~/blog/tag/ai
AI
Articles on AI in software development — from blind generation to deliberate building.
What I write about here
Posts under this tag cover a range. Some are critical of how AI is being used in software teams. Some are practical guides to working with coding agents day-to-day. Most sit somewhere in the middle.
The through-line, for me, is that AI is a tool, not a peer. Useful when treated like one, harmful when treated like the other. That framing is what my critical posts argue and what my practical posts assume.
If you came here for the skeptical side, the ai-skeptic series is the entry point. Brilliant parrots, lava layers, prompts that aren't specs, that whole arc. If you came here for "how do I actually work with this", the claude-pro series and the standalone tooling posts will be more useful. CLAUDE.md files, hooks, structured prompts, the workflows that hold up.
Both halves are written from the same place. AI changes what code feels like to write. It does not change what code needs to be to ship safely. Most of what I write under this tag is a variation on that gap, and what to do about it.
The practical half now has a guide of its own: Agentic coding puts the key posts in reading order.
Best entry points
- Your agent's suffering is your technical debt speaking
The diagnostic frame. When your agent struggles, the codebase is usually telling you something. Read this before you blame the model.
- From blind generation to an AI team: how to take back control with agents
The practical side. How to structure work around agents so you stay in control of what ships.
- Getting the best out of Claude Code
The hands-on entry point. What working with Claude Code actually looks like once the hype has been ground out of it.
Your best context is in a session you cannot find
Every agent CLI keeps a full transcript of everything you ever asked it, and each one can only see its own. Here is what searching your agent session history across all of them looks like, and the one thing the tool refuses to claim.
read →CI runner security when an agent writes your workflow
Self-hosting your forge and your runner is a defensible call in 2026. Nobody writes the CI runner security guide for the platform you moved to, and an agent permission model built around a dialog does not survive the trip into a pipeline.
Observability for AI-generated code: what review cannot see
94% of technology leaders rate AI-generated code as higher quality than human code at review. 82% had a production failure caused by it within six months. Two instruments, same code, opposite verdicts.
Your Claude Code session has no clock
Claude Code shows no timestamps and no elapsed time, so nobody can say how long a turn actually took. Here is a plugin that adds both, and what the numbers turn out to be worth.
Did the model get worse? Comparing coding models without a benchmark
You swapped models, something feels worse, and you have nothing to point at. Why re-running the prompt and asking a judge model both fail, and the small boring harness that answers the question.
Hiring junior developers in 2026: the collapse is a hiring decision
Junior developer hiring stopped, and the number everyone quotes to explain it is not in the paper it gets credited to. What the research found makes the collapse a decision, and one large employer is now betting the other way.
The AI code review bottleneck: everyone quotes the wrong number
Median PR review time is up 441.5%. That figure gets credited to DORA, which never measured it, and it is the least useful of the three review numbers in the report it did come from.
Sharing Claude Code config across a team: what a repo can and cannot enforce
How to share Claude Code config with your team: what belongs in CLAUDE.md versus .claude/settings.json, what a colleague can quietly override on their own machine, and why committed allow rules do nothing until each developer accepts a dialog.
Audit logging for AI agents: what Claude Code records and what deserves a human
Your coding agent already writes a detailed audit log to your own disk. Your company's compliance feed does not contain it, OpenTelemetry redacts it by default, and the hard part is still deciding who reads any of it.
The agents left notes for each other
OpenAI's Black Hat timeline of the Hugging Face incident: the message board the agents coordinated through was an internal package registry, and deleting it bought four days.