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.
TryCase is an AI-assisted end-to-end testing tool that checks the user journeys affected by GitHub pull requests and reports verdicts with video and screenshot evidence. It helps development teams verify web, API, CLI, worker, and package changes without maintaining a browser test suite.
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.
TryCase reads a pull request and selects the user journeys affected by the change, reducing the need to maintain a separate browser test suite.
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.
Each run produces a verdict, captioned video, and final screenshot on the pull request. Failure reports compare the expected and observed behavior.
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.
TryCase can use TryCase Auto, a connected ChatGPT subscription through Codex, or an OpenRouter API key. Claude subscription support is listed as coming soon.
The CLI supports starting, following, continuing, stopping, and retrieving verification results. Commands return JSON, while live follow output uses NDJSON.
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.
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.
Exercise APIs, command-line tools, workers, or packages through their actual commands when a change affects non-browser behavior.
Run verification from a terminal or coding-agent workflow, follow status changes, respond to attention requests, and download saved artifacts programmatically.
Use isolated pull-request environments and concurrent workers when multiple changes are under review or developers continue pushing while a check is running.
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.
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.
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.
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.
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.
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
GitBot is a local browser-based workspace for creating reusable coding bots powered by Claude Code, Codex, or OpenCode. It helps developers run those agents across repository folders with persistent threads and configurable permissions.
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.