Agent Notes
Field notes, operating models, and reusable team artifacts from real work with Claude, Codex, and coding agents.
Practices worth carrying into the next run
Restart AI Coding Sessions When Context Stops Being Verifiable
Restart an AI coding session when context stops being verifiable. Use a checkpoint that preserves facts, uncertainty, and the next safe probe.
Read note →
Before an AI Agent Asks a Question, Make It Search
Use AI agent context gathering to reduce avoidable team interruptions. Separate cheap lookups from decisions that genuinely need a human.
Read note →
Make Agent Integration Failures Explicit Before Asking Humans
Classify AI agent integration errors before asking humans for context. Preserve missing input, unavailable capability, denied access, and stale sources.
Read note →
Define AI Agent Work as Verifiable Execution Slices
Use AI agent task decomposition built around one outcome, changed surface, proof path, rollback, and stop condition instead of arbitrary small tasks.
Read note →
Turn Painful Agent Runs Into Evaluated Skills
Build AI agent skills from hard-won runs by extracting invariants, bounding authority, and testing new cases instead of saving an unverified prompt.
Read note →
Give AI Agents Permissions by Intent, Not Identity
Scope AI agent permissions to inspect, plan, patch, deploy, or verify. Review authority transitions instead of granting broad access by assistant identity.
Read note →
Build a Provenance Ledger for AI Agent Research
Use an AI agent provenance ledger to separate observed, inferred, contested, and unsupported claims before research drives engineering decisions.
Read note →
Use Reversible Rollouts for AI Agents in Production
Run an AI agent production rollout through observe, prepare, shadow, limited, and general stages with evidence, thresholds, and executable rollback.
Read note →
Monitor Long-Running AI Agent Work Without State Drift
Design AI agent monitoring as a read-only delta heartbeat with stable evidence, idempotent checkpoints, anomaly thresholds, and terminal conditions.
Read note →
What a Genuinely Blocked AI Agent Should Report
Use an AI agent blocker report to stop equivalent retries, preserve completed evidence, identify the failed dependency, and name the smallest unblock.
Read note →
Teaching an AI Reviewer to Disprove Itself Before It Comments
AI review false positives fall when do-not-flag policy, falsification checks, and trace reporting ship as one system.
Read note →
Typed Intent Routing Before an Agent Touches the Broker
Typed intent routing makes model-assisted agent routing usable only when scope, schema, approval, and audit evidence gate execution.
Read note →
Choosing Real-Time Commit Story Mining Over Bulk GitHub Indexing
Commit story mining works better when agents observe intent in real time instead of indexing every repository change first.
Read note →
When Editorial Quality Scores Stopped Being the Right Sort Order
AI editorial workflow boards should separate freshness, quality, and actionability so reviewers see new candidates first.
Read note →
Mining Huge AI Session Transcripts Without Drowning in Them
AI transcript mining needs evidence-first search, narrow excerpts, and claim labels before large agent logs become source material.
Read note →
Gate default model changes with golden sessions
Golden sessions give AI runtime model default changes a regression contract across prompts, profiles, approvals, CI, and live evidence.
Read note →
When Verification Schemas Drift From Runtime Reality
Verification schema drift happens when agent output schemas and runtime validators diverge. Make the contract executable before live runs.
Read note →
Turning a Pilot AI Platform Into an Operable Service Contract
An AI service contract turns a working internal AI pilot into an operable service with owners, dependencies, and fail-closed gates.
Read note →