Field notes from the AI-native SDLC.
What I'm learning shipping agent-built software in production: debugging loops, throughput math, the metrics that actually move.
Jul 7, 2026AISoftware Engineering
The AI-Native Way to Organize Software Work
Jul 7, 2026AIllm
The problem with "does this look right?"
Jul 3, 2026AISoftware Engineering
Recent AI News In Case You Missed It: Gated Models, Cheap Coders, and the Agent Stack
Jul 2, 2026AISoftware Engineering
A Gentle Introduction to Agent Harnesses
Jul 1, 2026AISoftware Engineering
The Spec Is the Source of Truth Now (Mostly)
Jun 30, 2026AISoftware Engineering
What Mattered Last Week in AI Engineering In Case You Missed it
Jun 29, 2026AISoftware Engineering
Building a Harness for Autonomous Coding Agents
Jun 18, 2026AISoftware Engineering
Designing In-App Help
The Case for a Contextual Drawer and a Shared Glossary
Jun 16, 2026AIai agents
Four Infrastructure Pieces That Quietly Decide Whether Agent Products Scale
Jun 15, 2026AIai agents
Three Products That Treat Agents as Members of the Team, Not Bots
Jun 15, 2026AISoftware Engineering
A Week Where Single-API LLM Stacks Got Harder to Defend
Jun 12, 2026AISoftware Engineering
Time-Lapse Engineering
How a High-Velocity SDLC Exposes the Invisible
Jun 11, 2026AISoftware Engineering
Ten Failure Modes from a Year of Running an Agent Harness — Part 2
Jun 8, 2026AISoftware Engineering
Ten Failure Modes from a Year of Running an Agent Harness — Part 1
Jun 5, 2026AISoftware Engineering
Why SQLite Bans AI Contributions: A Case Study in Open-Source Quality Engineering
Jun 3, 2026AISoftware Engineering
Two Quiet Results, One Shared Lesson: Where Capability Gains Are Coming From Now
Jun 2, 2026AISoftware Engineering
The Agent Ops Stack, Explained: Two New Tools and the Layer They Belong To
May 19, 2026
The Lazy Boundary
May 14, 2026
Rebuilding the SDLC for AI Throughput
May 14, 2026Pythonpytest
Anatomy of a Two-Day Pytest Debugging Loop