> For the complete documentation index, see [llms.txt](https://docs.zenml.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zenml.io/kitaru/agent-harness-platform.md).

# Agent Harness Platform

- [Overview](https://docs.zenml.io/kitaru/agent-harness-platform/agent-harness-platform.md): A runnable reference architecture for building an internal agent harness platform with Kitaru and PydanticAI
- [Durable Agent](https://docs.zenml.io/kitaru/agent-harness-platform/01-durable-agent.md): PydanticAI runs the agent loop. Kitaru keeps a durable record of the work that finished before a crash.
- [Sandbox](https://docs.zenml.io/kitaru/agent-harness-platform/02-sandbox.md): Run the agent's shell commands inside a Docker sandbox, so a mistaken command hits a throwaway container instead of your host.
- [Skills](https://docs.zenml.io/kitaru/agent-harness-platform/03-skills.md): Move the agent's procedure out of the system prompt and into a markdown file an operator can edit without changing code.
- [Credential Proxy](https://docs.zenml.io/kitaru/agent-harness-platform/04-credential-proxy.md): A separate proxy container holds the service credentials and injects auth headers; the worker never holds them
- [Typed Services](https://docs.zenml.io/kitaru/agent-harness-platform/05-typed-services.md): Add exec\_service for structured host-side calls (look up a record, create a ticket, publish a summary) when a shell command is the wrong shape
- [Human in the Loop](https://docs.zenml.io/kitaru/agent-harness-platform/06-hitl.md): ask\_question, a freeform HITL tool that pauses the flow until an operator answers from any surface
- [Production Notes](https://docs.zenml.io/kitaru/agent-harness-platform/production-notes.md): Which pieces of the Agent Harness Platform tour are teaching stand-ins, where each one plugs into production, and what to harden before you rely on the pattern


---

# 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.zenml.io/kitaru/agent-harness-platform.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.