# Overview

Rainbird Labs: Combining the power of knowledge representation and reasoning (KR\&R) with Large Language Models (LLMs) to deliver explainable and trustworthy AI.

{% hint style="info" %}
All tools delivered by Rainbird Labs are experimental. They may contain bugs, are subject to change and are not covered by our platform SLAs.
{% endhint %}

## Current projects

## Rule Tracker

**Status:** Pilot

A system to make it easier for knowledge engineers to build, understand, and troubleshoot graphs. It would provide clearer visibility into how relationships are evaluated, helping people understand graphs faster and with greater confidence. Overall, it would make knowledge graphs easier to create, analyse, and maintain.

## Bulk Document Extraction Pipeline

**Status:** R\&D prototype

Constructing knowledge graphs from large document collections is a time-consuming process that traditionally requires substantial input from domain experts. 

Key challenges include handling contradictory information across sources, detecting topic boundaries when documents span multiple domains, and scaling the process to large collections without proportionally increasing expert effort. This paper presents an automated pipeline that addresses these challenges by using large language models (LLMs) to drive each stage of knowledge graph construction.

## Archived projects

### Consult

**Status:** moved to open beta

Speak with a digital Knowledge Engineer at Rainbird Consult to help flesh out your decision domain. This tool supports knowledge elicitation by extracting tacit expert knowledge through a guided consultation. Documentation can also be uploaded where it is relevant to the consultation. 

A prompt summarising the knowledge and expertise captured is produced, which can be used to automatically generate a knowledge graph.

[Learn more](/rainbird/knowledge-modelling/modelling-features/building-with-co-author/consult.md)

### Generate from documentation

**Status**: moved to open beta

Provide a prompt and documentation to automatically generate a knowledge graph. Works best when using a Rainbird Consult prompt and/or documentation that clearly describes processes and rules.

[Learn more](broken://pages/nsfF5lUk2LeATBRtfmSv)

### Co-author

**Status:** moved to open beta

An agent that can support with modifications to, and explanations of, your knowledge graph to support in refinement.

[Learn more](#co-author-closed-beta)

### Noesis

**Status:** closed

A fine-tuned LLM dedicated to generating Rainbird knowledge graphs from unstructured data, complete with a set of Python APIs to integrate directly into ML pipelines.

[Learn more](https://rainbird.ai/platform/rainbird-noesis/) and join the early access programme.

### /interact

**Status:** moved to open beta

Interact is an API to provide data and query your knowledge graph in natural language to get deterministic results.

Where the reasoning engine asks questions to gather more data (from human or AI agents), the answers can be posted back via interact when using the same session.

[Learn more](/rainbird/developer-docs/api-guide/beta-apis/interact.md)

### /explain

**Status:** moved to open beta

Use the explain API endpoint to obtain natural language explanations for any decision provided to provide further details to the end-user or add to reports.

[Learn more](/rainbird/developer-docs/api-guide/beta-apis/explain.md)


---

# 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.rainbird.ai/rainbird/rainbird-labs/overview.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.