Verify AI Agent code changes - Revyl Documentation

AI agents work in a verification loop: make a code change, start the app, and iterate on the feedback. Revyl lets agents launch your mobile app in the cloud and verify their changes.

Prerequisites

Revyl CLI installed and authenticated. See Authentication for more details.
An AI Agent is installed (Cursor, Claude Code, Codex)

Initialize and Install Skills

Navigate to your project and initialize Revyl using the CLI:

revyl init

The initialization will:

Either link to an existing app or create a new one
Configure the framework to be used for the dev loop
Ask which AI coding tool is used to install the Agent Skill. See Agent Skills for more details.
Ask if you would like to build the app and upload the build to get started. Note: a build is required to verify any changes. See Framework Guides for how to configure your build for your framework.
You can then finish the setup. There is no need to start a dev session because that will be driven by the AI Agent.

Your AI Agent now has the skills necessary to use Revyl within the dev loop.

Add a Revyl section to your AGENTS.md or CLAUDE.md

If your repo already has an AGENTS.md or CLAUDE.md file, add a section to it directing your AI Agent to use Revyl whenever a code change occurs, so it verifies changes as part of its normal workflow. Otherwise, create a new file with that section. Here is an example:

# Agent Guidance
## Revyl Verification

When developing or changing a feature in this repo, use the Revyl dev loop to verify the behavior on a device before finishing.

- Read and follow the local `revyl-cli-dev-loop` skill guidance before running Revyl commands.
- Verify the user-visible outcome with device evidence, such as `revyl device screenshot`, `revyl device report --json`, or explicit interaction through `revyl device instruction`.
- Summarize Revyl verification in the final response: what path was exercised, what evidence was captured, and any issues or limitations. If Revyl cannot be run, state the concrete blocker and the fallback verification used.

Whenever a change occurs, your AI coding agent will now use Revyl to verify the change and iterate based on the feedback.

Add Pull Request Guidance

You can also add the Revyl session info to a Pull Request that gets opened so that you can review the recorded session, exact steps, network logs, and performance of the verification that was done. Here is an example section to add to the AGENTS.md or CLAUDE.md file:

## Revyl Evidence in Pull Requests

When opening or updating a PR for work where Revyl was run, include:

- A link to the Revyl session report. Generate it with `revyl session share <session-id> --json` and use the `shareable_link` it returns, so reviewers without a Revyl account can open the report.
- Screenshots embedded inline. Publish each image with `revyl session publish <file> --session <session-id> --json` and embed the `public_url` it returns. Never point image markdown at a local file path: the file is not uploaded, so it renders as a broken image.
- An explicit width on every image. Use an HTML `<img>` tag rather than `![alt](url)`, because a markdown image renders at full resolution and one phone screenshot then fills the whole comment.

There should be a body in the PR as such:

```markdown
## Revyl Verification

<table>
<tr>
<td align="center"><img src="https://backend.revyl.ai/api/v1/reports-v3/proof-media/home.png?token=<share-token>" alt="Signed-in home screen" width="220"><br><sub><b>Start state</b></sub></td>
<td align="center"><img src="https://backend.revyl.ai/api/v1/reports-v3/proof-media/settings.png?token=<share-token>" alt="Settings screen" width="220"><br><sub><b>After navigation</b></sub></td>
</tr>
</table>

- Report session: https://app.revyl.ai/sessions/report?token=<share-token>
```

Whenever a Pull Request is opened by your AI coding agent, the Revyl verification will be posted for review.

Best Practices

Frameworks like Expo/React Native support hot reloading, so most changes don’t need a rebuild. Others require a build every time, which can slow down verification — use Remote Builds to cut that time down.

​Prerequisites

​Initialize and Install Skills

​Add a Revyl section to your AGENTS.md or CLAUDE.md

​Add Pull Request Guidance

​Best Practices

Prerequisites

Initialize and Install Skills

Add a Revyl section to your AGENTS.md or CLAUDE.md

Add Pull Request Guidance

Best Practices