End-to-end QA testing for Agent2 agents. Starts the agent service, sends real API requests from eval datasets, validates responses against the output schema, and generates a health report with confidence stats. Use when asked to "test this agent", "QA the agent", "does this agent work", or "run agent health check".
Build Agent2 agents for Polymarket market discovery, scandal-reactive watchlists, social-sentiment market analysis, market-sentinel workflows, and paper-trading research. Use when creating or modifying agents that find Polymarket markets affected by public opinion, reputation shocks, social media, scandals, fandom narratives, or news-latency signals.
Use when a domain expert wants to clone their professional brain into an Agent2 agent — interactive multi-phase interview that extracts identity, Chain-of-Thought, tools, knowledge, examples, and output format, then generates a complete production agent with a Sachbearbeiter-style Chain-of-Thought prompt, Pydantic schemas, tools, knowledge collections, and Docker config. Triggers on "brain clone", "clone expert", "new domain agent", "extract expertise".
Use when adding pause/resume, human approval, provider routing, tool scoping, or knowledge search to an existing agent — covers all optional Agent2 framework capabilities with implementation patterns
Use when an agent needs to search documents, PDFs, or reference material — covers R2R collection setup, document ingestion, Knowledge MCP wiring, per-tenant collection scoping, and knowledge package architecture
Use when building an agent that needs deep domain expertise — reads documents, checks them against professional knowledge, asks clarifying questions, and produces structured domain-specific output. Covers knowledge-backed agents, document processing, multi-turn workflows with human approval, and per-context knowledge scoping.
Use when creating a new Agent2 agent, scaffolding a service, or when user says "new agent" or "add agent" — generates schema, tools, config, Dockerfile, and Docker Compose entry following Agent2 conventions
Use when an Agent2 agent returns errors, 500s, mock data unexpectedly, fails to start, or behaves incorrectly — systematic diagnosis for framework issues, config problems, Docker issues, and runtime failures