# Welcome

tagIt helps teams build, govern, observe, and improve **AI journeys** inside real products and workflows.

Most teams do not need another standalone chat surface. They need AI experiences that can be embedded into applications, connected to tools, governed by product and operations teams, and improved using real engagement signals.

tagIt brings those pieces together:

* **AI Orchestrator** runs agentic use cases through an API service that any authorized client or backend service can call.
* **AI Presence** captures AI and non-AI engagement signals so teams can understand the full journey, not just the chat transcript.
* **AI Canvas** provides a ready-to-use AI client and reference implementation for teams building their own front-end experience.

## Use these docs with your AI assistant

These docs are designed to be AI-friendly. You can point an AI assistant at this GitBook and ask it to help you plan, configure, integrate, or troubleshoot tagIt.

If your AI development environment supports MCP, connect it to the published tagIt GitBook MCP server:

```
https://tagit.gitbook.io/tagit/~gitbook/mcp
```

For setup details, see GitBook's [MCP server for published docs](https://gitbook.com/docs/publishing-documentation/mcp-servers-for-published-docs).

Good prompts include:

* "Use the tagIt docs to help me design my first agentic use case."
* "Summarize the minimum API fields I need to call the AI Orchestrator."
* "Help me decide whether this should be an Agentic Turn or Agentic Workflow."
* "Walk me through setting up AI Presence for an embedded chat experience."
* "Compare the AI Canvas setup with calling the Orchestrator API directly."

For AI assistants, see [AGENTS.md](/tagit/agents.md). It gives models a short operating guide for how to read and use this documentation.

## Start here

If you are new to tagIt, begin with:

1. [What is tagIt?](/tagit/getting-started/what-is-tagit.md)
2. [AI journeys overview](/tagit/getting-started/ai-journeys-overview.md)
3. [Concepts](/tagit/getting-started/concepts.md)
4. [Quickstart](/tagit/getting-started/quickstart.md)

## Build your first journey

For a practical setup path, use the guides in this order:

1. [Create a new account](/tagit/guides/guides/create-account.md)
2. [Add users and manage account access](/tagit/guides/guides/manage-account-users.md)
3. [Create and set up a context](/tagit/guides/guides/create-and-set-up-context.md)
4. [Set up context AI Orchestration](/tagit/guides/guides/set-up-context-ai-orchestration.md)
5. [Create and set up an agentic use case](/tagit/guides/guides/create-and-set-up-agentic-use-case.md)
6. [Set up context Tags](/tagit/guides/guides/set-up-context-tags.md)
7. [Set up AI Presence](/tagit/guides/guides/set-up-ai-presence.md)

You do not need every capability on day one. Start with the smallest useful AI journey, publish it, observe it, and expand from there.

## Reference

When you are ready to integrate:

* Use the [Orchestrator API reference](/tagit/reference/reference/api/orchestrator.md) to call an agentic use case.
* Use the [Collector API reference](/tagit/reference/reference/api/collector.md) to send events and conversation signals.
* Use the [AI client reference](/tagit/reference/reference/ai-client.md) to embed AI Canvas or build a compatible client.


---

# Agent Instructions: 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:

```
GET https://tagit.gitbook.io/tagit/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.