> 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/ai-assistant/ai-note-taker.md). # AI Note-Taker The AI Note-Taker turns every client meeting into structured intelligence that feeds back into ScaleAI. It captures the conversation, transcribes it, extracts key discussion points, decisions, and action items, and stores everything as a note against the client's profile. No more forgotten follow-ups or vague recollections — every meeting automatically becomes context that makes the next AI conversation, review, and recommendation sharper. **How it works** * **Captures meetings through multiple channels** — Granola for full meeting audio, Google Meet recordings, or voice input directly in the client chat * **Transcribes and extracts structured content** — key discussion points, decisions made, action items with ownership, financial details discussed, and follow-up triggers * **Suggests post-meeting workflows** — after processing, it recommends next steps like generating an AI Review, booking a follow-up via the [Scheduling Agent](/scaleconnect-docs/scaleai/ai-assistant/calendar-agent.md), or flagging action items * **Stores everything into the client's knowledge base** — the processed transcript becomes a [Client Note](/scaleconnect-docs/scaleai/ai-assistant/client-notes.md) that the AI Assistant, AI Reviews, and Broker Brain all draw from going forward *** ## How Meetings Are Captured The Note-Taker supports three capture channels. Each one produces a transcript that gets processed the same way. ### Granola Granola records the full meeting audio, transcribes it, and produces a structured summary with key points and action items. ScaleConnect imports the Granola output and stores the summary as a meeting transcript note against the matched client. Connect Granola from **Settings → Integrations → Granola**. Once connected, recent Granola meetings appear in the Notes tab for import — select the meeting, match it to the client, and the transcript is stored automatically. ### Google Meet Meetings booked through the [Scheduling Agent](/scaleconnect-docs/scaleai/ai-assistant/calendar-agent.md) include a Google Meet link. When the meeting is recorded via Google Meet, the recording is processed into a transcript and stored against the client. ### Voice input in client chat For quick conversations or phone calls, use the voice input button in the client chat. The audio is transcribed in real time using speech-to-text and can be saved as a note directly from the conversation. *** ## What the AI Extracts A raw transcript is useful for reference, but the real value is in what the AI pulls out of it. After processing, each transcript note includes: * **Key discussion points** — the main topics covered, summarised concisely * **Decisions made** — anything agreed upon during the meeting * **Action items with ownership** — tagged as **\[BROKER]**, **\[CLIENT]**, or **\[SYSTEM]** so it's clear who needs to do what * **Financial details discussed** — specific numbers, rates, property values, or loan structures that were referenced * **Follow-up triggers** — signals that should prompt a next action (e.g. "client wants to explore refinancing" → review or meeting) This extraction means the AI doesn't just know that a meeting happened — it knows what was discussed, what was decided, and what needs to happen next. *** ## Post-Meeting Suggestions After the Note-Taker processes a transcript, it suggests relevant next steps based on what was discussed:
SuggestionWhen it appears
Generate an AI ReviewThe meeting covered portfolio performance, strategy changes, or financial milestones worth formalising in a client-facing review
Book a follow-upAction items require a follow-up conversation, or the client requested another meeting
Flag action itemsSpecific tasks were assigned during the meeting that need tracking
These are suggestions, not automatic actions. You choose which ones to act on. Clicking a suggestion opens the relevant flow — the [AI Reviews](/scaleconnect-docs/scaleai/ai-assistant/ai-reviews.md) generator, the [Scheduling Agent](/scaleconnect-docs/scaleai/ai-assistant/calendar-agent.md) booking flow, or the action item tracker. *** ## How Transcripts Feed Back Into ScaleAI Processed transcripts are stored as [Client Notes](/scaleconnect-docs/scaleai/ai-assistant/client-notes.md) with the `meeting-transcript` type. Once stored, they become part of the client's knowledge base — the same pool of context that the AI Assistant, AI Reviews, and Broker Brain all draw from. This creates a compounding effect: 1. **First meeting** — the AI knows the client's portfolio data but nothing about your relationship or their concerns 2. **After the first transcript** — the AI knows what you discussed, what the client cares about, and what was agreed 3. **After several meetings** — the AI has a history of every conversation, every decision, and every follow-up, making its responses and reviews deeply personalised The more meetings you capture, the more the AI understands the client beyond their numbers — their priorities, their communication style, their concerns, and the trajectory of your advisory relationship. *** ## Practical Tips * **Record every meeting** — even a quick 15-minute call produces context the AI can use. The habit of capturing every interaction pays compound dividends. * **Use voice input for phone calls** — when a client calls you outside of a scheduled meeting, use the voice input in the client chat to capture the key points in real time. * **Add manual notes for off-platform conversations** — if you bump into a client at an event or have an informal chat, add a quick manual note in the Notes tab. The AI can't capture what it doesn't know about. * **Review the transcript before your next meeting** — open the client's notes and scan the last transcript. The AI will use it automatically, but you'll also walk in better prepared. *** {% hint style="info" %} The AI Note-Taker turns every client meeting into permanent, structured intelligence. No more forgotten action items or vague recollections — every conversation builds the client's knowledge base and makes the next interaction sharper. {% 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/ai-assistant/ai-note-taker.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.