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

# Review AI work

> Approve, correct, or reject what Florent drafted — value by value, with citations to the source.

When Florent reads a document and writes values onto a record, every value arrives **unverified**. Reviewing AI work is how you check each value against its source and decide, one value at a time: this is correct (**Approve**), or this is wrong (**Reject**). Florent drafts; you decide what becomes trusted data.

This page covers two things you do constantly: verifying a value against its source with a **citation**, and locking it in with **field review**.

<Note>
  Reviewing AI values is a permission. **Admin**, **Manager**, and **Builder** can approve and reject; a **Member** sees the values and their citations but the controls are read-only. See [Roles and permissions](/admin/roles-and-permissions).
</Note>

## Two gates, don't confuse them

You meet two different "approval" moments around AI work, and they answer different questions.

* **Task approval** — "May these drafted records be written at all?" A one-time gate inside a [run](/projects/run-a-playbook): an approver lets the drafted values land. This page does not own that model — see [Assignments and approvals](/playbooks/assignments-and-approvals).
* **Field review** — "Is each individual value human-verified?" Ongoing, per-value state on the record, done **after** the values have landed. This is what this page is about.

The normal sequence: the task is approved, the values land on records as **Pending review**, then you approve or reject each value. Approving the task does not approve the fields, and approving the fields does not approve the task.

## Verify before you approve: citations

Every value Florent extracts carries a **citation** — a pointer back to exactly where it came from: the file, the page, the highlighted region on that page, and the quoted text the AI relied on. Click a value to see the original passage instead of taking Florent's word for it.

Two small chips sit next to each AI value:

* **The confidence chip.** A small badge that rates how sure Florent is about the value (an icon out of 5 — green for 4–5, amber for 3, red for 1–2). Hover it to see the score and the AI's reasoning in a tooltip. For an empty value, the chip reads either **Confirmed absent** (Florent is confident the field genuinely isn't in the document) or **Not found — review** (Florent couldn't find it and you should check). You may also see **Scoring…** while scoring is in progress, or **Not scored**.
* **The source-count chip.** A small quote-mark badge with a number — how many citations back this value. A value with one citation opens its source directly; a value with several opens a short **Cited sources** list first so you pick which one to inspect.

<Tip>
  The reasoning in the hover tooltip lets you tell a confidently-absent field from a missed one **before** you even open the source. A **Confirmed absent** value is usually safe to approve; a **Not found — review** value is worth opening.
</Tip>

### What the source viewer shows

Click a citation to open the cited source.

<Steps>
  <Step title="Open the cited source">
    Press the confidence chip or the source-count chip on the value. The source viewer opens — filling the document pane in the record panel, or as a modal titled **Source for {field}** from a standalone chip.
  </Step>

  <Step title="Confirm the page and region">
    The original file renders inline, scrolled to the cited page (shown as a **Page N** badge) with the cited region highlighted. Read the **Cited text** banner underneath — the exact quote Florent used — and check that the highlighted passage actually says what the value claims.
  </Step>

  <Step title="Check the reasoning, if you need it">
    The viewer repeats the confidence chip and shows the AI's reasoning for the score (or, for an empty value, why it judged the field absent). A **Download** button pulls the original file if you want to open it yourself.
  </Step>
</Steps>

<AccordionGroup>
  <Accordion title="Audio and video sources">
    For a transcribed recording, the viewer shows a **Transcript** pane with speaker and timestamp lines instead of a PDF, scrolled to and highlighting the cited passage. The header reads **Transcript** with the recording's duration.

    {/* TODO: Screenshot — A transcript source: the Transcript pane with a highlighted line at a timestamp */}
  </Accordion>

  <Accordion title="Files that can't be previewed">
    A non-PDF, non-transcript source can't be shown inline. The viewer reads **This source can't be previewed here** and prompts you to use **Download** to open it. You still get the quoted **Cited text**.
  </Accordion>

  <Accordion title="A missing source file">
    If the cited file was deleted from the project, the viewer reads **This field cites a source file that couldn't be found.** The value is still there; only the linked file is gone.
  </Accordion>
</AccordionGroup>

## Field review: approve, reject, lock

Once you've verified a value, you record your decision. Each AI value shows a status badge that doubles as the menu trigger.

| Badge              | Meaning                    | Locked? |
| ------------------ | -------------------------- | ------- |
| **Pending review** | Awaiting your decision     | No      |
| **Approved**       | You confirmed it's correct | Yes     |
| **Rejected**       | You flagged it as wrong    | Yes     |

A fresh AI value lands as **Pending review**. You pick **Approve** or **Reject**, and the value locks. To re-open a locked value, use **Dismiss**, which returns it to **Pending review**. Dismiss is the only way to unlock.

<Warning>
  **Approved** and **Rejected** both lock the value — they protect it identically and differ only in meaning. **Rejecting does not delete or blank the value**; it flags it as wrong and surfaces it as follow-up work in [My work](/work/my-work). To actually fix a wrong value, **Dismiss** it first, then edit it (see [The project Data tab](/projects/data)).
</Warning>

### Review one value at a time

<Steps>
  <Step title="Open the record">
    Open a record from the [records table](/projects/data) to slide out the record panel. Each AI-written field shows its citation chip and its review status badge next to the label.
  </Step>

  <Step title="Verify the value">
    Use the citation chip to check the value against its source, as above.
  </Step>

  <Step title="Approve, Reject, or Dismiss">
    Press the status badge to open its menu — **Approve**, **Reject**, **Dismiss**. The item matching the current state is greyed out (when a value is already **Approved**, **Approve** is disabled).
  </Step>
</Steps>

<Note>
  Only **AI-written fields** carry review controls — a value has something to verify only when there's a citation behind it. A value a person typed by hand shows no review badge. If a field you expected to review has no badge, it was entered by a person, or Florent didn't ground it.
</Note>

### Review a whole record or a whole column at once

<Tabs>
  <Tab title="A whole record">
    At the bottom of the record panel, **Approve all on this record** approves every AI-written value on that record in one click. It appears only when you have review permission and the record actually has AI fields.
  </Tab>

  <Tab title="A whole column">
    In the records table, the column header for an AI-written field has a small dropdown (a down-arrow). Its menu — **Approve this column**, **Reject this column**, **Dismiss this column** — reviews that one field across every record in the current table that has an AI value for it. Use it to bulk-approve a field you trust across a whole import.
  </Tab>
</Tabs>

## What locking protects against

Approving or rejecting a value locks it, which matters in three concrete ways.

<AccordionGroup>
  <Accordion title="Later runs leave it alone">
    If a playbook re-runs and would have updated that field, it skips your locked value — neither the value nor its citation changes. Approve the values you trust to freeze them before any re-run.
  </Accordion>

  <Accordion title="Florent leaves it alone">
    When Florent proposes changes to an existing record, it strips out any locked fields from its proposal and tells you which fields it left untouched.
  </Accordion>

  <Accordion title="No silent hand-edits">
    A direct edit to a locked field is refused with a message telling you to **Dismiss the review first**. There's no silent overwrite path — unlocking is always deliberate.
  </Accordion>
</AccordionGroup>

<Warning>
  A run can finish (**Done**) with values still **Pending review** or **Rejected** — review is decoupled from run completion. Don't expect the run to wait for you. Chase outstanding review from [My work](/work/my-work) instead.
</Warning>

## Reviewing inside a run

When a [Document or AI task](/playbooks/task-types) drafts records, the approver opens a **Drafts to review** panel inside the run before anything is written. Each drafted record shows its fields, the confidence chips, and citations — and a per-draft state of **Ready** or **Needs changes**.

<Steps>
  <Step title="Open each source to verify">
    Use the citation chips to confirm the drafted values against their sources, exactly as on a record.
  </Step>

  <Step title="Fix anything that needs it">
    Edit a draft and **Save changes**, or **Discard** a draft you don't want. A draft marked **Needs changes** must be fixed or discarded before the rest can go through. Partial approval is allowed — some rows save, the others stay parked with a per-row reason.
  </Step>

  <Step title="Approve or reject">
    **Approve values** writes the drafts into the record type as records. **Reject** sends the task back — rejecting requires a reason, so type why before you confirm.
  </Step>
</Steps>

For generated documents, the in-run panel reads **Documents to review** — open each one to confirm it reads correctly, then **Approve documents**. Approved documents become part of the [project's files](/projects/files).

<Info>
  Approving the task is one gate; the values it writes still land as **Pending review** for field-level review. The rules for who can approve a task — including the assignee's manager — live in [Assignments and approvals](/playbooks/assignments-and-approvals).
</Info>

## Reviewing a batch

When an action runs over many files or records at once, every result is reviewed in a grid rather than one record panel — same citations, same Approve/Reject, shown in a two-column view per row. That flow is covered in full on [Batch action runs](/actions/batch-runs).

<Note>
  One difference to remember: rejecting a **field** never deletes anything, but rejecting a generated document in a batch run **deletes** the generated file. See [Batch action runs](/actions/batch-runs).
</Note>

## Where to go next

<CardGroup cols={2}>
  <Card title="Assignments and approvals" icon="user-check" href="/playbooks/assignments-and-approvals">
    Who can approve a task, and when approval is forced.
  </Card>

  <Card title="Batch action runs" icon="layout-grid" href="/actions/batch-runs">
    Run an action over many items and review every result in a grid.
  </Card>

  <Card title="The project Data tab" icon="database" href="/projects/data">
    Browse, filter, and edit the records your reviews produce.
  </Card>

  <Card title="Task types" icon="list-checks" href="/playbooks/task-types">
    How Document and AI tasks draft the records you review.
  </Card>
</CardGroup>