What 12 failure classes and 30 Billion tokens spent taught us about trusting AI coding agents

We've been watching AI coding agents fail in production for long enough that we started keeping a taxonomy.

Not "the agent hallucinated" — that's not a failure class, it's a category. The real failure modes are specific, they repeat, and crucially, they each require a different fix.

Here's what we found across hundreds of real runs, and why it changed how we think about agent governance.

The failure modes that actually kill agent runs:

1. Hallucination —