Your AI Coding Assistant Has No Memory of Why
A pull request lands. Two approvals, tests green, CI blue. It ships on a Tuesday. Three weeks later there's an incident. Somebody opens the file and f…
Architecture
⚑ Report a ProblemLatest Architecture news from Tech News
All topics
agents
ai
api
architecture
automation
aws
backend
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
softwareengineering
systemdesign
tutorial
typescript
webdev
World-Building Is the Test Discipline Agents Need
Originally published at tddbuddy.com . Related reading: The Bar for TDD Just Moved names the floor; TDD Already Does BDD, Without the Gherkin names th…
Agents Amplify Whatever Vocabulary They Find
Originally published at tddbuddy.com . This is part 2 of the "Vocabulary Is the Product" series. Part 1, The Hidden Output of TDD Was Never Code , arg…
I Made My AI Rules Self-Verifiable — Here's How
The problem wasn't that my rules were bad. The problem was I had no idea if they were being followed. I had 15 rules for my AI assistant. "Think befor…
Tests Pass, Design Breaks: Why TDD Can't Hold the Line on Design Intent
There is a popular misconception that if you do TDD, your design also stays correct. That if the tests pass, quality is guaranteed. In AI-assisted dev…
Harness Engineering: The 'New Software' in the AI Era?
With the massive AI boom we are experiencing, I started writing an article about testing. In the midst of my research, I began studying Harness Engine…
How I’m Using Agent Harnesses, TDD, and the Seam Model to Improve Development in Legacy Systems
How I’m Using Agent Harnesses, TDD, and the Seam Model to Improve Development in Legacy Systems Over the past few months, I’ve been investing a lot of…