> For the complete documentation index, see [llms.txt](https://docs.scaleconnect.com.au/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.scaleconnect.com.au/scaleconnect-docs/support/guides/getting-the-most-from-ai.md).

# Getting the Most from AI

ScaleConnect's AI tools are designed to work together — but like any tool, they deliver the most value when you use them deliberately. This guide covers the practical habits and strategies that will help you get the maximum return from ScaleAI across your practice.

{% hint style="success" %}
This is a practical guide. For the full feature reference — what each AI component does and how it fits together — see [AI-Powered Operations](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/help-centre/guides/ai-powered-operations.md).
{% endhint %}

***

## Feed the Knowledge Base

The AI is only as good as the context it has. Make a habit of:

* Adding notes after client meetings
* Uploading transcripts when available
* Sending AI reviews regularly (each one becomes context for the next)
* Saving useful AI responses to the client's notes

The knowledge base is the foundation that every AI feature draws from. A sparse knowledge base produces generic outputs. A rich one produces responses that feel like they were written by someone who knows the client personally.

***

## Trust but Verify

AI-generated content — reviews, suggestions, responses — is a starting point, not a final product. Always review before sending to clients. The AI handles the data analysis; you handle the judgement.

This is especially important for:

* **AI Reviews** — scan the recommendations before sending. The AI analyses the data accurately, but your professional context adds the nuance.
* **Message suggestions** — the AI drafts a relevant reply, but tone and relationship context are yours to adjust.
* **Broker Brain queries** — cross-reference book-level insights with your own knowledge of individual client situations.

***

## Use Broker Brain for Book-Level Insights

Don't underestimate [Broker Brain's](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/help-centre/guides/broker-brain.md) ability to query across your entire client base. Questions like "Who has fixed rates expiring in the next 90 days?" or "Which clients have equity above $200K?" take seconds and can shape your week's priorities.

Broker Brain is most powerful when you use it to:

* **Plan your week** — ask which clients need attention based on upcoming events or milestones
* **Prepare for team meetings** — pull book-level stats and pipeline summaries
* **Spot patterns** — identify clusters of clients in similar situations who could benefit from the same strategy

***

## Combine AI Features

The AI components are designed to work together:

1. Use **Broker Brain** to identify which clients need attention
2. Use **Client Assistant** to prepare for those meetings
3. Generate an **AI Review** to send before or after the meeting
4. Let the **Calendar Agent** schedule the follow-up
5. The **client-facing AI** keeps the client engaged between meetings

This chain — identify, prepare, review, schedule, engage — is the operational backbone of a scalable advisory practice.

***

## Next Steps

* [AI-Powered Operations](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/help-centre/guides/ai-powered-operations.md) — the full feature reference for ScaleAI
* [AI Reviews](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/help-centre/guides/ai-reviews.md) — generating and sending personalised portfolio reviews
* [Broker Brain](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/help-centre/guides/broker-brain.md) — loan book intelligence across all clients
* [Calendar Agent](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/help-centre/guides/calendar-agent.md) — trigger-based scheduling and outreach
* [Knowledge Base](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/help-centre/guides/client-notes.md) — building the AI's context for each client


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.scaleconnect.com.au/scaleconnect-docs/support/guides/getting-the-most-from-ai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.