# verify-loop: audit memory one claim at a time

Works a queue of uncertain memory claims, exhausting every source family before bringing the human exactly one question, with the evidence attached.

From the [Skills I've built](../index.md#skills) section of [The Muse Field Guide](../index.md).

## What it does

An interactive verification loop for the agent's stored knowledge: take one medium-confidence claim, exhaust every source family that could settle it, run the question pre-flight, and only then bring the human the next single question. It powers the Verify lane pattern in this inventory.

## Trigger

A verification round over stored claims, run as a standing practice in its own chat.

## What you need

- A store of claims with confidence levels, so the uncertain ones form a queue.
- Source families to check before asking: records, messages, files, and the human only last.
- A human willing to rule one question at a time.

## Setup sketch

The caveat is the design: the queue is never empty for long, because new claims keep arriving. The skill works precisely because it refuses to declare the data clean while a residue remains.

## Where this came from

House rules for the lane were set by the operator on October 19, 2026: one question per message, never a batch; and never a report that there is nothing to do while the underlying data is not fully verified clean.

Deep dive: [Memory that holds](../deep-dives/memory.md)

Related resources: [The Verify lane: one claim at a time](the-verify-lane.md), [Steal this setup: a Verify lane](verify-lane-starter.md), [Run a pre-flight before asking](preflight-before-asking.md)

Canonical page: https://www.niclydon.io/muse/items/verify-loop.html