# Prompt less, check more

> An AI agent can follow a rule in one reply and break it in the next. We tested code checks on proposed messages and actions, with specific feedback when a check fails. Carefully designed checks reduced detected violations in our tests. Poorly designed checks made agents less effective.

- Published: 2026-09-14
- Author: Jake Spillane, Hivemind Labs
- Full article: https://hivemind.au/insights/prompt-less-check-more

## Key findings

- Tested on τ²-bench, IFEval and 74 previously rejected production turns.
- Precise checks cut detected violations without hurting task completion.
- Generic retries and poorly designed checks made agents worse, so check the false-positive rate first.