agentic-systems-engineering

Use when planning or delivering an LLM or agentic-system project, especially for experiment loops, walking skeletons, demos, data stories, scope control, and release-readiness evidence.

Use when designing, implementing, reviewing, or debugging LLM-backed or agentic systems, including prompts, structured outputs, tool use, RAG, agent loops, orchestration, observability, security, cost/provider routing, and AI delivery plans.

Use when evaluating prompts, LLM features, agents, RAG, judges, tool-use policies, or any stochastic behavior where one successful run is not reliable evidence.

Use when setting up a project-local eval harness for prompts, agents, judges, RAG, tools, or other LLM behavior, especially when the default should be free/OSS promptfoo with repo-owned artifacts.

Promptfoo MCP server for validating configs, running focused evals, inspecting results, and developing eval cases from Codex.