delivering implementations, this session will sharpen your AI playbook.

Let’s move from experimentation to enterprise-grade execution.

Register now. https://partneredge.sap.com/en/library/education/psd/2026/jan/e_oe_te_w_PSD_WEB_00012763.html

#SAP #SAPBTP #SAPBusinessAI #Joule #SAPEnablement #AIInnovation

GRC, Trade and Tax in SAP Cloud ERP 2602

2026-02-19T14:07:53.164000+01:00

Hello Experts,

I'm excited to share the update regarding our latest release - GRC, Trade and Tax in SAP Cloud ERP 2602. This update highlights many significant innovations from SAP Risk and Assurance Management, SAP Watch List Screening, SAP Document and Reporting Compliance, as well as SAP Cloud Identity Access Governance.

For a quick overview of the top release highlights for GRC with 2602, you can watch the video below.

Video 1. Release Highlight Video for GRC, Trade and Tax in SAP Cloud ERP 2602

This blog covers the following innovations:

SAP Document and Reporting Compliance

AI-assisted trend analysis and summary for reports (beta)
Embedded analytics to facilitate VAT adjustments
E- verify and Automated Handling of Draft VAT Returns from Authorities
Enabling Electronic Invoices Through KSeF 2.0 for Poland

SAP Risk and Assurance Management

Extended analytical and reporting capabilities: new reporting dashboards with SAP Analytics Cloud, enterprise edition

SAP Enterprise Threat Detection

Intelligent alert handling and investigation recommendations
Management-focused monitoring dashboard

SAP International Trade

Export declaration for plants abroad in the context of Registration for Indirect Taxation Abroad (RITA)

SAP Watchlist Screening

Delta Screening

SAP Document and Reporting Compliance

AI-assisted trend analysis and report summary

Tax accountants often spend significant time validating data by comparing current tax figures with previous returns. To accelerate this process, we introduce AI-assisted trend analysis for VAT returns. This feature helps tax experts by automatically uncovering hidden trends, flagging outliers, and detecting root causes for discrepancies. It provides intelligent summaries that can be used to simplify the approval process and support future audits. This innovation allows the team to move from reactive validation to proactive analysis.

Picture 1. AI-assisted trend analysis and report summary

Value Proposition

Reduce the time needed to interpret VAT data across periods, leading to faster reviews, quicker approvals, and shorter reporting cycles.
Accuracy is improved and compliance risk is reduced. This helps identify anomalies early, minimizing manual errors and lowering the risk of incorrect filings.
Easy to make clear and informative data-driven decisions.

Capabilities

The analysis highlights key trends, fluctuations, and irregularities, and flags values that help to identify potential errors or compliance risks.
Provide concise summary of key VAT insights to support faster reviews, approvals, and decision-making.

Embedded analytics to facilitate VAT adjustments

During the preparation of statutory reports, tax experts require deep visibility into their data to ensure accuracy. With the 2602 release, the 'Manage Tax Items' activity within SAP Document and Reporting Compliance is enhanced with a powerful ''analyze data" option.

This provides tax experts with additional fields and the flexibility to analyze tax data to identify anomalies. Now you can easily see how invoices are mapped to your VAT returns and pinpoint any documents that might have been excluded, enabling seamless adjustments integrated directly with accounting. To further tailor the solution, you can now use extensibility to plug in your own custom analytics CDS views, allowing you to choose between standard SAP-delivered queries or your own defined views for analysis.

Video 2. Embedded analytics to facilitate VAT adjustments

Value Proposition

Advances the VAT review and adjustment by integrating analytics.
Improves accuracy and strengthens compliance through data-driven decisions.
Reduces manual effort and reliance on offline analysis and external tools.
Enhances analytical transparency and enables faster and more confident decision-making.

Capabilities

Embedded analytics within the Manage Tax Items for Legal Reporting application
Direct access to detailed VAT tax line-item records with added data points
Interactive analytical views with charts, filters, and drill-down capabilities
Trend analysis and comparisons across multiple VAT dimensions
Identification of documents for inclusion in or exclusion from VAT returns
Analysis at the point of action without switching applications
Support for efficient VAT reconciliation and compliance preparation

For more information, see: Manage Tax Items for Legal Reporting | SAP Help Portal

E- verify and Automated Handling of Draft VAT Returns from Authorities

A growing number of tax authorities are providing pre-populated, or draft, tax returns based on real-time transactional data. Our latest update helps you automate the handling of these draft returns, ensuring consistency with your company's books. With this feature, you can pull auto-populated returns from an authority's portal and automatically compare them with the returns prepared in your ERP system to identify any mismatches.

Based on the reconciliation results, you can then process actions such as submitting a delta file, accepting, or rejecting the draft. This streamlines the entire process, from review and correction to the submission of the final return.

Video 3. E- verify and Automated Handling of Draft VAT Returns from Authorities

Enabling electronic invoices through KSeF 2.0 for Poland

With the Polish Ministry of Finance enforcing the use of electronic invoices through the KSeF 2.0 platform beginning in February 2026, we are equipping you to meet this mandate head-on. SAP Document and Reporting Compliance now enables you to generate B2B e-invoices in the required XML format from both Finance (FI) and Sales & Distribution (SD), including tax invoices, correction invoices, down-payment invoices, and self-billing invoices. You can submit these invoices interactively to KSeF 2.0, visualize them in a human-readable PDF format with a QR code, and retrieve supplier invoices for automated posting.

Picture 2. Enabling electronic invoices through KSeF 2.0 for Poland

SAP Risk and Assurance Management

Extended analytical and reporting capabilities: new reporting dashboards with SAP Analytics Cloud, enterprise edition

We are introducing the new Risk and Compliance Cockpit, an SAP Analytics Cloud story that gives you an instant, comprehensive overview of your organization's compliance landscape.

This dashboard empowers compliance managers to identify process inefficiencies by visualizing compliance issues organized by type and status, with charts showing trends over time. It makes it easy to compare current performance against historical data, highlight long-term trends, and identify deviations. With insights into average issue resolution times and year-to-year analysis, this single source of truth helps you prioritize critical unresolved issues and improve operational efficiency.

Video 4. Extended analytical and reporting capabilities: new reporting dashboards with SAP Analytics Cloud, enterprise edition

Value Proposition

Get an instant overview of compliance issues, organized by type and status
Improved operational efficiency supported by trend and year-to-year analysis
Charts visualize trends over time
Overview of what to prioritize by highlighting critical unresolved issues

Capabilities

Identify inefficiencies in organizations' processes
Instant overview of compliance issues
Filter business data to examine specific categories of compliance issues
Visual and comparative analysis of data
Compare current performance while highlighting long-term trends and deviations

For more information, see: Risk and Compliance Cockpit

SAP Enterprise Threat Detection

Intelligent alert handling and investigation recommendations

In SAP Enterprise Threat Detection, cloud edition, investigations are the central hub for examining security incidents. This new capability automates and enhances this critical process.

The primary value of this feature is to decrease the manual effort required by SAP monitoring agents and increase their overall efficiency. When an agent prepares an investigation to send to a customer, they are now supported with automatic, case-specific response and mitigation recommendations.

This helps teams by automatically compiling investigation results and formulating suggestions for customers on how to address the alerts. The system intelligently generates these recommendations based on the standard operating procedure of the specific pattern that created the alert, further enhanced by predefined value lists and machine learning functionality. This ensures that the advice provided is both highly relevant and immediately actionable, allowing your security teams to move from detection to resolution faster and more effectively.

Picture 3. Intelligent alert handling and investigation recommendations

For more information, see: Generating Investigation Recommendations

Management-focused monitoring dashboard

We are introducing a powerful new monitoring dashboard within SAP Enterprise Threat Detection, cloud edition, specifically designed for management roles. In today's complex security landscape, having a clear, high-level view of your organization's cyberhealth is not just an advantage; it is a necessity. This new dashboard is for all managers and security leaders who need to quickly understand current security events, alerts, and ongoing investigations to make informed, timely decisions.

It facilitates a deeper understanding of complex security data by offering a comprehensive picture of your system's cyberhealth and protection status. The dashboard also shows the distribution of security events by various criteria, effectively highlighting the most affected systems, patterns, and users to help you focus resources where they are needed most.

To ensure the information is tailored to your specific needs, you can also create your own personalized monitoring pages with a selection of charts that are most relevant to your responsibilities..

Picture 4. Management-focused monitoring dashboard

For more information, see: Using the Monitoring Dashboard

SAP International Trade

Export declaration for plants abroad in the context of Registration for Indirect Taxation Abroad (RITA)

For businesses operating with plants abroad, ensuring the correct export declaration is crucial. In a plant abroad scenario, this feature ensures that the country of the delivering plant, rather than the country of the company code, determines the correct foreign trade organization for the customs declaration. This enhancement improves compliance with international trade regulations for businesses leveraging the "Registration for Indirect Taxation Abroad" (RITA) scope.

Value Proposition

Enhance compliance with trade regulations by ensuring the correct foreign trade organization is used for export declarations.

Capabilities

Manage your export declaration in SAP Global Trade Services using the foreign trade organization within the country of the plant abroad.
Identify plants abroad on pro forma invoice line items by considering countries where registration for indirect taxation (RITA) is enabled.

In SAP Cloud ERP, a billing document exists where goods delivery is performed via a foreign plant, for example, the plant country is different from the country of the company code.

Picture 5. Export declaration for plants abroad in the context of Registration for Indirect Taxation Abroad (RITA)

In SAP GTS, Edition for SAP HANA, the FTO of the corresponding export declaration is now determined based on the legal unit corresponding to the foreign plant used in the billing document.

Picture 6. Export declaration for plants abroad in the context of Registration for Indirect Taxation Abroad (RITA)

For more information, see: Enablement of Plants-Abroad for Export Processing and Foreign Plant

Delta screening with SAP Watch List Screening and manual release of blocked document items

Continuous compliance with sanction party lists is critical. Screening requests sent to SAP Watch List Screening will now remain active for delta screening for up to one month. This means the system automatically performs delta screenings against any changes to watch lists and updates the status of your business partners and documents accordingly, providing automatic coverage without requiring new manual screenings.

Additionally, for situations requiring manual intervention, the "Manage Documents - Trade Compliance" Fiori app now allows authorized users to manually release a trade compliance document item that is blocked. This creates a simple, straightforward, and auditable overrule process to comply with legal requirements while ensuring business continuity.

Picture 7. Delta screening with SAP Watch List Screening and manual release of blocked document items

For more information, see: Integration with SAP Watch List Screening and Delta Screening in SAP Watch List Screening

Watch the replays of our SAP Cloud ERP 2602 Early Release Series!

From January 12-16, we hosted a series of 22 expert-led live sessions to highlight the exciting innovations shipped with the SAP Cloud ERP 2602 release. Missed the live sessions? We've got you covered! Take advantage of the entire series or pick and choose the sessions most relevant to you. You will find the recording and presentation for Artificial Intelligence as well as 21 other topics of interest. Don't miss this chance and watch them on demand–anywhere, anytime.

Find all our assets

We at Cloud ERP and SCM Product Success offer a service as versatile as our product itself. Check out the numerous offerings our team has created for you below:

Don’t hesitate to leave a comment and check out our community page to ask your questions and engage with the experts. Follow the PSCC_Enablement tag to stay up to date with our latest blog posts.

From Conversational AI to Business AI: Why SAP Joule Changes Enterprise Process Execution

2026-02-19T21:12:18.251000+01:00

Generative AI has quickly moved from experimentation to enterprise boardroom discussions. But for SAP consultants, architects, and transformation leaders, the real question is not whether AI can generate content.
The real question is:
Can AI understand enterprise processes, respect governance, and execute transactions within complex ERP landscapes?
That is where SAP Joule changes the conversation.
Joule is SAP’s generative AI agent embedded across the SAP suite of applications including S/4HANA, Ariba, SuccessFactors, and SAP BTP. It is designed specifically for enterprise business processes rather than general-purpose interaction.
Unlike other generative AI tools, Joule is not simply a chatbot on top of ERP. It is an embedded enterprise process agent, designed to work seamlessly within SAP’s architecture, data model, and governance framework.

1. Process-Aware, Not Just Prompt-Aware
Joule understands structured SAP business objects such as:
• Purchase Orders
• Invoices
• Journal Entries
• Sales Orders
It operates within live transactional contexts and respects user roles and authorizations. For architects, this means AI aligned with process design—not disconnected automation.

2. Native Enterprise Data Integration
Joule leverages SAP master and transactional data directly within the system landscape. It understands:
• Organizational hierarchies
• Role-based authorizations
• Process dependencies
This ensures accuracy, consistency, and alignment with enterprise architecture principles.

3. Governance by Design
For transformation leaders, trust is critical. Enterprise AI must meet compliance and security requirements.
Joule:
• Adheres to SAP’s data residency and privacy standards
• Operates within existing authorization frameworks
• Does not use customer business data to train foundation models for other tenants
Embedded governance ensures safe and compliant AI adoption.

4. AI That Acts — Not Just Advises
Joule moves AI from advisory to execution.
It can:
• Trigger workflows
• Draft journal entries
• Create purchase requisitions
• Guide users through process steps
This is where AI starts delivering tangible business outcomes rather than just insights.

5. Cross-Functional Process Orchestration
Enterprise transformation requires breaking functional silos.
Joule works across S/4HANA, SuccessFactors, Ariba, and SAP BTP:
• Retrieves HR data from SuccessFactors
• Processes financial transactions in S/4HANA
• Updates procurement records in Ariba
All within a single interaction. This end-to-end orchestration simplifies complex business processes.

6. No Training Required
Joule comes pre-trained on SAP business objects and processes:
• No need to teach it what a Purchase Order or General Ledger is
• Aligns with standard SAP process models
• Accelerates adoption without steep learning curves

7. Developer Enablement
Beyond end users, Joule supports developers by:
• Understanding ABAP and SAP CAP (Cloud Application Programming Model)
• Generating code aligned with SAP Clean Core principles
• Supports innovation without compromising upgrade stability
This accelerates transformation initiatives while preserving system integrity.

Joule goes beyond traditional generative AI chatbots. Embedded within SAP applications, it serves as the user interface for Business AI, simplifying and orchestrating interactions and workflows across complex enterprise environments.

For consultants, architects and transformation leaders, the strategic takeaway is clear:
AI value in SAP landscapes will not come from conversations alone.
It will come from embedded, governed, and process-aware intelligence that drives measurable outcomes.
Joule represents a foundational step toward that future.

How are you approaching embedded AI adoption in your SAP landscape—and what challenges are you seeing in moving from pilot use cases to enterprise-wide execution?
We would love to hear your experiences, insights, and lessons learned.

Source:
SAP Help Portal | SAP Online Help
Discovery Center

Meet Your Ops Agents - Powered by SAP Automation Pilot and Joule

2026-02-23T11:10:00.063000+01:00

Building on our latest innovation around SAP Automation Pilot and AI-powered IT Operations, I am excited to share that we are already seeing real productive use cases for Day-2 Operations Agents which are powered by SAP Automation Pilot content and consumed directly in Joule in a truly agentic manner.

🎥 Meet Your Ops Agent

See an example about Ops Agent powered by SAP Automation Pilot and discover how easy it is to set up an MCP server, expose automations, and trigger them in an agentic way through Joule.

This approach unlocks a completely new way to ops automation where AI agents can reason, execute, and orchestrate operational tasks seamlessly following customers requests and needs.

The demonstration walks through a scenario about an S/4HANA Health Monitoring Ops Agent in Joule, designed to:

Provide system health & diagnostics insights;
Perform automated analysis & deliver actionable recommendations;
Proactively send alerts when potential issues are detected;

📖Just the beginning

There is an unlimited range of Ops Agent scenarios enabled through SAP Automation Pilot, including for example:

SAP BTP Operations (e.g. Cloud Foundry applications, SAP HANA Cloud, SAP cTMS, etc.);
SAP Build and Day 2 Operations for your apps;
SAP Integration Suite checks and actions via automated API calls;
Integrations with custom solutions;
And many more …

Stay tuned as we will be revealing more real-life agentic operations scenarios in the coming weeks.

🚀 Get involved: Join Our Customer Engagement Initiative

If you would like to bring your own automation scenario and experience first-hand the AI-driven operations capabilities of SAP Automation Pilot and Joule, join our Customer Engagement Initiative: Agentic AI Operations with SAP Automation Pilot

⏳Registration is open until March 15, 2026 - secure your spot soon!

Learn More

If you would like to explore MCP servers in more detail or start using them in your own landscapes, please check out the SAP Automation Pilot official documentation which provides further insights:

Looking forward to collaborating and shaping the future of agentic IT operations together.

SAP Community - Joule

Trust but Verify - Validating SAP Joule Agents with Int4 Suite

The Scenario: From Email to Sales Order

Configuring Validation in Int4 Suite: A 3-Step Guide

Step 1: Create the Automation Object

Step 2: Define Content and "Soft Rules"

Step 3: Set S/4HANA Database Validation

The Moment of Truth: Running the Test

Why This Matters

Full Scenario

Important note:

Setting Up Document Grounding with Cloud Integration Automation service: Making Joule context-aware

Setting up Document Grounding using Cloud Integration Automation service

Useful Links

SAP UX Q1/2026 Update – Part 4: SAP SuccessFactors (AI, Joule and More)

Enjoyable: Design and Usability Enhancements

New Home Page Design (Web)

New Home Page Design (Mobile)

Easy On-Boarding with WalkMe

Examples of Good UX in Workforce Management

SAP SuccessFactors Workforce Scheduling

Geofencing in SAP SuccessFactors Time Tracking

Better outcomes with AI and Analytics

Career and Talent Development for employees and managers: skills, succession

Automatically Create Skills from Resume

AI-Recommended Development Goals Based On Skills

AI and Analytics for Managing Career and Talent Development

AI Successor Recommendation Based On Skills

Performance and Goals: Joule Agent, AI and Analytics for Managers

Performance Insights

Additional Joule support for employee self-services

Together: Supporting Collaboration in Teams

Joule integration into Microsoft Teams

AI-assisted Writing Available in Microsoft Teams

Further Information on 2H2025 Release Highlights

Continue Reading

Setup and Activation Guide: Joule in SAP S/4HANA Private Cloud

Prerequisites

Pre-Setup Checklist

Setup Steps

1. BTP Platform Configuration

2. Trust and Security Setup

3. Content Provider Configuration

4. Joule Service Activation

5. Fiori Launchpad Integration

Post-Activation Validation

Troubleshooting Common Issues

Best Practices

Next Steps

The Combined Power of SAP Joule and AI for the RISE with SAP Methodology

Managing Joule on SAP BTP: Roles, Analytics, Administration and Troubleshooting

Creating a ‘Hello World’ Joule Agent

Creating the Joule Agent

Testing the Joule Agent

Testing the Deployment

Conclusion

SAP Joule for Consultants (J4C): A Strategic Overview

Unlock the Power of People Management with Joule

Summary:

AI’s Role in Organizational Change Management

Impact key:

🟪 Change Effectiveness ensures change activities deliver outcomes and remain sustainable over time.

POV on How to Approach Custom Agents in the Enterprise - Blog Series

POV 1: Create Custom Agents in SAP (Part 1/4)

POV 2: Agent to Agent Collaboration with SAP and non-SAP Agents (Part 2/4)

POV 3: Using Integration Suite as Your Governed MCP Server Platform (Part 3/4)

POV 4: Putting it all Together Across Your Enterprise (Part 4/4)

Joule A2A: Connect Code Based Agents into Joule

Overview of Joule Capabilities

Setup

1. Login to your IAS tenant:

2. Create new Application:

3. Add Joule application as a dependency:

4. Create Client Secret:

1. Building the Agent with LangGraph

2. Building the Joule Pro-Code Capability

Understanding the Joule Agent Result Variable

Key Components of the Response

Example

Extracting Specific Information

SAP Watchlist Screening

Value Proposition

Value Proposition

Capabilities

Value Proposition

Capabilities