# Perplexity playbooks

Perplexity is an answer engine that searches the web and replies with cited sources. Paid plans add deeper Research reports, a choice of models from several labs, and file and app creation. People use it for quick fact finding, longer research and questions over their own files and connected apps.

- Vendor: Perplexity AI
- Kind: assistant
- Surfaces: web, desktop, mobile, api
- Connects: The Mac app connects to local MCP servers through the PerplexityXPC helper, rolling out to paid plans first. Built-in connectors cover Gmail, Google Calendar, Google Drive, Notion, Slack, GitHub, Jira and more.

- Docs: https://www.perplexity.ai/help-center/en/

## Good at

- Answers with links to the sources it used, so you can check them
- Research mode, which runs many searches and writes a long report
- Questions over connected apps such as Gmail, Google Drive, Notion and Slack

## Limits

- Perplexity says access to advanced models may be limited when usage is heavy.
- Local MCP servers work only in the Mac app, and the help center lists remote MCP as coming soon.
- It answers and writes reports, but it does not click through websites for you. That job belongs to its Comet browser.

## Playbooks (3)

- [Find the questions AI assistants answer without naming your brand, and plan content to fix it](https://agentshandbook.com/p/find-questions-ai-answers-without-citing-you.md): You get a table of buyer questions with your mention rate, competitors' mention rates and cited sources per assistant, plus a short content plan for the biggest gaps that you approve. (trust: corroborated, risk: low)
- [Research a specific property address and compile a dossier on sales, zoning, and risk](https://agentshandbook.com/p/research-a-property-address-and-build-a-dossier.md): You get a structured dossier covering the key data points for a specific property, with sources for each claim, ready to cross-check before you rely on it. (trust: reported, risk: medium)
- [Run a deep research report and check that every citation supports its claim](https://agentshandbook.com/p/run-a-deep-research-report-and-verify-its-citations.md): You get a report where every factual claim links to a source that loads and says what the report claims, plus a table of the claims you cut or changed.
 (trust: corroborated, risk: medium)

## Lessons

- [AI research tools cite sources that are broken, made up, or do not say what is claimed](https://agentshandbook.com/lessons/ai-research-citations-fail-to-support-claims.md)