# Agent

- [Agent](https://docs.neuron-ai.dev/agent/agent.md): Easily implement LLM interactions with built-in memory and tool usage.
- [Messages](https://docs.neuron-ai.dev/agent/messages.md): Unified context unit across AI providers and LLMs.
- [Tools & Toolkits](https://docs.neuron-ai.dev/agent/tools.md): Give Agents the ability to interact with your application context and services.
- [Chat History](https://docs.neuron-ai.dev/agent/chat-history-and-memory.md): Learn how Neuron AI manage multi turn conversations.
- [Streaming](https://docs.neuron-ai.dev/agent/streaming.md): Presenting AI response to your user in real-time.
- [Structured Output](https://docs.neuron-ai.dev/agent/structured-output.md): Enforce the Agent output based on the provided schema.
- [MCP](https://docs.neuron-ai.dev/agent/mcp-connector.md): Connect the tools provided by Model Context Protocol (MCP) servers to your agent.
- [Middleware](https://docs.neuron-ai.dev/agent/middleware.md): Interact with the agent execution flow to customize its behaviour.
- [Async](https://docs.neuron-ai.dev/agent/async.md): Run workflows in an async context.
- [Monitoring & Debugging](https://docs.neuron-ai.dev/agent/observability.md): Monitor your AI Agents, RAGs, and Workflows in real-time.
- [Error Handling](https://docs.neuron-ai.dev/agent/error-handling.md): Managing errors fired by your agent.
- [Evals](https://docs.neuron-ai.dev/agent/evaluation.md): Evaluating the output of your agentic system
- [Testing](https://docs.neuron-ai.dev/agent/testing.md): Fake components to help you test your AI powered system


---

# 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.neuron-ai.dev/agent.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.