> 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-reviews.md).

# AI Client Reviews

AI Reviews are automated portfolio analyses that ScaleAI generates for each of your clients on a schedule you control.

Every review is built from real data — properties, loans, cashflows, goals, and market conditions — and tailored to the client's situation. You review the analysis, optionally add your own recommendations, and send it to the client in one flow.

Unlike ad-hoc conversations with your [AI Assistant](/scaleconnect-docs/scaleai/ai-assistant.md) or [Broker Brain](/scaleconnect-docs/scaleai/broker-brain.md), reviews are structured, periodic, and designed to be shared directly with clients through the ScaleApp chat.

***

## How Reviews Are Triggered

Reviews are generated based on the frequency you configure — either globally for all clients or individually per client.

### 1. Scheduled Reviews

When a client's review cycle comes due, ScaleAI automatically generates the review and routes it according to your approval mode.

Available frequencies: Monthly, Bi-monthly, Quarterly, Semi-Annual, Annual

### 2. Manual Reviews Trigger

You can trigger a review for any client at any time, outside the regular schedule.

1. Open the client's AI Assistant and open the **Review Template Settings** modal.
2. From there, generate a one-off review that uses the client's current template and settings.

{% hint style="info" %}
You can also request an AI Review for a specific client or many clients simultaneously through the AI Assistant or Broker Brain.
{% endhint %}

One-off reviews are useful before a scheduled meeting, after a significant market event, or when a client's circumstances change (new property, salary increase, loan refinance).

{% @arcade/embed url="<https://app.arcade.software/share/26orvjfIEtXs4pGrYhwX>" flowId="26orvjfIEtXs4pGrYhwX" %}

***

## Review Contents

Each review is composed of both fixed and selectable sections you can toggle on or off per client.

### Fixed sections

These are included in every review regardless of configuration:

<table><thead><tr><th width="216.734375">Section</th><th>What it covers</th></tr></thead><tbody><tr><td><strong>Portfolio Composition</strong></td><td>Breakdown of property types, locations, values, and ownership structures</td></tr><tr><td><strong>Summary</strong></td><td>Executive overview of the client's position and key takeaways</td></tr><tr><td><strong>Snapshot</strong></td><td>Current metrics — total equity, LVR, debt, net worth, cashflow position</td></tr><tr><td><strong>Property Overview</strong></td><td>Individual property details with values, loans, rental yields, and growth</td></tr><tr><td><strong>Observations &#x26; Insights</strong></td><td>Data-driven observations following fact → insight → implication chains</td></tr><tr><td><strong>Key Drivers</strong></td><td>The primary factors influencing the client's portfolio direction</td></tr><tr><td><strong>Goal Progress</strong></td><td>Status against each goal with percentage completion and timeline</td></tr><tr><td><strong>Next Steps &#x26; AI Summary</strong></td><td>Prioritised actions with [BROKER], [CLIENT], and [SYSTEM] ownership tags</td></tr></tbody></table>

### Selectable sections

Toggle these on or off from the Review Template Settings. All are enabled by default.

<table><thead><tr><th width="241.9296875">Section</th><th>What it covers</th></tr></thead><tbody><tr><td><strong>Portfolio Performance</strong></td><td>Property values over time, total equity growth, debt trajectory</td></tr><tr><td><strong>Loan Structure &#x26; Competitiveness</strong></td><td>Current rates vs market, refinance opportunities, loan type suitability</td></tr><tr><td><strong>Cashflow Position</strong></td><td>Rental income, repayments, net cashflow, surplus or deficit analysis</td></tr><tr><td><strong>Rate Sensitivity</strong></td><td>Impact of rate movements on repayments, serviceability, and cashflow</td></tr><tr><td><strong>Goals &#x26; Lifestyle Alignment</strong></td><td>How the portfolio aligns with the client's life goals and timeline</td></tr><tr><td><strong>Tax Optimisation</strong></td><td>Negative gearing, depreciation, CGT considerations, deduction opportunities</td></tr><tr><td><strong>Wealth Trajectory</strong></td><td>Long-term net worth projections, equity compounding, retirement readiness</td></tr><tr><td><strong>Borrowing Power</strong></td><td>Current borrowing capacity, limiting factors, and trends over time</td></tr><tr><td><strong>Market Update &#x26; Opportunities</strong></td><td>Local market conditions, growth corridors, and investment signals</td></tr><tr><td><strong>Action Items</strong></td><td>Detailed action list expanding on the prioritised next steps</td></tr></tbody></table>

{% hint style="info" %}
Disable sections that aren't relevant to a client's situation. A First Home Buyer with no properties yet doesn't need Portfolio Performance or Loan Structure — focus the review on deposit progress, borrowing power, and market opportunities.
{% endhint %}

***

## How to Configure Review Settings

Review settings can be configured at two levels: globally for your account, or individually per client. Per-client settings always override your global defaults.

### Global Settings

1. Open **Settings** from the sidebar.
2. Navigate to **Automations**.
3. Under **AI Client Reviews**, configure the default frequency, approval mode, and section toggles.
4. These settings apply to every client who doesn't have their own per-client overrides.

<figure><img src="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" alt=""><figcaption></figcaption></figure>

### Client-Specific Settings

1. Open the client in the **Client Manager**.
2. Go to the **AI Assistant** tab on the client's detail page.
3. Click the settings icon to open the **Review Template Settings** modal.
4. Choose the template type (First Home Buyer, Existing Home Owner, Investor, and/or Downsizer).
5. Set the review frequency.
6. Toggle individual sections on or off.
7. Add any additional context in the free-text field to steer the AI's analysis.

<figure><img src="https://1103942972-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIVoALSAigc466POg2rP1%2Fuploads%2Fgit-blob-646ef760b9767323423c51876a02e3100cc2d047%2FAI_Assistant_Client_Review_Settings.png?alt=media" alt=""><figcaption></figcaption></figure>

### Approval mode

The approval mode controls what happens after ScaleAI generates a review:

<table><thead><tr><th width="205.55859375">Mode</th><th>Behaviour</th></tr></thead><tbody><tr><td><strong>Auto-approve</strong></td><td>Reviews are sent directly to the client's ScaleApp chat — no manual sign-off needed</td></tr><tr><td><strong>Pending approval</strong></td><td>Reviews land in your Tasks queue for review before sending</td></tr><tr><td><strong>Manual review</strong></td><td>Full manual oversight — you must read, optionally edit, and explicitly send each review</td></tr></tbody></table>

Auto-approve is best when you trust the AI output and want a hands-off approach. Pending approval gives you a chance to scan each review before it reaches the client. Manual review is the most cautious option — nothing goes out without your explicit action.

***

## Reviewing and Acting on AI Reviews

When reviews are generated under **Pending approval** or **Manual review** mode, they appear in your Tasks queue.

1. Click the **Tasks** icon in the top navigation bar. The badge count shows how many items are waiting.
2. The review queue displays swipeable cards — one per pending review.
3. Each card shows the client's name, review type, and the full AI-generated analysis.
4. Read through the review. Check that the observations are accurate and the next steps make sense for the client's current situation.
5. Optionally add your own **recommendations** in the text field at the bottom of the card. Your recommendations are appended to the review before it's sent.
6. Choose an action:
   * **Send** — delivers the review as an HTML message in the client's ScaleApp chat
   * **Skip** — moves to the next review without sending (the skipped review remains in the queue)
   * **Book Meeting** — triggers the [Calendar Agent](/scaleconnect-docs/scaleai/ai-assistant/calendar-agent.md) scheduling flow to book a follow-up meeting with the client alongside the AI Review
7. Once sent, the review is delivered as a formatted HTML message in the client's chat thread within ScaleApp. The client can read it on their mobile device, ask follow-up questions through the app's AI assistant, and take action on the recommended next steps.

{% hint style="info" %}
Adding your own recommendations is where reviews become most valuable. The AI provides the data analysis — your expertise adds the strategic advice that turns a report into a conversation starter.
{% endhint %}

{% @arcade/embed url="<https://app.arcade.software/share/4fWEsKNs7K0AR2CnwO3y>" flowId="4fWEsKNs7K0AR2CnwO3y" %}

***

## How Reviews Feed Into Other Features

AI Reviews don't exist in isolation — they connect to other parts of the ScaleAI ecosystem:

* **Calendar Agent** — A review that recommends a meeting can trigger the [Calendar Agent](/scaleconnect-docs/scaleai/ai-assistant/calendar-agent.md) to schedule one. The Book Meeting button on the review card opens this flow directly.
* **Client Notes** — Review content is stored against the client's profile, building the knowledge base that makes future reviews and AI conversations more personalised. See [Transcription](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/scaleai/transcription.md) for how notes accumulate.
* **AI Workflows** — Reviews can be part of automated chains. For example, a review identifies an expiring fixed rate, recommends refinancing, and the [Scheduling Bot](/scaleconnect-docs/scaleai/broker-brain/ai-workflows.md) picks up the signal to book a meeting. See [AI Workflows](/scaleconnect-docs/scaleai/broker-brain/ai-workflows.md) for the full chain.
* **Ask AI** — After a review is sent, you can use [Ask AI](https://github.com/scaleapp-au/scaleconnect-docs/blob/main/scaleai/product-docs/scaleconnect-docs/scaleai/ask-ai.md) to deep-dive into any observation or metric the review surfaced.

### AI Reviews in Client Notes

{% @arcade/embed url="<https://app.arcade.software/share/z2wU3pkuO9k6y94jqxTf>" flowId="z2wU3pkuO9k6y94jqxTf" %}

***

<details>

<summary>Can I customise the review format or template?</summary>

You control which sections appear and can add free-text context to steer the analysis. The review structure itself (snapshot, observations, goal progress, next steps) is standardised to ensure consistency across clients and review cycles.

</details>

<details>

<summary>What happens if I skip a review?</summary>

Skipped reviews stay in your queue. They won't be sent to the client. You can return to them later, or they'll be replaced by the next scheduled review for that client when the cycle repeats.

</details>

<details>

<summary>Can clients see the review before I send it?</summary>

No. Under Pending approval and Manual review modes, the review only reaches the client after you explicitly send it. Under Auto-approve, reviews are sent immediately upon generation.

</details>

<details>

<summary>How does the AI generate different reviews for different client types?</summary>

ScaleAI uses the client type (First Home Buyer, Existing Home Owner, Investor, Downsizer) to adjust the analysis framework, weighting, and language. An investor review emphasises yield and tax position; a first home buyer review emphasises deposit savings and borrowing capacity. The underlying data is the same — the interpretation lens changes.

</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/scaleai/ai-assistant/ai-reviews.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.