> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/administer-and-govern/security-and-assurance/architecture-and-assurance-review.md).

# Architecture and assurance review

Frame technical, security and procurement review around the actual deployment rather than generic platform claims.

IT and procurement reviews usually need two kinds of evidence: **how the platform works** and **how your intended use of it is configured**.

Those are related but not interchangeable.

## Platform questions

Typical platform-level review areas include:

* identity and access;
* data handling and storage;
* external Connections and credential handling;
* model-provider configuration;
* programmatic/API access;
* execution monitoring and incident evidence;
* service reliability and support;
* current security, legal and compliance evidence.

Product documentation can explain product behaviour, but formal claims in the last category require current assurance material.

## Use-case questions

A specific deployment adds another layer:

* which Projects and business processes are in scope;
* which systems and data sources they connect to;
* which actions can change external systems;
* which human or service identities provide that authority;
* who can build, publish, operate and administer the capability;
* what human boundaries remain and who owns recurring exceptions;
* how changes are tested and introduced to the live path;
* what execution evidence is reviewed in normal operations and during incidents.

A platform security document cannot answer these implementation-specific questions on its own.

## Keep an evidence pack that matches the deployment

For a substantive review, assemble the current platform assurance material together with a use-case-specific view of data flows, Connections, identities, roles, human handoffs and operational support ownership. Update that view when the operational design or connected systems change.

For execution evidence, see [Logging and monitoring reference](/reference/technical-and-support/runtime-and-security/logging-and-monitoring.md). For rollout controls, see [Rollout and operations](/administer-and-govern/rollout-and-operations.md).

Do not use an old GitBook statement as proof of certification, contractual status or a security control that needs formal evidence.


---

# 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.lleverage.ai/administer-and-govern/security-and-assurance/architecture-and-assurance-review.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.