> ## Documentation Index
> Fetch the complete documentation index at: https://docs.clavata.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Content Feed

> Review the content your labels have evaluated in production, see each label result, and filter by label and label version.

<Note>
  This is Moonbounce's label-first experience. If you're looking for the
  policy-first experience, switch using the version selector above.
</Note>

The **Content Feed** shows the content you've sent to the evaluate API, along
with how your labels scored it. Use it to spot-check results, find edge cases,
and pull real examples back into a label's dataset.

<Warning>
  The feed displays live content from your evaluation traffic, so you may
  encounter toxic, offensive, or otherwise harmful material. You'll be asked to
  acknowledge this before the feed is shown.
</Warning>

## What each row shows

Every entry is a piece of content that was evaluated, paired with the label
result for it:

* **Content** — the text or image that was evaluated.
* **Result** — whether the content matched the label, based on whether its
  confidence met the label's threshold.
* **Confidence** — how strongly the label matched.
* **Version** — the label version that produced the result.

Rows are sorted newest-first by default.

## Filtering the feed

Pick the slice you want to review:

* **Label** — choose which label's results to look at.
* **Label version** — narrow to a specific published version of that label.
* **Date range** — limit the feed to a time window.
* **Confidence** — isolate uncertain or high-confidence results by score range.

You can also sort by recency or by confidence.

## Curating datasets from the feed

The feed is also a workspace for improving a label. Select one or more items and
add them to a label's dataset to capture real edge cases — both content the
label *should* match and content it *shouldn't* — then test against them as you
refine.

## Where to next

<CardGroup cols={2}>
  <Card title="Labels, Versions & Datasets" icon="layer-group" href="/v2/labels_versions_datasets">
    How drafts, published versions, and per-label datasets fit together.
  </Card>

  <Card title="Integrating a Label" icon="plug" href="/v2/integrating_a_label">
    Send a label version to the evaluate API so its results show up here.
  </Card>
</CardGroup>

***

## We'd Love to Hear From You

Whether you have a suggestion, feedback, or a bug to report, here are the best ways to get in touch:

* **In the App:** Use the **Feedback button** for direct suggestions.
* **On Slack:** Reach out to the team in your shared channel.
* **With your AM:** Talk to your dedicated account manager.
* **Via Email:** Send a message to [**support@moonbounce.io**](mailto:support@moonbounce.io).
* **Security, availability, or other incidents:** Use the in-app **Feedback button** or email [**support@moonbounce.io**](mailto:support@moonbounce.io). See [Customer Feedback](/feedback/customer_feedback) for what to include.