> 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/scaleai-for-clients.md). # ScaleAI for your Clients ScaleAI is available to your clients directly in the ScaleApp mobile app. It gives them 24/7 access to an AI assistant that understands their portfolio, their strategy, and their financial position — answering questions in plain language using their real data. The client-facing AI runs on the same ScaleAI engine as [Broker Brain](/scaleconnect-docs/scaleai/broker-brain.md) and the [AI Assistant](/scaleconnect-docs/scaleai/ai-assistant.md), but it's tuned for a different audience. It speaks in second person ("your portfolio", "your LVR"), uses a warm and professional tone, and avoids broker jargon. Every answer is grounded in the client's actual numbers. **How it works** 1. **Draws on the client's full portfolio** — property values, loan balances, equity positions, cashflow projections, goal tracking, and strategy outputs from the simulator 2. **Enriched by the knowledge base you build** — notes you write, reviews you send, and meeting transcripts you capture via [Client Notes](/scaleconnect-docs/scaleai/ai-assistant/client-notes.md) all become context the client's AI can reference 3. **Explains, not just retrieves** — the AI contextualises educational content with the client's own data, so instead of a textbook definition of LVR, it says "Your LVR is currently 68% on your Surry Hills property, meaning you have around $192,000 in equity" 4. **Routes to you when it should** — when the AI can't answer or a human decision is needed, it offers an "Ask my Broker" option that sends the question directly to you in ScaleConnect *** ## What Clients Can Ask The AI assistant surfaces **quick prompt categories** that guide clients toward useful questions. These appear as tappable cards when the client opens the chat:
Quick PromptWhat It Covers
Finance & LoansLoan balances, interest rates, repayment schedules, refinancing options
Legal & ConveyancingSettlement timelines, contract terms, property transfer basics
Market LearningsSuburb performance, growth trends, rental yield benchmarks
Base Case StrategyWhat the current strategy projects, how scenarios play out
Borrowing PowerHow much additional capacity the client has, what affects it
Beyond quick prompts, clients can ask free-form questions. Common topics include: ### Portfolio and Properties * "What's my total portfolio worth right now?" * "How much equity do I have across all my properties?" * "What's the current LVR on my investment property?" * "How has my property in Brisbane changed in value since I bought it?" ### Cashflows and Goals * "Am I on track for my savings goal?" * "What does my personal cashflow look like this financial year?" * "When will I have enough for a deposit on my next property?" * "How much rental income am I earning each month?" ### Strategy Questions * "What does my current strategy mean for the next five years?" * "What happens if interest rates go up by 0.5%?" * "Why is my cashflow negative this year?" * "How does negative gearing affect my tax position?" ### General Education * "How does stamp duty work in Victoria?" * "What's the difference between P\&I and interest-only?" * "Can you explain capital gains tax on investment properties?" * "What does LVR mean and why does it matter?" The AI always contextualises educational answers with the client's own data — so they get practical understanding, not textbook definitions. *** ## How It Differs from Broker Brain ScaleAI for Clients and [Broker Brain](/scaleconnect-docs/scaleai/broker-brain.md) are both powered by the same AI engine, but they serve different purposes and different audiences.
ScaleAI for ClientsBroker Brain
AudienceYour clientYou (the broker)
Data scopeOne client's portfolio onlyYour entire loan book
ToneConversational, reassuring, jargon-freeAnalytical, direct, broker-focused
PerspectiveSecond person — "your portfolio", "your LVR"Third person — "Sarah's LVR", "your client"
AccessScaleApp mobile appScaleConnect desktop platform
CapabilitiesPortfolio queries, education, goal trackingBook-wide analytics, pipeline, cross-client insights
AnalyticsIndividual performance, personal projectionsLoan composition, revenue analysis, refinance signals
Think of it this way: Broker Brain gives you intelligence across your entire practice. ScaleAI for Clients gives each individual client intelligence about their own position. {% hint style="info" %} The client AI never has access to other clients' data, your pipeline, your commission figures, or any book-wide analytics. It only sees what belongs to that specific client. {% endhint %} *** ## Broker Controls As the broker, you have meaningful control over what the client's AI knows and how it behaves. You don't need to configure anything in ScaleApp directly — your actions in ScaleConnect shape the client AI experience. ### Knowledge Base Influence Everything you add to a client's [knowledge base](/scaleconnect-docs/scaleai/ai-assistant/client-notes.md) influences what their AI assistant knows. If you add a note after a meeting summarising what was discussed, the client's AI can reference that context when answering follow-up questions. * **Manual notes** you write become AI context for the client * **AI reviews** you send are stored as notes and inform future AI answers * **Meeting transcripts** you upload are processed and indexed ### Enable/Disable Toggle The [note toggle](/scaleconnect-docs/scaleai/ai-assistant/client-notes.md) on each note in the knowledge base controls whether that note feeds into the client-facing AI. If you've recorded something that's relevant for your own reference but shouldn't influence client-side responses, disable it. This gives you fine-grained control: | Toggle State | Effect on Client AI | | ------------ | ------------------------------------------------------------------------------- | | **Enabled** | Note is included in the client AI's context — it may reference this information | | **Disabled** | Note is excluded — the client AI won't see or reference it | ### Sent Reviews When you send an [AI Review](/scaleconnect-docs/scaleai/ai-assistant/ai-reviews.md) to a client, the review content becomes part of their knowledge base. The client's AI assistant can then reference past reviews when answering questions, creating continuity between your formal reviews and the client's day-to-day interactions with the AI. ### Scheduling Agent Settings The [Scheduling Agent](/scaleconnect-docs/scaleai/ai-assistant/calendar-agent.md) settings you configure in ScaleConnect affect how the client AI handles meeting requests. If a client says "I'd like to book a meeting with my broker," the AI uses your scheduling preferences, availability, and trigger rules to respond appropriately. *** ## Privacy and Data Boundaries Data isolation is enforced at every level. The client-facing AI operates within strict boundaries that protect both your clients and your practice. ### Client Data Isolation Each client's AI assistant only accesses data belonging to that client. It cannot see, query, or reference: * Another client's properties, loans, or portfolio * Another client's notes, reviews, or transcripts * Aggregate data about your loan book * Other brokers' data within the same team This isolation is enforced at the API level — it's not a prompt instruction the AI could accidentally bypass. The data endpoints the client AI calls are scoped to the authenticated client's user ID. ### Broker-Only Context Certain information in ScaleConnect is broker-only and never reaches the client-facing AI: * Your internal notes that you've disabled via the knowledge base toggle * Pipeline and deal flow data * Commission and revenue figures * Loan book analytics and cross-client insights * Team management information ### What the Client Can See The client AI can access and discuss: * Their property details, values, and addresses * Their loan structures, balances, and rates * Their cashflow projections (personal, property, portfolio) * Their goal progress and savings tracking * Their strategy outputs from the simulator * Notes and reviews that are **enabled** in the knowledge base * General educational content about property investment {% hint style="info" %} If you're ever unsure whether a specific piece of information is visible to the client AI, check the note's toggle in the knowledge base. If it's enabled, the AI can use it. If it's disabled, it's excluded. {% endhint %} *** ## How It Benefits Your Practice ScaleAI for Clients isn't just a feature for your clients — it's a tool that works for your brokerage. ### Reduced Inbound Queries When clients can get answers to routine questions — "What's my LVR?", "When does my fixed rate expire?", "How much equity do I have?" — they don't need to call or email you. The AI handles the day-to-day, freeing you to focus on high-value advisory work. ### Increased Engagement Clients who interact with the AI regularly stay more connected to their portfolio. They understand their position better, which means more productive conversations when you do meet. See [Client Engagement](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/scaleai/client-engagement.md) for more on this. ### Warmer Referrals When a client shows a friend or colleague their AI-powered portfolio dashboard, it's a natural conversation starter. "My broker gives me this" is a powerful referral trigger. ### Better Meeting Prep Because the AI tracks what clients ask about, you can see the topics on their mind before a meeting. If a client has been asking the AI about refinancing options, you know that's likely to come up. *** {% hint style="info" %} Every client gets their own AI assistant in ScaleApp — available 24/7, grounded in their real numbers, and shaped by the knowledge base you build through notes, reviews, and meeting transcripts. {% endhint %} --- # 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/scaleai-for-clients.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.