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

# Coverage auditor

> An autonomous agent that finds undocumented Salesforce components and proposes brand-new docs — evidence-backed, styled to your templates, delivered to the Inbox.

Most documentation tooling only updates what already exists. The coverage auditor closes the other gap: it finds important Salesforce components that have **no documentation at all** and drafts new docs for them, so your coverage grows without anyone assigning writing work.

Everything it produces lands in the [Inbox](/guides/inbox) as a **new doc** proposal for you to review.

## How a run works

<Steps>
  <Step title="Find undocumented components">
    The auditor scans your synced Salesforce catalog for components with **zero doc tags** — nothing in your docs claims to cover them. It respects your coverage eligibility settings, so components you've excluded (for example, managed-package namespaces) are never proposed. See [Coverage](/guides/coverage).
  </Step>

  <Step title="Rank by importance and recency">
    Candidates are ranked so the components that matter most — heavily referenced, recently changed — come first.
  </Step>

  <Step title="Check your docs corpus first">
    Before drafting anything, the auditor searches your existing documentation. If a component is already meaningfully mentioned somewhere, it's skipped — no duplicate pages.
  </Step>

  <Step title="Require real evidence">
    The auditor only writes about what it can actually see. Components with hidden or empty source are skipped rather than guessed at, and skips are remembered for **30 days** so the same dead ends aren't retried every run.
  </Step>

  <Step title="Draft and file">
    For each surviving candidate, the auditor drafts a doc per configured doc type, grounded in the component's real metadata and shaped by your [templates and style](/guides/templates-and-style). The batch is filed into the Inbox as new-doc proposals.
  </Step>
</Steps>

<Note>
  This is the same rule every LivingContext agent follows: **grounded or it doesn't ship**. A proposal without evidence is a skip, not a guess.
</Note>

## Configure it

Configuration lives at **Settings → Doc suggestions**:

| Setting               | Options                                                                                                                                                                                                               |
| --------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Run on a schedule** | Turn scheduled auditing on or off                                                                                                                                                                                     |
| Frequency             | Daily, weekly, monthly, or manual only                                                                                                                                                                                |
| Doc types             | Which kinds of docs it should draft — functional (process guide, user FAQ, business glossary, onboarding guide) and technical (technical reference, integration doc, data dictionary, runbook, troubleshooting guide) |
| **Max per run**       | How many proposals per batch, 1–20 (default **5**)                                                                                                                                                                    |
| **Run now**           | Trigger a run immediately with the saved settings, even when the schedule is off                                                                                                                                      |

A status line shows the cadence and the last run's outcome — how many undocumented components were scanned and how many docs were proposed. Scheduled runs ride the shared agent sweep, which checks every 15 minutes whether a run is due — enabling the schedule starts the first audit within one tick. See [Agents overview](/agents/overview#how-often-agents-run).

<Tip>
  Start with a low **max per run** and weekly frequency. Reviewing five well-grounded proposals a week is sustainable; fifty at once is not.
</Tip>

## Reviewing proposals

New-doc proposals appear in the [Inbox](/guides/inbox) alongside commit-driven updates, grouped as suggestions. For each one you can read the full draft, see why the component was proposed, and accept or dismiss it.

When you accept and ship a proposal, the new doc is **automatically tagged to the Salesforce component that prompted it** — so the component immediately counts as documented in [Coverage](/guides/coverage), and future org changes to it will trigger freshness checks.

## What it won't do

* It never publishes directly — every draft goes through Inbox review and lands as a normal change in your Git repository.
* It never proposes components excluded by your eligibility settings.
* It never fabricates content for components whose source it can't read.