> 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/workspace/set-up-your-automations.md).

# AI Automations

ScaleConnect's AI automations monitor your clients' portfolios in the background, generate periodic reviews, and trigger meetings when key thresholds are reached. Instead of manually tracking every client's LVR, equity position, and goal progress, you configure the rules once and let ScaleAI handle the ongoing analysis.

There are two automation types: **AI Client Reviews** and the **Scheduling Bot**. Both can be configured globally (across your book) or overridden per client.

![Settings > Automations page showing AI Client Reviews and Scheduling Bot sections](https://1103942972-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIVoALSAigc466POg2rP1%2Fuploads%2Fgit-blob-da60510de7f27fc8e4cf73a44d628fb07725c19d%2FSettings_AI_Automations.png?alt=media)

{% hint style="info" %}
Automations are set up as the final step of the Add Client flow. You can also configure or edit them from **Settings → Automations** or from each client's detail panel in the Client Manager.
{% endhint %}

***

## Where to configure automations

| Location                           | Scope                                 | How to get there                                                            |
| ---------------------------------- | ------------------------------------- | --------------------------------------------------------------------------- |
| **Add Client flow**                | Per client — set during onboarding    | Add Clients → complete profile, properties, and goals → AI Automations step |
| **Settings → Automations**         | Global defaults for your account      | Sidebar → Settings → Automations                                            |
| **Client Manager → Client detail** | Per client — override global settings | Client Manager → select a client → AI Assistant tab → settings icons        |

Per-client settings always override your global defaults. If you haven't configured anything for a specific client, your global settings apply.

***

## AI Client Reviews

AI Client Reviews are automated portfolio assessments that ScaleAI generates on a schedule. Each review analyses the client's properties, loans, cashflows, goals, and market conditions, then produces a structured report you can approve and send.

### Client type

Reviews are tailored to the client's situation. Select a client type to shape the analysis focus:

<table><thead><tr><th width="212.890625">Client type</th><th>Review emphasis</th></tr></thead><tbody><tr><td><strong>First Home Buyer</strong></td><td>Deposit progress, stamp duty concessions, FHSS eligibility, borrowing capacity, purchase timeline</td></tr><tr><td><strong>Existing Home Owner</strong></td><td>Equity growth, refinancing opportunities, debt paydown, strategic options (upgrade, renovate, invest)</td></tr><tr><td><strong>Investor</strong></td><td>Portfolio yield, negative gearing, capital growth, expansion capacity, tax position</td></tr><tr><td><strong>Downsizer</strong></td><td>Downsizer super contributions, sale proceeds, lifestyle alignment, age pension impact, CGT</td></tr></tbody></table>

### Review frequency

How often ScaleAI generates a review for the client:

* **Monthly** — short-term focus, changes since last month, immediate action items
* **Bi-Monthly** — every two months
* **Quarterly** — medium-term trends, progress toward annual goals
* **Semi-Annually** — broader strategic check-in
* **Annually** — comprehensive year-in-review with long-term planning

### Approval workflow

Controls what happens after ScaleAI generates a review:

| Mode                 | Behaviour                                                                                  |
| -------------------- | ------------------------------------------------------------------------------------------ |
| **Auto-approve**     | Reviews are sent directly — no manual sign-off needed                                      |
| **Pending approval** | Reviews land in your queue. You review, optionally add recommendations, then send or skip. |
| **Manual review**    | Full manual oversight — nothing goes out without your explicit action                      |

{% hint style="warning" %}
If you choose **Pending approval** or **Manual review**, unactioned reviews appear as a badge count on the **AI Review** item in your sidebar. Open it to work through the queue.
{% endhint %}

### Review scope

Toggle which areas the AI analyses for each review. All ten parameters are enabled by default — turn off any areas that aren't relevant to a particular client.

| Parameter                            | What it covers                                                              |
| ------------------------------------ | --------------------------------------------------------------------------- |
| **Portfolio Performance**            | Property values, total equity, debt positions, overall portfolio health     |
| **Loan Structure & Competitiveness** | Interest rates vs market, refinancing opportunities, loan type suitability  |
| **Cashflow Position**                | Rental income, repayments, net cashflow, surplus or deficit                 |
| **Rate Sensitivity**                 | Impact of rate changes on repayments and serviceability                     |
| **Goals & Lifestyle Alignment**      | Progress toward goals, timeline feasibility, lifestyle fit                  |
| **Tax Optimisation**                 | Negative gearing, depreciation, CGT considerations, deduction opportunities |
| **Wealth Trajectory**                | Long-term equity growth, net worth projections                              |
| **Borrowing Power**                  | Current borrowing capacity, limiting factors, trends                        |
| **Market Update & Opportunities**    | Local market conditions, growth trends, investment opportunities            |
| **Action Items & AI Summary**        | Prioritised next steps with ownership tags (broker, client, or system)      |

### Additional context

You can add free-text context to steer the review — for example, "Client is considering selling the Bondi unit in Q3" or "Focus on rate expiry in January." This is passed to ScaleAI alongside the portfolio data.

***

## Scheduling Bot

The Scheduling Bot monitors client readiness and either books meetings automatically or notifies you when a client hits a threshold you've defined.

### Action mode

Choose what happens when a client becomes ready:

{% tabs %}
{% tab title="Auto-book meetings" %}
ScaleAI automatically books a meeting in your connected Google Calendar and sends the client an invite with your template message. Best for brokers who want a hands-off approach to client engagement.
{% endtab %}

{% tab title="Notify me first" %}
ScaleAI sends you a notification when a client reaches the trigger threshold. You decide whether and when to book. Best for brokers who prefer to review before reaching out.
{% endtab %}
{% endtabs %}

### Timing settings

| Setting             | What it controls                                                       | Options                                          |
| ------------------- | ---------------------------------------------------------------------- | ------------------------------------------------ |
| **Lead time**       | How far ahead of a key date (e.g. fixed rate expiry) to trigger action | 1 month, 2 months, 3 months, 6 months, 12 months |
| **Meeting trigger** | The metric that determines client readiness                            | LVR, Equity, Goals                               |
| **Target value**    | The threshold that fires the trigger (e.g. LVR reaches 80%)            | Any percentage value                             |

{% hint style="info" %}
**How client readiness works:** ScaleAI classifies each client into one of three readiness tiers — **Month** (ready now), **Quarter** (ready soon), or **Year** (longer-term). The classification uses LVR, available equity, cash savings, and borrowing power. When a client moves into your configured trigger zone, the bot acts.
{% endhint %}

![Scheduling Bot settings with action mode tabs, lead time, trigger metric, and target value](https://1103942972-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIVoALSAigc466POg2rP1%2Fuploads%2Fgit-blob-488cc12d60b7e2b3d0986c7bd9c5a1d8bb7d5cde%2FAI_Assistant_Scheduling_Bot_Settings.png?alt=media)

### Meeting invite message

Customise the message sent with calendar invites. Use it to set context for the meeting — e.g.:

> Hi \[Name], great news! Your LVR has hit 80%, meaning you may have equity to unlock. I've tentatively booked a time for us to chat.

***

## Working with pending reviews

When reviews come through (under **Pending approval** or **Manual review** mode), you work through them in the AI Review queue:

1. Open **AI Review** from the sidebar — the badge shows how many reviews are waiting.
2. Each review card shows the client name, review type, and the full AI-generated analysis covering the sections you've enabled.
3. Read through the review. Add your own recommendations in the text field at the bottom if needed.
4. **Send** to deliver the review to the client, **Skip** to move to the next one, or use the calendar icon to book a meeting directly from the review card.
5. Once all reviews are actioned, the queue resets until the next cycle.

You can also trigger a one-off review for any client from the Client Manager — open the client's detail panel, go to the AI Assistant tab, and use the review settings to generate one immediately.

***

<details>

<summary>FAQs</summary>

**Can I change automation settings after a client is created?**\
Yes. Open the client in the Client Manager, go to their detail panel, and update the review template or scheduling bot settings at any time. Changes take effect from the next review cycle.

**Do automations require Google Calendar to be connected?**\
The Scheduling Bot's auto-book feature requires a Google Calendar integration. Reviews work independently of calendar — they're generated and queued in-app regardless. See [Connect Your Integrations](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/workspace/connect-your-integrations.md) for setup.

**What happens if I have global settings and per-client settings?**\
Per-client settings always win. If you've configured automations for a specific client (either during onboarding or from the Client Manager), those override your global defaults.

**Can I disable automations for a specific client?**\
Yes. Edit the client's automation settings and switch to **Manual review** with a longer frequency (e.g. annually). The AI will still generate reviews but less frequently, and nothing goes out without your approval.

**How are reviews different from Ask AI / Broker Brain?**\
AI Reviews are scheduled, structured portfolio assessments that follow your template and scope settings. Ask AI and Broker Brain are conversational — you ask questions and get real-time answers. Reviews are proactive; Ask AI is reactive.

**What data does the AI use to generate reviews?**\
ScaleAI pulls the client's full portfolio data: property values, loan details, cashflows, goals, personal financials, and market data. It cross-references this against benchmarks (LVR thresholds, yield ranges, debt service ratios) to produce actionable insights.

</details>


---

# 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/workspace/set-up-your-automations.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.