AI Systems Atlas

E-06Failure Taxonomy

/evals/failure-taxonomy

Classify every failure by where in the loop it originated — perception, reasoning, planning, tool use, recovery, verification, or the final answer.

Key insight

The distribution tells you what to fix next. A recovery-heavy histogram wants a better retry loop, not a bigger model.

Failure mode

Buckets so broad (“reasoning”) that every failure fits and none suggests an intervention.

Further reading
RelatedTrajectory evalRetry loop

Elsewhere in the atlas

Harnesses →Security →Context →Coding Agents →