> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons.md).

# Add-ons

- [Overview](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/add-ons.md): Add-on packages that extend Umbraco.AI with additional capabilities.
- [Prompt Management](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt.md): Prompt Management add-on for creating and executing reusable prompt templates.
- [Concepts](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/concepts.md): Core concepts for Prompt Management.
- [Getting Started](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/getting-started.md): Get started with Prompt Management.
- [Template Syntax](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/template-syntax.md): Variable interpolation syntax for prompt templates.
- [Property Actions](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/property-actions.md): Use prompts directly from property editors in the backoffice.
- [Scoping](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/scoping.md): Control where a prompt is allowed to run using allow and deny rules.
- [API](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/api.md): Management API endpoints for Prompt add-on.
- [List](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/api/list.md): List all prompts.
- [Get](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/api/get.md): Get a prompt by ID or alias.
- [Create](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/api/create.md): Create a new prompt.
- [Update](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/api/update.md): Update an existing prompt.
- [Delete](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/api/delete.md): Delete a prompt.
- [Execute](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/api/execute.md): Execute a prompt template.
- [Check Alias Exists](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/api/alias-exists.md): Check whether a prompt alias is in use.
- [Reference](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/ai-prompt-service.md): Service for managing and executing prompts.
- [AIPrompt](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/prompt/ai-prompt-service/ai-prompt.md): Model representing a prompt template.
- [Agent Runtime](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent.md): Agent Runtime add-on for configuring and running AI agents with streaming responses.
- [Concepts](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/concepts.md): Core concepts for Agent Runtime.
- [Getting Started](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/getting-started.md): Get started with Agent Runtime.
- [Instructions](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/instructions.md): Configuring agent instructions for optimal behavior.
- [Workflows](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/workflows.md): Create custom workflows for orchestrated agents.
- [Scopes](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/scopes.md): Categorise agents using surfaces, and control where they are available using scopes.
- [Permissions](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/permissions.md): Configure tool permissions for agents using scopes, explicit tool lists, and user group overrides.
- [Streaming](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/streaming.md): Handling SSE streaming and AG-UI events.
- [Frontend Client](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/frontend-client.md): Build custom agent-driven UIs using the UaiAgentClient base client.
- [Frontend Tools](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/frontend-tools.md): Defining and handling frontend tools for agents.
- [API](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api.md): Management API endpoints for the Agent add-on.
- [List](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api/list.md): List agents, surfaces, workflows, and check alias availability.
- [Get](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api/get.md): Get an agent by ID or alias.
- [Create](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api/create.md): Create a new agent.
- [Update](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api/update.md): Update an existing agent.
- [Delete](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api/delete.md): Delete an agent.
- [Run](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api/run.md): Run an agent and get the complete response as JSON.
- [Stream](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api/stream.md): Stream agent response updates as Server-Sent Events.
- [Stream (AG-UI)](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/api/stream-agui.md): Stream AG-UI protocol events as Server-Sent Events.
- [Reference](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/ai-agent-service.md): Service for managing and running agents.
- [AIAgent](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/ai-agent-service/ai-agent.md): Model representing an AI agent.
- [UaiAgentRepository](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent/ai-agent-service/uai-agent-repository.md): Read-only repository for fetching active agents in frontend components.
- [Semantic Search](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/search.md): Semantic vector search add-on for finding content by meaning.
- [Concepts](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/search/concepts.md): How semantic vector search indexes and retrieves content.
- [Custom Vector Store](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/search/custom-vector-store.md): Replace the built-in vector store with a custom implementation.
- [Agent Copilot](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent-copilot.md): Copilot chat UI add-on for AI agents with sidebar, tool execution, and Human In The Loop (HITL) support.
- [Copilot Usage](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent-copilot/copilot.md): The AI Copilot provides an interactive assistant sidebar in the Umbraco backoffice.
- [Frontend Tools](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/agent-copilot/frontend-tools.md): Defining frontend tools that agents can call from the Copilot chat UI.
- [Deploy Support](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/deploy.md): Deploy Umbraco AI entities like connections, profiles, and prompts between environments.
- [Installation](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/deploy/installation.md): Install the Umbraco AI Deploy add-on packages for environment-based deployment.
- [Configuration](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/deploy/configuration.md): Configure sensitive data filtering and deployment settings for Umbraco AI Deploy.
- [Deploying Entities](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/deploy/deploying-entities.md): Deploy AI connections, profiles, prompts, and agents between environments using Umbraco Deploy.
- [Best Practices](https://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons/deploy/best-practices.md): Security, workflow, and configuration best practices for deploying AI entities across environments.


---

# 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://docs.umbraco.com/ai-in-umbraco/17.latest/add-ons.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.