# AI & Agents

- [Build with AI](https://docs.predicthq.com/ai/build-with-ai.md): Tools and resources for building PredictHQ integrations with AI assistants and coding agents.
- [MCP Server](https://docs.predicthq.com/ai/mcp.md): Query PredictHQ's APIs through any MCP-compatible AI assistant using natural language.
- [Tech Docs MCP Server](https://docs.predicthq.com/ai/tech-docs-mcp-server.md): Search PredictHQ's technical documentation from inside your code editor or AI assistant.
- [Bolt](https://docs.predicthq.com/ai/bolt.md): An AI-native notebook for exploring and building with PredictHQ - available inside the PredictHQ WebApp.
- [Using PredictHQ with AI Assistants](https://docs.predicthq.com/ai/using-predicthq-with-ai-assistants.md)
- [PredictHQ MCP in Agentic Workflows](https://docs.predicthq.com/ai/predicthq-mcp-in-agentic-workflows.md): Using the PredictHQ MCP server in autonomous agentic workflows.


---

# 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://docs.predicthq.com/ai.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.