> 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/client-notes.md). # Client Notes Client Notes are the living record for each client — housing AI-generated summaries, meeting transcripts, review outputs, and your own annotations in one place. They sit in the **Notes** tab on every client's detail page and serve as the long-term memory that ScaleAI draws on when answering questions, generating reviews, and preparing meeting briefs. The richer a client's notes, the more personalised and accurate every AI output becomes. *** ## **How it Works** 1. **Accumulates knowledge from every interaction** — manual notes you write, AI summaries saved from chat, review outputs, and meeting transcripts all feed the same knowledge base 2. **Feeds directly into the AI Assistant, AI Reviews, and Broker Brain** — every enabled note becomes context the AI uses to personalise responses, tailor review analysis, and inform meeting prep 3. **Gives you control over what the AI sees** — the enable/disable toggle on each note lets you include or exclude specific notes from AI context without deleting them 4. **Compounds over time** — each note makes the next AI conversation, review, and recommendation more relevant than the last ![Client Notes tab showing the notes list for a client](https://1103942972-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIVoALSAigc466POg2rP1%2Fuploads%2Fgit-blob-5d044fc135c832381c13c64c0b9acbeeff4b1e16%2FClient_Notes.png?alt=media) *** ## What's Stored Four types of notes accumulate in a client's knowledge base:
TypeSourceHow it gets there
Manual notesYouCreated directly in the Notes tab — meeting observations, strategy rationale, personal context, anything you want the AI to know
AI summariesAI AssistantSaved from a chat response using the Add to Notes button
Review outputsAI ReviewsAutomatically stored when a review is generated — monthly, quarterly, annual, or one-off
Meeting transcriptsAI Note-TakerKey actions items & decisions are captured from each meeting, then processed into structured notes with key points and action items.
Every note includes a title, body content, optional attachments, and a timestamp. AI-generated notes are visually distinguished with a purple glow icon so you can tell at a glance what was written by you versus the system. *** ## Adding Notes ### Manual notes Click **New Note** in the Notes tab. Give it a title and write your content. Use manual notes for context the AI can't capture on its own — personal circumstances, off-platform conversations, strategy rationale, or things a client mentioned in passing. ![New note creation form](https://1103942972-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIVoALSAigc466POg2rP1%2Fuploads%2Fgit-blob-e62d1bde52193e963efacf87efa576d7059a5a0b%2FClient_Notes_NewNote.png?alt=media) ### Saving from AI chat When the [AI Assistant](/scaleconnect-docs/scaleai/ai-assistant.md) gives you a response worth keeping, click the ***Add to Notes*** button on that response. It's saved as an AI summary note against the client's profile — no copy-pasting required. {% @arcade/embed url="" flowId="abM05dvqlLMfh3GCtuRE" %} ### Automatic from reviews Every [AI Review](/scaleconnect-docs/scaleai/ai-assistant/ai-reviews.md) that's generated — whether sent, skipped, or pending — is stored as a note. This means the AI has a record of what it's already told the client, what was recommended, and what's changed since. {% @arcade/embed url="" flowId="z2wU3pkuO9k6y94jqxTf" %} ### Meeting transcripts The [AI Note-Taker](/scaleconnect-docs/scaleai/ai-assistant/ai-note-taker.md) captures meeting audio, transcribes it, and produces a structured summary with key discussion points, decisions, action items, and follow-up triggers. These are stored as transcript notes automatically. *** ## The Enable/Disable Toggle Every note has a toggle that controls whether it feeds into the AI's context. Enabled notes are included when the AI generates responses, reviews, or recommendations. Disabled notes are kept on file but excluded from AI context. This is non-destructive — disabling a note doesn't delete it. You can re-enable it at any time. **When to disable a note:** * **Outdated information** — a client's situation has changed and old context would mislead the AI * **Superseded by newer notes** — an older review has been replaced by a more recent one * **Sensitive material** — something you want on record but don't want influencing AI outputs * **Noise reduction** — early notes from onboarding that are no longer relevant By default, all notes are enabled. Be selective — the AI performs best when the knowledge base is current and relevant, not bloated with stale context. {% @arcade/embed url="" flowId="crhMUaTwAZDJNqcNbXRZ" %} *** ## Viewing and Managing Notes Notes are displayed in reverse chronological order in the Notes tab. Each note shows: * Title and creation date * Note type icon (manual, AI summary, review, transcript) * Enable/disable toggle * Preview of the content Click any note to expand it inline and read the full content. ### Editing Notes Click into a note to edit the title or body. Useful for adding context after a meeting, correcting details, or appending follow-up information. ### Deleting Notes Delete removes a note permanently — it can't be recovered. If you're unsure, disable the note instead. Deletion is appropriate for duplicates, test notes, or content added in error. {% @arcade/embed url="" flowId="HnYdLmyOAWrPPkilsRaP" %} *** ## How Client Notes Impact your AI Assistant Your client notes are the personalisation layer. Everything else gives the AI understanding of property finance, tax, and strategy mechanics — notes give it understanding of *this specific client*. What they discussed last meeting, what the broker recommended, what's changed since the last review, what their priorities are. *** ## Best Practices
PracticeWhy it matters
Add a note after every client interactionOff-platform calls, emails, and hallway conversations don't get captured automatically. A quick manual note closes the gap.
Use descriptive titles"March meeting" is less useful than "March meeting — discussed refinancing IP2, client hesitant on variable rate." The AI uses titles for context.
Disable rather than deleteYou might want that context again later. Disabling keeps it on file without cluttering AI responses.
Review the knowledge base before triggering a one-off reviewScan enabled notes and disable anything stale. The AI Review quality is directly tied to the quality of the context it draws from.
Save useful AI responses as notesWhen the AI gives you a good analysis, save it. It becomes context for the next conversation — the AI builds on its own previous answers.
*** {% hint style="info" %} Client Notes are the foundation of ScaleAI's personalisation. Every note you add, every transcript captured, and every review sent compounds into a richer picture of the client — making every future AI interaction more relevant and more accurate. {% 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/client-notes.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.