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...

martedì 30 giugno 2026 New tab

662 words~3 min read

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 before acting." "Check context before asking." "Capture learning after complex tasks." Good rules. Important rules.

After 30 sessions, I finally checked: my "think before acting" rule had been followed exactly zero times.

Not because the AI was ignoring it. Because the rule was a wish — not a verifiable constraint. It had no teeth.

The TDD Insight Nobody Applied to AI Config

I Made My AI Rules Self-Verifiable — Here's How

I Made My AI Rules Self-Verifiable — Here's How

Related reading

Stop Telling Your AI to "Be Careful Next Time." It Has No Memory of Yesterday.

AI Coding Tip 024 - Force a Criteria Check Before the Task Ends

AI Agents Need More Than Fact-Checking

I Built a Closed-Loop Self-Healing System for My AI Config — By Accident

Your AI is not bad, your instructions are

You Already Know What Your First AI Rule Should Be. You Just Have Not Written…

Related reading

Stop Telling Your AI to "Be Careful Next Time." It Has No Memory of Yesterday.

AI Coding Tip 024 - Force a Criteria Check Before the Task Ends

AI Agents Need More Than Fact-Checking

I Built a Closed-Loop Self-Healing System for My AI Config — By Accident

Your AI is not bad, your instructions are

You Already Know What Your First AI Rule Should Be. You Just Have Not Written…