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

# Prompts

> Peec AI ships native MCP prompts: ready-to-run analysis workflows exposed as slash commands in your AI tool. Each prompt runs a scripted sequence of tool calls and formats the output for you.

Prompts are a built-in MCP primitive. Instead of asking your AI assistant to combine tools step-by-step, you invoke a single slash command and get a fully formatted report back.

<Note>
  Prompts are versioned with the Peec AI MCP server. When we ship a new one, it appears in your client automatically. No install.
</Note>

## How to invoke a prompt

The command surface depends on your client.

| Client                      | How to invoke                                                   |
| --------------------------- | --------------------------------------------------------------- |
| Claude (Desktop, Web, Code) | Type `/` in the message input and pick the prompt from the list |
| Cursor                      | Type `@` in the chat and pick the prompt                        |
| Other MCP clients           | Check your client's documentation for prompt support            |

<Tip>
  If prompts don't show up after connecting, remove and re-add the Peec AI integration to refresh the tool and prompt list.
</Tip>

## Available prompts

All prompts take a `project` argument (name or ID). Your AI assistant resolves the name for you, so `"Acme Q2"` works as well as a project ID.

### peec\_weekly\_pulse

**Weekly Visibility Pulse.** Week-over-week digest covering brand metrics, competitor movers, source shifts, and sentiment flags. Formatted for sharing internally.

| Argument  | Required | Description        |
| --------- | -------- | ------------------ |
| `project` | Yes      | Project name or ID |

Use when: you want a quick Monday-morning snapshot of what changed last week.

***

### peec\_competitor\_radar

**Competitor Movement Radar.** Scans every brand × topic × engine combination for significant shifts. Returns the biggest gainers and losers, hypothesized drivers, and the topics where your own brand is most exposed.

| Argument       | Required | Description                                             |
| -------------- | -------- | ------------------------------------------------------- |
| `project`      | Yes      | Project name or ID                                      |
| `threshold_pp` | No       | Minimum percentage-point change to flag (default: `10`) |

Use when: a competitor suddenly seems more visible and you want to know where and on which engines.

***

### peec\_engine\_scorecard

**AI Engine Scorecard.** Per-engine breakdown of brand visibility, share of voice, sentiment, position, plus source retrieval and citation rate from your own domains. Highlights the engine with the most untapped potential.

| Argument  | Required | Description        |
| --------- | -------- | ------------------ |
| `project` | Yes      | Project name or ID |

Use when: you want to know which AI engine to focus on next.

***

### peec\_topic\_heatmap

**Topic × Model Heatmap.** Visibility heatmap across all your topics and all tracked AI engines, calibrated to your own baseline so cells are labeled as blind spots, weak, moderate, strong, or dominant.

| Argument  | Required | Description        |
| --------- | -------- | ------------------ |
| `project` | Yes      | Project name or ID |

Use when: you want to find blind spots and strongholds across topics and engines at a glance.

***

### peec\_prompt\_grader

**Prompt Set Grader.** Grades your tracked prompt set on topic balance, tag hygiene, funnel coverage, branded/unbranded segmentation, duplicate detection, and model data gaps. Returns an A-F report card with the top 3 fixes.

| Argument  | Required | Description        |
| --------- | -------- | ------------------ |
| `project` | Yes      | Project name or ID |

Use when: you suspect your prompt set is skewed, incomplete, or noisy.

***

### peec\_source\_authority

**Source Authority Audit.** How your domains perform as sources across AI engines: retrieval rates, citation rates, top URLs, content type breakdown, and authority gaps where competitors are cited but you are not.

| Argument  | Required | Description        |
| --------- | -------- | ------------------ |
| `project` | Yes      | Project name or ID |

Use when: you're optimizing content and want to know which URLs and formats get picked up by AI.

***

### peec\_campaign\_tracker

**PR / Campaign Impact Tracker.** Before/after comparison around a launch date. Tracks brand metrics and source pickup, broken down by engine. Pass specific URLs to track a PR push, or omit them to analyze your whole domain.

| Argument        | Required | Description                                                                         |
| --------------- | -------- | ----------------------------------------------------------------------------------- |
| `project`       | Yes      | Project name or ID                                                                  |
| `campaign_date` | Yes      | Launch date in `YYYY-MM-DD` format                                                  |
| `urls`          | No       | Comma-separated URLs to track. If omitted, analyzes your own brand domains broadly. |

Use when: you shipped a PR campaign, guest post, or content refresh and want to measure AI impact.

## Combining prompts with free-form questions

Prompts are a starting point. After a prompt runs, follow up with questions in plain language. Your AI assistant still has access to every [tool](/mcp/tools), so you can drill into any row, engine, or topic.

> *"Run the weekly pulse, then dig into why Perplexity visibility dropped"*
> *"After the competitor radar, show me the chats from last week that mentioned Acme"*

<Info>
  Prompts are read-only. They only use the same Peec AI data you can already see in the dashboard.
</Info>