#llm-evals

Playbook for PMs shipping AI products with PRDs, evals, HITL, launch gates, cost, and observability.

Production-shaped agentic RAG: LangGraph plan->act->verify agent + hybrid retrieval + guardrails + an eval gate in CI. Provider-agnostic; runs offline with no keys.

Source-backed archive of agent prompt-injection incidents, research records, trust-boundary patterns, schemas, and sanitized defensive summaries.

Slack-native internal knowledge chatbot with nightly-reindexed RAG (Pinecone) and source-cited answers. Reference build behind a 50% onboarding-time-reduction case study.

Executable, benchmarked Agent Skills for startup strategy, growth, and positioning. CI-gated for Antigravity, Codex, Claude Code, Cursor, Opencode, Hermes & others.

Reproducible benchmark for LLM-based structured extraction from documents. Compare Claude / GPT / Gemini / open-weight on the same task with cost + latency tracking.