Guides for building software with agents.

Reliability, context, tools and infrastructure.

The Temptation to Build Everything

Resisting the temptation of vibe coding is the new stoic discipline

Featured guide31 Oct 20263 min read

A single timestamp cannot distinguish a late correction from a real-time state change.

26 Jul 2026AI Agents4 min read

Tie every prompt workaround to a failure case, then test its removal when the model changes.

26 Jul 2026AI Agents4 min read

Ship the model, reasoning mode, and history adapter as one versioned protocol.

25 Jul 2026AI Agents4 min read

Removing a tool from the model's list doesn't revoke the credentials behind it, so check permissions when the call executes.

25 Jul 2026AI Agents4 min read

Report the share of runs that reach each milestone, so you can see the step where an agent starts failing.

25 Jul 2026AI Agents4 min read

Daily notes for engineers. Your commits, pull requests and agents show up under each day.

Retry failed webhooks

Fix the flaky retry test

Editing retry.test.tsWaiting for you

68 LLM and agent frameworks ranked by GitHub stars, with language, age, size and funding.

59 patterns that give away AI-generated design, writing and code.

“Every thought — however small — gets an em dash.”

The em dashFirst place, writing