> For the complete documentation index, see [llms.txt](https://help.form.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.form.io/dev/ai.md).

# AI and Form.io

Using AI, LLMs, and machine learning alongside the Form.io Platform.

Form.io serves as the data standardization layer for enterprises in regulated industries. AI may chang who builds applications, but does not change the need for secure and reliable infrastructure that supports such applications.

Form.io offers two products for working with AI — the Agentic Coding Toolset for the build moment, and the Universal Agent Gateway for the runtime moment.

## Agentic Coding Toolset

The Agentic Coding Toolset is a Claude Code plugin, an MCP server, and a skill library that brings Form.io into the AI coding environment. It allows an AI agent to build applications on Form.io. Anything from planning data models, generating forms, configuring access controls, and scaffolding front-ends, it works at the point of development or buildout.

[Learn more about the Agentic Coding Toolset.](#agentic-coding-toolset)

## Universal Agent Gateway (UAG)

The Universal Agent Gateway is a runtime governance layer that lets AI agents interact with deployed Form.io applications through the Model Context Protocol. It enables AI agents in production to read, submit, and update form data inside an enterprise system. UAG operates at runtime or in production.

[Learn more about UAG.](#universal-agent-gateway-uag)


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.form.io/dev/ai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.