Automated test script generation turns test cases into executable automation without writing code by hand. In Text2Test you write test steps in plain text and they run as deterministic tests. When a step needs code, Text2Test generates the script from your plain-text description, or you paste your own Playwright script.
You don't maintain a separate codebase of test scripts. Plain-text steps and scripts live in the same test case inside Text2Test, run together, and stay tied to the requirement they came from.
| You need to | Use | How you write it |
|---|---|---|
| Test a user flow: click, type, verify | Plain-text step | In plain text, the way you'd explain it to a teammate |
| Precise programmatic control at one step | Script Injection, generated | Describe the step in plain text; Text2Test writes the script |
| Reuse automation you already have | Script Injection, your own | Paste your existing Playwright script |
| Set up or check data through an API | HTTP Request step | Method, URL and assertions on the response |
Every step is plain text. No selectors, no test code.
| Task | Manual | Text2Test |
|---|---|---|
| Time to write one test script | 30-60 min | Seconds |
| Coverage for 20-feature product | 2-4 weeks | Hours |
| Script quality consistency | Varies by engineer | Consistent |
| Traceability to test cases | Manual tagging | Automatic |
| Updates when specs change | Manual rewrite | Regenerates |
A test case in Text2Test is not a single instruction type. It is a sequence. Each step can be a different prompt type, combined in any order to match exactly what you need to test.
Write the steps in plain text. Text2Test Native reads the screen semantically and executes. No selectors, no DOM knowledge required.
Paste an existing script or auto-generate one and run it inline within the test. For when you need precise programmatic control at a specific step.
Hand control to AI for complex flows that need reasoning. Autopilot navigates the product autonomously and hands back when done.
Take a screenshot diff or check element visibility at any point in the sequence. Catches layout regressions and UI changes.
Call an API and assert on the response. Combine with UI steps to test the full stack in a single test case.
Mix and build in any order. A test case can start with a T2T Native step, run an HTTP request to set state, verify visually, inject a script for a specific action, and hand off to Autopilot for the final flow. All in one sequence.
It is turning test cases into executable automation without writing code by hand. In Text2Test you write steps in plain text and they run directly. When a step needs code, Text2Test generates the script from a plain-text description, or you paste your own Playwright script.
No. Most steps are plain text and run as they are. Scripts are optional: generate one from a plain-text description, or paste your own Playwright script, for steps that need precise programmatic control.
Yes. Paste a Playwright script as a Script Injection step and it runs inline with your plain-text steps, in the same test case.
Yes. Trigger test plans from your pipeline on every push. Tests run in Text2Test, and you get a drillable report for every run.
Copilot autocompletes code as you type. It has no knowledge of your test cases or requirements, and you still own and maintain every script. With Text2Test you describe tests in plain text, tied to your actual requirements, and they run without a script codebase to maintain.
Plain-text steps read the screen semantically, so renamed elements and layout changes usually don't break them. You don't spend engineering time chasing broken locators after every frontend deploy.
Run analysis explains every failure in plain language, including when the real cause is a few steps before the step that failed. You see what went wrong and why, not just a stack trace.
If your team has more than 10 features to test, manual script writing is already your bottleneck. Text2Test closes the gap between test case and running automation without the engineering overhead.
Start Testing