# Confidence (/docs/memory/intelligence/confidence)
Not every memory deserves the same trust. A fact confirmed by two systems is more reliable than a passing remark from one conversation. Docklee gives each memory a confidence that changes over time, and uses it when it ranks recall results.

## What raises and lowers confidence [#what-raises-and-lowers-confidence]

| Signal | Effect |
| --- | --- |
| The source of the memory | Some sources are more reliable than others, and the starting confidence reflects that. |
| How clearly it could be classified | A memory with an obvious type starts higher than an ambiguous one. |
| Agreement from another memory | Raises confidence for both memories. |
| A conflicting memory | Lowers confidence, and both memories are flagged for review. |
| Age without use | Lowers confidence slowly over time. |

## Agreement [#agreement]

When two memories state the same fact, even in different words or from different sources, Docklee links them and raises the confidence of both:

| Memory | From |
| --- | --- |
| "Customer prefers dark mode." | Your support chat, through `Dock` |
| "User setting: dark theme enabled." | Your settings service, through the API |

Recall then ranks the preference higher than a fact stated only once.

## Low confidence goes to review [#low-confidence-goes-to-review]

A memory whose confidence falls too low is flagged for review instead of being dropped. A person decides whether to keep, correct, or remove it. See [Review and correction](/docs/memory/governance/review-and-correction).

## Confidence in recall results [#confidence-in-recall-results]

The `confidence` on a recalled record (`confidence_score` over HTTP) is a score from 0 to 1 for how well that memory answers your query. It combines relevance with the memory's own confidence and the other ranking signals.

<CodeTabs items={['Python', 'TypeScript']}>
  <Tab value="Python">
    ```python
    records = lynk.recall_sync("Which theme does the customer use?")
    trusted = [record for record in records if record.confidence >= 0.6]
    ```
  </Tab>
  <Tab value="TypeScript">
    ```ts
    const records = await lynk.recall('Which theme does the customer use?');
    const trusted = records.filter((record) => record.confidence >= 0.6);
    ```
  </Tab>
</CodeTabs>

<Callout type="idea">
Pick a cutoff by testing your own questions. A fixed cutoff that suits one memory space can be too strict for another.
</Callout>

## Next steps [#next-steps]

You know how trust is scored. See how memories connect to each other next.

<Cards>
  <Card title="Entities and links" href="/docs/memory/intelligence/entities-and-links" description="People, companies, and the links between memories." />
  <Card title="Ranking" href="/docs/memory/intelligence/ranking" description="Every signal recall uses." />
  <Card title="Contradictions and updates" href="/docs/memory/intelligence/contradictions-and-updates" description="What happens when facts conflict." />
</Cards>
