> For the complete documentation index, see [llms.txt](https://notara.gitbook.io/notara-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://notara.gitbook.io/notara-docs/connectors/perplexity.md).

# Perplexity

The Perplexity connector gives the Notara agent access to real-time web research. Unlike the agent's training data cutoff, Perplexity can fetch and synthesize current information — today's news, recent documentation changes, competitor pricing, and anything else on the live web.

## What It Enables

| Tool                     | Capability | Description                                                     |
| ------------------------ | ---------- | --------------------------------------------------------------- |
| `perplexity_search`      | `read`     | Research a topic and return a synthesized answer with citations |
| `perplexity_search_news` | `read`     | Find and summarize recent news on a topic                       |

Both tools execute immediately — they're read-only and have no side effects.

## Setup

**No setup required.** Perplexity is a platform connector — Notara manages the API key for you. It's available to all Pro plan workspaces.

To enable it:

1. Go to **Tools** in the Notara dashboard.
2. Find **Perplexity** and click **Enable**.
3. The connector is active immediately.

Usage counts toward your workspace's monthly credit allocation (1 credit = 10,000 tokens; Perplexity searches typically consume 1,000–3,000 tokens per query).

## Usage Examples

**Research a competitor:**

```
@Notara Research Linear's latest pricing changes and compare to what we offer.
```

**Get current documentation:**

```
@Notara What's the latest Anthropic Claude API pricing as of today?
```

**News briefing:**

```
@Notara Give me a briefing on AI coding assistant news from the past week.
```

**Technical research:**

```
@Notara What are the current best practices for pgvector index tuning in Postgres 17?
```

## Using Perplexity in Skills

Perplexity shines when combined with Skills. For example:

**Competitor monitoring skill:** a scheduled automation that runs every Monday, uses `perplexity_search_news` to find competitor announcements, and posts a digest to your `#growth` channel.

**Market research skill:** a skill that takes a company name as input, uses Perplexity to research it, and returns a structured brief using your custom prompt template.

To use Perplexity in a skill, include it in the skill's **Bound Tools** when editing the skill. The tool will be available to the agent when the skill is active.

## Bringing Your Own Perplexity Key

If you have a higher Perplexity rate limit or prefer to manage costs directly, you can connect your own Perplexity API key:

1. Obtain a key from [perplexity.ai](https://www.perplexity.ai/settings/api).
2. In Notara, go to **Tools → Perplexity → Advanced**.
3. Enter your API key and click **Save as BYOK**.

Your own key will be used instead of the platform key, and Perplexity usage will be billed directly to your Perplexity account rather than counting against Notara's platform allocation.

## Rate Limits

With the platform key, Perplexity searches are subject to reasonable fair-use limits. If your team runs many research-heavy automations, consider bringing your own key for dedicated capacity.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://notara.gitbook.io/notara-docs/connectors/perplexity.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.