Claude Code for Project Managers: The Weekly Update We Kept
Sep 27, 2026 · 7 min read
Claude Code for project management: ours drafts weekly client updates and retros, refuses to draft while a video link is missing, and never presses send.
Read moreWhat I learned running a company on Claude. The real numbers and the parts that broke.
Pick a topic, or start with the three posts below. The older posts cover AI coding and Django.
Latest
Should I Automate This? First Ask Whether It Should Exist
Sep 25, 2026 · 9 min read
Eliminate before you automate. Our AI build gate said DON'T to a vacation reminder for the wrong reason, so I added a question zero. Here it is.
Read more
Two Bots Argued on a Pull Request for 21 Hours
Sep 22, 2026 · 9 min read
Our Claude Code GitHub Action reviewer and a nightly routine looped on one PR for 21 hours: 147 review runs, about $500. The fixes we made on both sides.
Read more
Claude Code Team Setup: Shared Settings, /setup, What Broke
Sep 19, 2026 · 7 min read
Claude Code team setup for people who don't code: one repo, shared settings in git, a /setup command that reads our roster, and what broke on day one.
Read more
Knowledge Graph vs RAG: We Piloted a Graph and Killed It
Aug 6, 2026 · 7 min read
We piloted an LLM knowledge graph on 46 documents with kill criteria set first. 89% of edges were true, but a rerun matched 16% of labels. Search won.
Read more
How to Prompt Claude Code: 5 Lessons From 356 Sessions
Feb 9, 2026 · 8 min read
Five Claude Code prompting lessons from 356 sessions building an interactive guide with SkiFree and a music engine. The biggest: name the reference.
Read more
Microservices vs Monolith: What Segment's 140 Services Cost
Dec 28, 2025 · 5 min read
Segment folded 140+ microservices into one monolith and shipped shared-library fixes faster. When microservices pay off and when a small team pays the tax.
Read more
Software Craftsmanship in the Age of AI: When Craft Pays
Dec 28, 2025 · 6 min read
AI made the choice between clean code and shipping visible. Where craft still pays for itself, where it's a trap, and what the METR study measured.
Read more
Why AI Agents Get Stuck in Loops (and Quit Too Early)
Dec 18, 2025 · 6 min read
AI agents get stuck in loops when they have to decide how many times to do something. A Collatz study shows why, and how to make an agent stop on time.
Read more
Is AI Making Developers Worse? Yes, and They're Worth More
Sep 18, 2025 · 4 min read
AI coding agents write code that's almost right. Catching what's wrong takes fundamentals, so developers who have them are worth more now.
Read more
How Law Firms Are Using AI: Notes From a Legal Conference
Jul 18, 2025 · 5 min read
Law firms are using AI for research and first drafts, with a person checking every citation. What I saw at a legal conference, and what the surveys say.
Read more
Panel of Experts Prompting: Templates and What Research Found
May 25, 2025 · 5 min read
Panel of experts prompting asks AI to simulate specific experts who argue. Copyable templates, what the debate research found, and when it's overkill.
Read more