Verify and configure SAP AI Core credentials, retrieve auth tokens, and manage resource groups. Runs a setup health check, resolves authentication errors, and lists, creates, updates, or deletes resource groups. Use when checking whether AI Core is set up, configuring credentials, getting a Bearer token, or managing resource groups.

Manage the full SAP AI Core deployment lifecycle: scenarios, executables, configurations, and deployments. Lists and inspects scenarios and executables, creates configurations, creates, lists, stops, deletes, or patches deployments, fetches deployment logs, and removes duplicate LLM deployments. Use when managing AI Core deployments and their configurations.

List and explore foundation models available in the SAP AI Core Generative AI Hub: browse providers, model names, versions, capabilities, and executable IDs, and get curl inference examples for deployed models. Use when discovering available models, finding an executable-id or model-name for deployment, or generating inference examples such as chat completions, embeddings, or image generation.

Run GenAI evaluations on SAP AI Core: benchmark LLMs and prompts against a test dataset using system-defined and custom (LLM-as-judge) metrics, then retrieve aggregate results. Supports all three evaluation types — prompt registry, orchestration registry, and grounding (RAG) orchestration registry. WHEN: user wants to evaluate or benchmark an LLM / prompt / orchestration config, run a GenAI evaluation, create or list evaluation metrics, define a custom LLM-as-a-judge metric, create a prompt template (prompt registry) or an orchestration-registry config (with or without grounding) for evaluation, create an evaluation configuration or execution, or fetch evaluation results / scores for an execution. DO NOT USE FOR: agent evaluation via the offline aeval service — use `aeval-offline-evaluation`; building a production orchestration/RAG pipeline for inference — use `genai-hub-orchestration`; generic executions, deployments, or artifacts unrelated to evaluation — use `aicore-lifecycle-management`; credentials, resource groups, or object stores — use `aicore-admin-resources`.