> For the complete documentation index, see [llms.txt](https://docs.rainbird.ai/rainbird/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rainbird.ai/rainbird/getting-started/readme.md).

# What is Rainbird?

Rainbird turns your policy and expertise into a knowledge graph. It then uses it to make decisions consistently, with evidence for every outcome.

Use Rainbird to automate decisions that must be right every time. Examples include eligibility checks, underwriting, claims triage, and compliance sign-off. Given the same facts, Rainbird always reaches the same decision. It shows the exact rules and evidence behind it.

Build a knowledge graph of the decision you want to automate, then integrate it into the processes, products or services your customers already use — so every decision they rely on is faster, consistent, and explainable, at whatever volume you need.

### How it works

Rainbird works in three stages: **codify, reason, prove.**

1. **Codify** — Capture your policy and expertise as a knowledge graph.
2. **Reason** — The Reasoning Engine applies that knowledge deterministically to reach a decision.
3. **Prove** — Every decision ships with an evidence tree. It contains the rules, facts, and certainty behind it. People and machines can read it.

### The Rainbird platform

**Codify — create knowledge graphs**

* **Rainbird Agentic Knowledge Engineer** (RAKE `closed beta` ) — Turns written policy into a working knowledge graph. Use it as a starting point for review.
* **Rainbird Studio** — The no-code environment where Knowledge Engineers directly view, author, test, and publish knowledge graphs.
* **Rainbird Foundry** — Encodes a whole policy estate across an enterprise, resolving policy conflicts and gaps during the process.

**Reason — get a decision**

* **Rainbird Reasoning Engine** — Reasons over your knowledge graph to reach a decision. It requests only needed data. It reasons symbolically, without an LLM in the decision loop. It returns the same decision for the same facts every time.

**Prove — see the evidence**

* **Rainbird Evidence Tree** — Every decision includes its evidence tree. It contains the rules, facts, and certainty that produced it, in natural language and JSON.

### Integrate Rainbird into your systems

* **Rainbird Claude Skill** — Use Claude to research, build, and live-test knowledge graphs.
* **APIs & SDKs** — Call a knowledge graph directly from your applications.
* **MCP** `closed beta` — Publish a knowledge graph as an MCP tool. Your AI agents can call it and receive a decision with its evidence tree.
* **Rainbird Agent** — A pre-built application for getting decisions from Rainbird. Configure it from Studio.
* **3rd-party connectors** — Automation platforms including UiPath, Blue Prism, and Microsoft Power Automate.

Wondering what you can do with Rainbird? Want to integrate automated decisions into your business? See our use case examples for inspiration.

{% content-ref url="/pages/lUq2XATe7VjJXvP1eOM9" %}
[Example use cases](/rainbird/getting-started/use-cases.md)
{% endcontent-ref %}


---

# 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.rainbird.ai/rainbird/getting-started/readme.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.