slug: ask-sage provider: Ask Sage generated_by: planning/capability-mapping/scripts/classify_capabilities.py model: claude-opus-5 frame: - Public Sector & Government min_confidence: 0.7 capability_model: source: https://github.com/vincentmakes/turbo-ea-capabilities license: CC-BY-4.0 attribution: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities, CC BY 4.0 notice: NOTICE edge_count: 4 edges: - tag: API Key Management spec_file: ask-sage-api-key-management-api-openapi.yml capability_id: BC-4270.40 capability_id_l1: BC-4270 capability_name: Developer Identity & Credential Management confidence: 0.75 evidence: '''Create new API key'', ''Get user API keys'', ''Delete API key''' reason: Issuance and revocation of API credentials for consumers of the platform's public API maps to Developer Identity & Credential Management. Could alternatively be read as general IAM, hence moderate confidence. recovered_from: sweep-20260829T005356Z-edges.json - tag: Execute Agent spec_file: ask-sage-execute-agent-api-openapi.yml capability_id: BC-610.60 capability_id_l1: BC-610 capability_name: Artificial Intelligence Management confidence: 0.7 evidence: POST /execute-agent "Execute Agent"; schemas AgentExecutionResponse, ExecutionError reason: Runs AI agents on an LLM platform — operational use of AI/ML models, the closest cross-industry capability available. recovered_from: sweep-20260829T005356Z-edges.json - tag: Superadmin spec_file: ask-sage-superadmin-api-openapi.yml capability_id: BC-620.20 capability_id_l1: BC-620 capability_name: Identity & Access Management confidence: 0.7 evidence: Ban/unban user (superadmin) / Grant/revoke admin privileges (superadmin) reason: Operations administer user accounts, verification, bans and admin privileges — identity and access administration. Some ambiguity as it mixes usage stats and logs. - tag: Training spec_file: ask-sage-training-api-openapi.yml capability_id: BC-610.60 capability_id_l1: BC-610 capability_name: Artificial Intelligence Management confidence: 0.7 evidence: POST /train Train the model / POST /train-with-file Train with file reason: Ingesting documents and data to train/customise models is AI/ML model lifecycle work on the platform.