> 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/scaleai/broker-brain.md). # Broker Brain Broker Brain is your loan book intelligence engine. It operates across your entire client base — surfacing refinance signals, revenue forecasts, review schedules, and portfolio trends without you having to ask. While the [AI Assistant](/scaleconnect-docs/scaleai/ai-assistant.md) works with one client at a time, Broker Brain sees your whole book in a single conversation. Open it from the **Broker Brain icon** in the top navigation bar. {% @arcade/embed url="" flowId="LTZo3YNEpWfnEEsiMgEX" %} *** ## **How it works** 1. **Has your full client book loaded in every conversation** — every client, property, loan, strategy, and cashflow projection across your brokerage, plus your dashboard metrics, deal flow, pipeline, and loan composition 2. **Powered by the same financial model as the AI Assistant** — the same dependency graph and knowledge system, but scoped to your entire book rather than a single client, so it traces patterns and trends across portfolios ### **What it does for you** * **Understand your loan book at a level you can't get manually** — portfolio performance as a whole, concentration risk, segment growth, period-over-period shifts, and how macro market movements ripple through different parts of your book * **Surface trends and sensitivities across clients** — rate exposure, cashflow pressure, equity milestones, fixed rate expiry clusters, and which clients are most affected when conditions change * **Draw similarities between successful strategies** — identify what's working across your client base, which strategy patterns produce the best outcomes for similar profiles, and where proven approaches could apply to other clients * **Spot opportunities and risks before they land on your desk** — refinance candidates, overdue reviews, clients approaching key thresholds, and revenue shifts — ranked by readiness and potential value *** ## Getting Started Click the **Broker Brain icon** in the top navigation bar. The welcome screen shows three suggested actions you can click to get started immediately:
Suggested QueryWhat it returns
Brokerage SnapshotMonthly performance summary with key metrics and changes
Revenue ForecastProjected commission income across your book
Refinance SignalsRanked list of clients showing refinance readiness
Type a question, click a suggestion, or use the microphone button for voice input. After each response, Broker Brain suggests contextual follow-up questions — if you just asked about refinance candidates, the follow-ups might include "Show me their current rates vs market" or "Which of these have fixed rates expiring soonest?" *** ## Using Broker Brain Conversations are saved in the left sidebar, grouped by date.
ActionHow
Start a new conversationClick the + button in the sidebar
Resume an old conversationClick any past conversation in the sidebar
Rename a conversationHover over a conversation → click the rename icon
Delete a conversationHover over a conversation → click the delete icon
Voice inputClick the microphone button in the message bar
Broker Brain formats responses with tables, bullet points, highlighted metrics, and follow-up suggestions. You're not limited to the suggested actions — ask any natural language question about your book and it queries your data in real time. *** ## Broker Brain vs AI Assistant Broker Brain and the [AI Assistant](/scaleconnect-docs/scaleai/ai-assistant.md) are powered by the same ScaleAI engine, but they serve different scopes. | | Broker Brain | AI Assistant | | --------------- | ------------------------------------------------------------------ | ------------------------------------------------------------------ | | **Scope** | Your entire client book — all clients, all properties, all loans | A single client's portfolio and strategies | | **Access** | Broker Brain icon in the top navigation bar | AI Assistant tab inside a client's profile | | **Best for** | Book-level trends, segmentation, revenue analysis, pipeline review | Deep dives into one client's cashflows, goals, strategy comparison | | **Perspective** | Third person — "Your client Sarah has an LVR of 62%" | Client-focused — "This client's equity position is…" | Use Broker Brain when you want to scan across your book. Use the AI Assistant when you're working with a specific client and need detailed analysis of their situation. *** ## Capabilities These aren't pre-built reports — you ask natural language questions and Broker Brain queries your data in real time.
Brokerage snapshot A monthly performance summary covering new clients added, deals in pipeline, loans settled, total loan book value, and key changes since last month. Try: *"Give me a brokerage snapshot"* · *"Summarise this month's brokerage performance"*
Revenue forecast Projected trail commission and upfront commission across your book, broken down by lender, client segment, or time period. Useful for planning and capacity management. Try: *"What's my projected trail commission for the next quarter?"* · *"Break down my commission by lender"*
Refinance signals Clients who may be ready to refinance based on objective criteria — LVR below 80%, fixed rates expiring in the next 3–6 months, rates above market, or significant equity growth. Ranked by readiness and potential value. Try: *"Show me clients with LVR under 80% who could refinance"* · *"List all clients with fixed rates expiring in the next 90 days"*
Review schedules Which clients are due for a review this month, which reviews are overdue, and which are coming up in the next cycle. Cross-references with your [AI Review](/scaleconnect-docs/scaleai/ai-assistant/ai-reviews.md) settings. Try: *"Which clients are due for a review this month?"* · *"Show me clients who haven't had a review in over 6 months"*
Client segmentation Break your book down by client type (First Home Buyer, Investor, Existing Home Owner, Downsizer), geography, lender, loan type, or any combination. Useful for targeted campaigns or understanding book composition. Try: *"Break down my loan composition by lender"* · *"How many investors do I have in NSW?"*
Equity milestones Clients approaching key equity thresholds — 80% LVR (no more LMI), 70% LVR (better rates available), or absolute equity amounts that unlock new borrowing capacity for their next purchase. Try: *"Who has the highest available equity in my book?"* · *"List clients approaching 80% LVR"*
Rate sensitivity Which clients are most exposed to rate changes — those on variable rates with tight serviceability, clients with large balances on high rates, or portfolios where a small rate movement creates a meaningful cashflow impact. Try: *"Which clients are most exposed to a rate rise?"* · *"Compare my book's average LVR this quarter vs last quarter"*
{% hint style="info" %} You're not limited to these categories. Ask Broker Brain anything about your book — "Which clients haven't logged into ScaleApp in 60 days?", "What's my average LVR across investors?", or "List clients with more than $200k in available equity." {% endhint %} *** ## Configuration Broker Brain works out of the box with no setup required — it automatically has access to your full client book. The following options let you tailor how it operates.
SettingWhereWhat it controls
Voice inputMicrophone button in the message barDictate questions instead of typing. Responses are also read aloud when voice mode is active.
Conversation historyLeft sidebarAll conversations persist until you delete them. Group by date, rename for easy reference, or delete when no longer needed.
Data scopeAutomaticBroker Brain sees every client in your book based on your account permissions. Team members only see clients they have access to.
{% hint style="info" %} Broker Brain is read-only — it analyses and reports but doesn't modify data or trigger actions. To act on what it surfaces, use the relevant feature: [AI Reviews](/scaleconnect-docs/scaleai/ai-assistant/ai-reviews.md) to send a review, [Scheduling Agent](/scaleconnect-docs/scaleai/ai-assistant/calendar-agent.md) to book a meeting, or the [Simulator](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/scaleai/getting-around.md) to adjust a strategy. This separation means you can explore freely without risk of changing anything. {% endhint %} ***
Does Broker Brain have access to all my clients? Yes. Broker Brain has read access to every client in your book — profiles, properties, loans, strategies, cashflows, and goals. It queries this data in real time when you ask a question.
Can I ask about a specific client in Broker Brain? Yes. While Broker Brain is optimised for book-level questions, you can ask about individual clients by name — "What's Sarah Chen's current LVR?" or "Show me James Nguyen's cashflow position." For deep client-specific analysis, the [AI Assistant](/scaleconnect-docs/scaleai/ai-assistant.md) tab is purpose-built for that.
Is conversation history shared with my team? No. Each broker's Broker Brain conversations are private to their account. Team members have their own conversation histories based on their own client book access.
Can Broker Brain take actions like sending reviews or booking meetings? Broker Brain is read-only — it analyses and reports but doesn't modify data or trigger actions directly. To send a review, use the [AI Reviews](/scaleconnect-docs/scaleai/ai-assistant/ai-reviews.md) queue. To book a meeting, use the [Scheduling Agent](/scaleconnect-docs/scaleai/ai-assistant/calendar-agent.md). Broker Brain helps you identify what needs attention; you take the action from the appropriate feature.
--- # 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/scaleai/broker-brain.md?ask=&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.