8Decisions under the agent kit
Confidence bands
The agent kit maps every answer to an action by its confidence. These tables replay that mapping on every answer in the run.
| choice band | Rule | Agent action | Answers | Share | Correct | Accuracy |
|---|---|---|---|---|---|---|
trust | confidence >= 0.85 | act on it | 4 | 13.3% | 2 | 50.0% |
verify | 0.60 <= confidence < 0.85 | act, say so, and verify | 13 | 43.3% | 10 | 76.9% |
defer | confidence < 0.60 | gather evidence or ask the user | 13 | 43.3% | 5 | 38.5% |
| noul band | Rule | Agent action | Answers | Share | Correct | Accuracy |
|---|---|---|---|---|---|---|
yes | P >= 0.80 | treat as yes | 0 | 0.0% | 0 | n/a |
no | P <= 0.20 | treat as no | 0 | 0.0% | 0 | n/a |
unsure | 0.20 < P < 0.80 | treat as unsure | 0 | 0.0% | 0 | n/a |
Coverage and accuracy
choice: coverage and accuracy as the threshold rises. Dashed lines mark the kit's thresholds.Default project policy
The agent kit's AGENTS.md snippet ships a default project policy. The report replays it on every item and counts what an agent following it to the letter would have done: the right thing, a cautious extra step (an unnecessary question or review), or a wrong action (acting on a vague request, or shipping a risky change unreviewed).