Research prototype

Intent-monitor

Question: what can recorded actions tell us that an agent's stated plan alone cannot?

Inspect the prototype and its offline demo

The idea

A reassuring explanation is not independent evidence of what an agent did. Intent-monitor compares claims in a provided reasoning trace with a recorded tool-call ledger and flags certain inconsistencies.

It compares three approaches on constructed examples: reasoning-text-only monitoring, a tool-name blocklist, and a stated-plan/ledger comparison.

The safety thinking

The prototype asks which signal a monitor observes, what its baseline misses, and which benign actions it should not flag. Positive examples alone would not answer the false-positive question, so the demo also includes benign cases with explicitly licensed actions.

The recorded ledger is action evidence. It is not a window into the model's true motives.

What is and is not established

The default extractor is a deterministic regex stub. The fixtures are hand-built. Results show how the mechanism behaves on those examples, not a naturalistic catch rate.

The default comparison works at verb-class granularity; target and argument reconciliation is not established by that stub. Real-model paths do not, on their own, validate general effectiveness.

This is a research prototype to inspect and question, not a production safety product, peer-reviewed result, or guarantee of detecting harmful behavior.

agent-safetymonitoringevaluation

Start a conversation about this work.