> 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/getting-started.md).

# Getting Started

Get your team up and running with Notara in four steps. Most teams are sending their first agent messages within 15 minutes.

## The Four-Step Flow

### Step 1: Sign Up & Onboarding

Create your Notara account at [app.notara.ai](https://app.notara.ai). You can sign up with email and password, or authenticate directly via Slack OAuth. During onboarding, you'll:

* Enter basic company info (name, description, industry)
* Add your BYOK LLM key — Notara requires you to bring your own key for the AI model
* Set up a Stripe subscription to activate your workspace

→ [Detailed onboarding walkthrough](/notara-docs/getting-started/onboarding.md)

### Step 2: Connect Slack

Install the Notara Slack app into your workspace. This is what gives the agent a presence in your Slack — a bot user that can receive mentions, respond in threads, and send direct messages.

You'll be redirected through a Slack OAuth flow. Once authorized, the Notara bot will appear in your Slack sidebar and introduce itself with a welcome message.

→ [Slack setup guide](/notara-docs/getting-started/slack-setup.md)

### Step 3: Configure a Channel

Invite the bot to one of your Slack channels and configure it from the dashboard. Channel configuration lets you set:

* Which tools the agent has access to in this channel
* Which context collections are loaded for this channel
* Which skill profile is active (growth, engineering, full)
* Per-channel tool permission overrides

→ [Channel configuration guide](/notara-docs/getting-started/channels.md)

### Step 4: Start Using

Tag `@Notara` (or whatever you named your bot) in the configured channel, or send it a direct message. Ask it anything: look up a Linear issue, summarize a document from your library, draft a message, run a web search — whatever your connected tools and context support.

For deeper power-ups:

* [Connect your first tool connector](/notara-docs/connectors.md) — Linear, GitHub, Stripe, and more
* [Build a context library](/notara-docs/libraries.md) — upload your handbook, runbooks, API docs
* [Set up automations](/notara-docs/automations.md) — weekly digests, scheduled reports
* [Connect an external agent via MCP](/notara-docs/mcp.md) — use your workspace from Claude Code or Cursor

## What You'll Need

| Requirement         | Notes                                             |
| ------------------- | ------------------------------------------------- |
| Slack workspace     | Admin or app-install permission                   |
| LLM API key         | Anthropic, OpenAI, Gemini, Kimi, GLM, or DeepSeek |
| Stripe subscription | Pro plan at $299/mo                               |
| Modern browser      | Chrome, Firefox, Safari, or Edge                  |

## Need Help?

Check the [FAQ](/notara-docs/faq.md) for common questions, or email <support@notara.ai>.


---

# 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/getting-started.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.