ai-enablement-ws

Audit a Google ADK tool file against the five known gotchas (DI params, thin wrappers, _j helper, async-wrap blocking calls, httpx context manager) before they bite in production

After creating an ADR, run the cross-referencing checklist — update README Artifacts table, add Related Decisions section to source proposal, cross-link sibling ADRs to each other

Mid-task durability — dump current state and a next-step file before context fills, so the next session resumes without re-deriving where you were

Generate and verify a pre-demo checklist for an ADK/agent project — env vars, GCP auth, embedding swap, ngrok/Slack wiring, dry-run, tests, real-vs-synthetic data

Scan a project's docs (README, CLAUDE.md, ADRs, runbooks) for inconsistent project naming, scope, or framing — catches the "README says retail, CLAUDE.md still says Kroger" class of bug

Refresh a project's status — derive current state from code/tests/git, regenerate the project's status memory entry and (if requested) a status section in the README

Generate a new Architecture Decision Record from a topic, decision description, or rough notes

Design a full agentic system — loop architecture, tool manifest, memory, guardrails, observability

Capture session learnings as a structured solution doc in docs/solutions/ — the knowledge flywheel

Retail ML dataset readiness audit — completeness, PII governance, temporal leakage, cold-start, data contracts

Design an LLM evaluation framework — metrics, test sets, pass/fail gates, drift triggers, and tooling

Generate a model card covering overview, intended use, evals, limitations, governance, and versioning

PII exposure audit — map data elements across the AI lifecycle and surface HIGH/MED risk intersections

Audit a prompt for clarity, injection risk, token efficiency, hallucination surface, and fallback behavior

Design a RAG architecture — chunking, embedding, retrieval pattern, re-ranking, and observability

Structured adversarial test plan — OWASP LLM Top 10 2025 + agentic battery with concrete test cases and payloads

Run a full architecture review — strengths, findings, checklist, ADR recommendations

Design a phased AI feature rollout — shadow → canary → limited GA → full GA with eval gates and rollback triggers

Generate an AI incident runbook — model degradation, hallucination spikes, cost blowouts, agentic runaway, and more

AI supply chain security review — model provenance, AI-BOM, embedding integrity, framework dependencies, third-party APIs

AI-specific threat model covering prompt injection, data poisoning, PII leakage, excessive agency, and supply chain risks

Append raw session findings to today's daily log (docs/daily/YYYY-MM-DD.md) — fast scratch capture that feeds /compound

Structured trade-off analysis — build/buy/borrow or option comparison with weighted scoring and a firm recommendation

Web-search for AWS AI/MLOps updates, diff against the AWS cheatsheet, and propose changes for approval

Web-search for Azure AI/MLOps updates, diff against the Azure cheatsheet, and propose changes for approval

Web-search for GCP AI/MLOps updates, diff against the GCP cheatsheet, and propose changes for approval

Web-search for OSS AI/MLOps releases, diff against the OSS cheatsheet, and propose changes for approval