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

# Inspiration

> Read tracked accounts, outliers, and brand-account performance to ground every decision.

Inspiration is the research layer. It reads the accounts you track, the outliers (top-performing content) from them, and your own brand-account performance. It is the grounding the [pipeline](/guides/pipeline) draws on before any draft.

## Operations

| What                           | MCP tool                                               |
| ------------------------------ | ------------------------------------------------------ |
| Tracked inspiration accounts   | `list_inspiration_accounts`, `get_inspiration_account` |
| Content from a tracked account | `get_inspiration_content`                              |
| Outliers (top performers)      | `list_outliers`                                        |
| Your own brand accounts        | `list_brand_accounts`                                  |
| Your own account performance   | `get_brand_account_performance`                        |

All reads need `brandkit:read`.

## Scoping to a brand kit

Most reads accept a `brandKitId` so you see only the accounts and outliers linked to one brand. `list_outliers --brand-kit <id>` (CLI) or the `brandKitId` argument (MCP) narrows the pool. If a scoped read comes back empty, the brand kit may have no linked accounts; check `get_brand_kit` for its `inspirationAccounts` and `brandAccounts`. Accounts are linked to a brand kit in the app.

## Mining outliers (the two-step)

Outliers carry the signal that makes a draft perform. List them, then go deep on the best.

<Steps>
  <Step title="List">
    `list_outliers` (scoped with `brandKitId`) to find the top performers. Each carries performance signals.
  </Step>

  <Step title="Get content">
    `get_inspiration_content` on the top few for the full detail: transcript, hashtags, and the structure you want to learn from (hook archetype, pacing, CTA).
  </Step>
</Steps>

This two-step is the Ground phase of the pipeline. The patterns you extract here are what the host LLM emulates, in the user's own voice, when it drafts.