> 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/api/rest-api/scaleai-rest-api.md).

# ScaleAI REST API

{% @scale-docs-page-title/page-title title="ScaleAI REST API" %}

{% hint style="warning" %}
**Confirm before publishing:** Reconcile all 21 method/path pairs, request DTOs, response DTOs, auth checks and stream media types against the currently deployed FastAPI `/openapi.json`. The route inventory below comes from the repository's `scaleai-r16-openapi.json` snapshot; it does not establish that each operation or schema matches production today. Confirm whether internal `/frontend` routes belong in the published reference.
{% endhint %}

This is the R16 FastAPI engine used by ScaleApp and backend services for chat, reviews, suggestions, meeting scheduling, note summarisation and memory embedding. It is an **internal service API**. The proposed public API should expose selected product operations through a separate, authorized contract.

The current snapshot advertises `https://agent-backend.r16.app` and contains 21 operations and 27 component schemas. The imported [ScaleAI r16 reference](https://scaleai-r16.apidocumentation.com/reference) displays each operation's current documented request body and DTO fields.

## Operation index

| Family                  | Method and path                                               | Request DTO                |
| ----------------------- | ------------------------------------------------------------- | -------------------------- |
| Service                 | `GET /`, `GET /health`, `GET /models`, `GET /config`          | None                       |
| Identity and strategies | `GET /auth/validate`, `GET /strategies`                       | None                       |
| Chat                    | `POST /chat/`, `POST /chat/stream`                            | `ChatRequest`              |
| Portfolio review        | `POST /review/chat`, `POST /review/stream`                    | `ReviewRequest`            |
| Structured review       | `POST /review/json`                                           | `JSONReviewRequest`        |
| Meeting scheduler       | `POST /meeting-scheduler/`, `POST /meeting-scheduler/stream`  | `MeetingSchedulerRequest`  |
| AI suggestions          | `POST /suggestions/ai`, `POST /suggestions/ai/stream`         | `MessageSuggestionRequest` |
| Broker suggestions      | `POST /suggestions/broker`, `POST /suggestions/broker/stream` | `MessageSuggestionRequest` |
| Note summarisation      | `POST /notetaker/summarise`                                   | `SummariseRequest`         |
| Memory embedding        | `POST /memory/embed`                                          | `EmbedRequest`             |
| Internal frontend       | `GET /frontend`, `GET /frontend/{filename}`                   | None                       |

The exact trailing slash is part of the documented path. Do not silently substitute `/chat` for `/chat/` or `/meeting-scheduler` for `/meeting-scheduler/` in a generated client.

## Request and response models

The snapshot defines `ChatRequest`/`ChatResponse`, `ReviewRequest`/`ReviewResponse`, `JSONReviewRequest`/`JSONReviewResponse`, `MeetingSchedulerRequest`/`MeetingSchedulerResponse`, `MessageSuggestionRequest`/`MessageSuggestionResponse`, `SummariseRequest`/`SummariseResponse` and `EmbedRequest`/`EmbedResponse`. It also includes action, attendee, memory, transcript, user and validation models.

For each operation, use the generated reference for field types, required fields and validation errors. The `/stream` operations need a separately verified event format and media type: the current snapshot lists `application/json` for their 200 responses, which does not prove the actual streaming transport.

## Service boundary

ScaleAI reads product data through its authorized data services and tools. This FastAPI spec does not document the product REST API or the database GraphQL schema. A client-facing version should define its own authentication, resource permissions, stable response DTOs, error contract and rate limits before any of these internal paths are offered externally.


---

# 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/api/rest-api/scaleai-rest-api.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.