slug: opik
provider: Opik
generated_by: planning/capability-mapping/scripts/classify_capabilities.py
model: claude-opus-5
frame:
- Software & Technology
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: AI Spend
  spec_file: opik-ai-spend-api-openapi.yml
  capability_id: BC-600.80
  capability_id_l1: BC-600
  capability_name: IT Financial Management
  confidence: 0.72
  evidence: getSpendSummary  Get spend summary ; getSpendRecommendations  Get spend recommendations ;
    getSpendUsers  Get spend user leaderboard
  reason: Reports composition, summary, per-user breakdown and cost-saving recommendations for LLM/AI
    spend within a workspace — technology spend visibility, showback and cost optimisation. Mapped to
    IT Financial Management; some chance a grader prefers a generic analytics capability, hence not higher.
- tag: Automation rule evaluators
  spec_file: opik-automation-rule-evaluators-api-openapi.yml
  capability_id: BC-610.60
  capability_id_l1: BC-610
  capability_name: Artificial Intelligence Management
  confidence: 0.7
  evidence: POST /v1/private/automations/evaluators  createAutomationRuleEvaluator  Create automation
    rule evaluator; schema AutomationRuleEvaluator_Public
  reason: Automation rule evaluators are Opik's LLM-as-a-judge scoring rules applied to logged traces
    — automated evaluation of AI model outputs, part of the AI/ML model lifecycle and responsible-AI monitoring
    (BC-610.60). Not a generic workflow-automation capability.
- tag: Datasets
  spec_file: opik-datasets-api-openapi.yml
  capability_id: BC-610.60
  capability_id_l1: BC-610
  capability_name: Artificial Intelligence Management
  confidence: 0.7
  evidence: POST /v1/private/datasets/{dataset_id}/items/from-traces  createDatasetItemsFromTraces  Create
    dataset items from traces
  reason: Evaluation datasets curated from production traces/spans and versioned for LLM experiments —
    training/evaluation data assets in the AI/ML model lifecycle (MLOps), not generic enterprise master
    data.
- tag: Experiments
  spec_file: opik-experiments-api-openapi.yml
  capability_id: BC-610.60
  capability_id_l1: BC-610
  capability_name: Artificial Intelligence Management
  confidence: 0.7
  evidence: POST /v1/private/experiments/execute  executeExperiment  Create and execute experiment; GET
    /v1/private/experiments/feedback-scores/names  findFeedbackScoreNames
  reason: Experiments here are LLM evaluation runs over datasets producing feedback scores — model evaluation
    within the AI/ML lifecycle, not product A/B testing of features.