> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fullotto.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Change profile

> Before it reviews a pull request, Otto classifies the change, and the review is shaped by that classification.

> [!NOTE]
>
> The change profile is in preview and is turned on per workspace. Ask us to
> enable it for yours.

Before a full review starts, Otto classifies the pull request: what kind of change it is, how risky it is, which kinds of risk it carries, and how far a defect could reach. That one classification decides how hard the review works, whether a second reviewer joins in, and what the reviewer checks first.

## What you see

Every full review's summary gets one line:

> **Change:** bug fix · high risk (concurrency, stored data) · reaches a few other modules

| Part | Values |
| - | - |
| Change type | feature, bug fix, refactor, dependency bump, infra or config change, tests or docs only, design or spec |
| Risk | low, moderate or high: how costly or subtle a defect here could be |
| Risk areas | security, stored data, contracts (APIs and other code that relies on this code), money, concurrency, deploy |
| Reach | stays in the changed code, reaches a few other modules, or reaches many callers |

Re-reviews of new commits that only look at what changed keep the line from the review they build on.

## What it changes

* **How deep the review goes.** A high-risk change gets a thorough review. A low-risk one, such as a change to tests or docs only, can get a lighter review.
* **Whether a second reviewer runs.** In workspaces with [adversarial reviews](https://docs.fullotto.app/configuration/adversarial-reviews.md) in `auto` mode, the profile answers the gate's risk, contract and security checks. See [Model-assisted gate](https://docs.fullotto.app/configuration/adversarial-reviews.md#model-assisted-gate).
* **What the reviewer checks first.** In workspaces where it's turned on, the reviewer is told how the change was classified and gets a short checklist for up to three risk areas. For example, "every new or changed entry point checks who the caller is" for security, or "retries are idempotent" for concurrency. The reviewer is told to follow the code wherever it says otherwise.

## Guard rails

The classification makes a review more careful only when it is fairly sure (three to one). It makes a review lighter only when it is very sure (nine to one), and never past what Otto's own signals require:

* A review is never lightened past a design or spec document, a migration that ships with code, a path your `otto.yml` reviews at Deep or Max, an open blocking finding from an earlier review, a change touching authentication, permissions or secrets, or a removed definition that other files still use.
* When the classifier is unsure about a part, Otto's own signals decide that part. When it is slow or unavailable, they decide all of it, and the line says it came from Otto's rules.

`otto.yml` settings still apply. [Review depth](https://docs.fullotto.app/configuration/review-depth.md) picks the review tier, and the adversarial `gate` settings still turn checks off, scope them to paths and set their thresholds. See [Model-assisted gate](https://docs.fullotto.app/configuration/adversarial-reviews.md#model-assisted-gate) for how thresholds combine with the profile.

## What the classifier sees

A small classification model reads only the pull request's metadata:

* the changed file paths, their sizes and line counts, and the risk areas their paths suggest;
* the names of changed definitions and how many other files use them;
* counts of security-relevant patterns on the changed lines, such as new endpoints or removed guards;
* the title and description, with code blocks removed.

It never sees your code or the diff. It answers in a fraction of a second, before the review starts.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.