# Consult

Rainbird Consult uses knowledge elicitation techniques to help construct a detailed prompt that can be used to generate a graph from knowledge and documentation.

Through a guided interview, Consult will elicit relevant expertise for your chosen use case. Once sufficient information has been obtained, a prompt will be produced that can be copied and used in the Rainbird Studio.<br>

**Why use Consult?**

Existing documentation can contain explicit knowledge about rules and policies, but tacit knowledge held by Subject-Matter Experts (SMEs) is often crucial in decision-making.

Creating a prompt with Consult helps with the capture of this information that can improve the graph that is generated.

<figure><img src="/files/h9dbgpkdTaARLOvWCmP3" alt=""><figcaption></figcaption></figure>

{% hint style="info" icon="rectangle-beta" %}
Rainbird Consult is currently in beta. It may contain bugs, is subject to change and is not covered by our platform SLAs. Your feedback can help shape development.
{% endhint %}

## Getting Started

Visit <https://consult.rainbird.ai> to begin. Simply describe your decision-making process, and Consult will guide you through capturing your expertise. Upon completion, receive a prompt that can be used to automatically [generate a graph](/rainbird/knowledge-modelling/modelling-features/building-with-co-author.md#starting-a-new-graph).

## Supported Documents

Enhance your consultation by uploading relevant business documentation:

* Supported formats: PDF, DOCX, TXT
* Maximum size: 100MB
* Text-only content (images not currently supported)

## Documentation Best Practice

To optimise the usage of documentation it is important to upload suitable documents that add context to the consultation that enable follow-up questions to be asked that elicits additional expertise.

&#x20;The following type of documents should work well:

1. Process-focussed documents describing workflows and decision-points ✅
2. Framework documents that outline general principles and approaches ✅
3. Guidelines that include rationales and context for decisions ✅
4. Case studies that illustrate how rules/policies are applied in practice ✅
5. Training materials that explain concepts progressively ✅

Documents that are less likely to perform well include:

1. Documents that are highly visual, with meaning held in graphs, charts or complex tables ❌
2. Academic-style papers with multiple column layouts, complex mathematical calculations or references and citations that break-up the main text flow ❌
3. Scanned documents with poor OCR quality ❌

## Important Information

### Data Security

Consult uses third-party AI services (Anthropic hosted in AWS Bedrock). However this data will be encrypted in transit and at rest by AWS Bedrock and will not be used for training purposes. Data will be processed within the EU and continues to be ISO27001 compliant.&#x20;

### System Parameters

* Token limits apply to consultations and document processing that may impact the use experience or report generation
* Warning provided at 80% token usage
* Sessions are not currently saved - avoid leaving consultations inactive for long periods of time
* Service may be interrupted during peak periods


---

# 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/knowledge-modelling/modelling-features/building-with-co-author/consult.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.