TryCase icon

TryCase

TryCase is an AI-assisted end-to-end testing tool that checks GitHub pull request journeys and reports verdicts with video and screenshot evidence.

TryCase

AI end-to-end testing for pull requests

TryCase is an AI-assisted end-to-end testing tool for software pull requests. After a repository is connected, it reads each pull request, identifies the user journeys affected by the changes, and runs those journeys against the application in an isolated environment.

The service is designed to add behavioral verification to the pull-request workflow without requiring teams to write or maintain a browser test suite. It returns a verdict and supporting proof—including a captioned video and screenshot—through GitHub, while a command-line interface provides a way to start, monitor, and retrieve verification runs.

Key features

Pull-request-aware test selection

TryCase reads a pull request and selects the user journeys affected by the change, reducing the need to maintain a separate browser test suite.

End-to-end interaction across interfaces

The agent opens the application in a browser and interacts with web interfaces like a user. APIs, CLIs, workers, and packages can be exercised through their real commands.

Evidence attached to GitHub

Each run produces a verdict, captioned video, and final screenshot on the pull request. Failure reports compare the expected and observed behavior.

Parallel, isolated execution

Runs use disposable environments separate from CI, and multiple environments can run according to the plan. New commits update an active run rather than waiting behind it.

Flexible AI provider options

TryCase can use TryCase Auto, a connected ChatGPT subscription through Codex, or an OpenRouter API key. Claude subscription support is listed as coming soon.

CLI and automation workflow

The CLI supports starting, following, continuing, stopping, and retrieving verification results. Commands return JSON, while live follow output uses NDJSON.

Use cases

  • Reviewing application changes

    Connect a repository so each pull request can be checked for the user journeys touched by the change, with a verdict and proof available during review.

  • Checking web journeys

    Use the browser-based agent to check a real customer-facing flow—such as a changed interface or navigation path—without maintaining a dedicated browser test script.

  • Verifying backend and command-line behavior

    Exercise APIs, command-line tools, workers, or packages through their actual commands when a change affects non-browser behavior.

  • Automating test operations

    Run verification from a terminal or coding-agent workflow, follow status changes, respond to attention requests, and download saved artifacts programmatically.

  • Parallel team development

    Use isolated pull-request environments and concurrent workers when multiple changes are under review or developers continue pushing while a check is running.

Pros and Cons

Pros

  • Tests can be started from pull requests without first writing a browser test suite.
  • Results include visual evidence that reviewers can inspect directly alongside the code change.
  • Disposable environments isolate runs from CI and support parallel work while developers continue pushing commits.
  • The CLI exposes structured JSON/NDJSON output for monitoring and automation.
  • Users can choose TryCase-managed AI or connect a ChatGPT subscription through Codex or an OpenRouter key.

Cons

  • The standard test environment is limited to 4 vCPU and 8 GB of memory, so repositories with higher runtime requirements may need setup adjustments.
  • Testing time and concurrent environment limits vary by plan, and running workers consume testing time independently.
  • The product is focused on connected GitHub repositories and currently lists Claude subscription support as coming soon.

FAQ

How does TryCase work with GitHub pull requests?

Install the TryCase GitHub App on selected public or private repositories. You can run checks on every push or trigger one by commenting /trycase run on a pull request. The CLI can also start and monitor verification runs.

Do I need to write end-to-end tests first?

No. TryCase reads the pull request, identifies affected user journeys, and tests them without requiring a browser test suite. You can provide additional instructions through a pull request reply or a verification prompt file.

What results does TryCase return?

A pull request receives a pass or fail verdict, a captioned video, and a final screenshot. Failure details describe what was expected and what actually happened, providing evidence for review.

Where does the test environment run, and how are secrets handled?

Each pull request runs in a disposable environment with 4 vCPU and 8 GB of memory. Use non-production values only. Secrets are encrypted, are not printed in logs or pull requests, and are made available only to approved commands and hosts.

How does the trial and testing-time billing work?

The free trial lasts 14 days and includes 3 end-to-end testing hours and 30 TryCase Auto credits, with no card required. Paid plans start at $19 per month; testing time is measured from actual sandbox runtime, and there are no automatic overage charges.

Quick Facts

Category
Developer tool; AI testing
Primary workflow
End-to-end verification for GitHub pull requests
Interfaces tested
Web apps, APIs, CLIs, workers, and packages
Execution environment
Disposable Linux environment with 4 vCPU and 8 GB memory
CLI
Node 20+; JSON commands and NDJSON live updates
Trial
14 days, 3 testing hours, and 30 TryCase Auto credits; no card required