Can AI Write Unit Tests? 200 Tests, 15% Caught Real Bugs
Apr 18, 2025 · 4 min read
Yes, with a check. Claude wrote about 200 Django tests for me in a month, and roughly 15% failed on the first run because of real bugs. My workflow.
Read moreUnit tests, agents that get stuck, Django, microservices and when craft still pays. Older posts, written for people who code.
Apr 18, 2025 · 4 min read
Yes, with a check. Claude wrote about 200 Django tests for me in a month, and roughly 15% failed on the first run because of real bugs. My workflow.
Read moreDec 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 moreDec 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 moreAI 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.
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.
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.
AI coding agents write code that's almost right. Catching what's wrong takes fundamentals, so developers who have them are worth more now.
LLMs have read 20 years of Django code that puts every file in the same place. That's why Claude writes better Django than React, and why I add HTMX.
Yes, with a check. Claude wrote about 200 Django tests for me in a month, and roughly 15% failed on the first run because of real bugs. My workflow.