Engineering Blog

Technical insights into multi-agent orchestration, local protocols, and
developer-centric terminal workflows.

Agent Loop Engineering Is Context Engineering in Disguise

Agent Loop Engineering Is Context Engineering in Disguise

The loop engineering parts list from June 2026, classified by one question: five blocks are context moves, one is a schedule, and the genre's signature failure is fixed by a seventh block the list never counted.

Search Claude Code Session Transcripts Before They Delete

Search Claude Code Session Transcripts Before They Delete

Your session transcripts hold every decision you've made with an agent, and the only free way to search them counts mentions instead of truth. Rank the survivors by date and the reversed decision stops winning.

Run Headless AI Agents Overnight: One Task, One Context

Run Headless AI Agents Overnight: One Task, One Context

A frozen spec substitutes for the memory a disposable agent doesn't have - but only if every task is genuinely independent. The arithmetic for when a flat-rate build loop actually holds.

Write the Acceptance Test Into Your AI Agent's Spec

Write the Acceptance Test Into Your AI Agent's Spec

A green build proves the code compiled. It says nothing about whether the work is correct. Write the acceptance test into the spec, then measure how well it survives an agent gaming its own grade.

Use an MCP Server So Your AI Agent Reads Current Docs

A vibe-coded Stripe integration buries nine decisions in one handler. A teaching clause plus a plan-mode gate surfaces all nine - only three are worth your own trip to the docs.

Review AI-Generated Code by Blast Radius, Not Uniformly

Your daily review-minute budget is fixed, but a missed bug's dollar cost isn't. Spend the same minutes unevenly by blast radius and cut expected losses by roughly half, without reviewing more.

Claude Code Stop Hooks: The Two-Tooth Completion Gate

Claude Code Stop Hooks: The Two-Tooth Completion Gate

While you watch an agent work, you are quietly doing two jobs: judging what it may touch, and judging when the work is actually done. Headless mode deletes you from both at once. The gate that inherits the second job fails two separate ways unless it has two teeth.

AGENTS.md Too Long? Split Into Directory-Scoped Rules Files

AGENTS.md Too Long? Split Into Directory-Scoped Rules Files

A single root rules file guarantees every convention is always present for every edit - which is exactly what floods a backend edit with frontend rules it will never use. The fix is directory-scoped files, and the tax has a number: 62.5%.