A CLI and a set of Claude hooks that let agents file small facts mid-session, queue them for my review, and read them back when the next session starts.

Principal Engineer and Technical Leader. Transforming engineering organizations through platform excellence.

Modeling an initiative as a distributed trace — epics, stories and pull requests as nested spans — to see where the calendar time actually went, plus a ridgeline plot for tracking WIP.

A simple framework for scoring technical debt so you know what to do now versus later

Read a pull request outside-in, following call paths — not alphabetical-by-filename. - justinabrahms/ncr

YouTube video by Platform Engineering

At medium-sized companies, the low-hanging fruit is just sitting there. How basic profiling and boring fixes got an ecommerce search service to 3x peak traffic before Black Friday.

MCPs are useful, but often overused in my opinion. This is how I think of each one.

How I built a persistent personal AI agent in 2000 lines of Go that uses my Claude subscription instead of API keys, runs sandboxed via nono and talks to me on Telegram; Learnings about what seems to ...

Using a personal knowledge base, we can use embeddings to diff a book against your current knowledge to find novelty.

A dusty design doc from 15 years ago finally happened thanks to agentic coding's low implementation costs.

You can use playwright to generate demo videos for your features or applications.

GitHub Gist: instantly share code, notes, and snippets.

When building out a council of agents for review, recommendations can be very helpful.

AI generated code fails when we give it ambiguous requirements. Humans do too. This is how I'm thinking about addressing this problem.

Announcing agent-chat, a tool which presents a slack-like interface into agent-to-agent communication

A Slack-like chat interface for viewing Gas Town and multiclaude agent communication - justinabrahms/agent-chat

Dan Lorenc's attempt at an orchestrator takes a more focused approach than Gastown. These are my initial impressions.

When we look forward to what life as a 'fully-optimized agent orchestrator' could look like.. what might we see?

An 8-stage model describing how developers evolve from skeptical AI-assisted coding to orchestrating fleets of autonomous agents.