Import Existing Tests

If your team already has test specs, scripts, or issues, you can bring them into a TestVibe group instead of recreating each feature by hand.

Imported features become part of Tests and can be edited, generated, and run like other TestVibe tests.

An ordinary GitHub issue, from the moment it is imported to a passing Playwright test — including the question the agent asks along the way. The import, generation, and run take a couple of minutes of real time.

What To Import

TestVibe drafts a Gherkin feature from existing material. Each import is Assistant-drafted, not a 1:1 copy, so review the result before generation.

Source	Why
A document — PDF, Word, Excel, CSV, text, or Markdown	A spec, test script, or spreadsheet of test cases is segmented into one or more feature drafts.
A GitHub issue	An issue from the linked repo becomes a feature draft.
Raw Gherkin text	Paste it directly into a blank feature (see below).

Import From A Document Or GitHub Issue

1. Open the Tests.
2. Select the group where the new feature belongs.
3. From the New test dialog choose Import document (PDF, Word, Excel, CSV, text, or Markdown — or drop the file onto the feature list or a feature row), or choose Import issue (requires a connected issue tracker).
4. Watch the staged pipeline run, answering any inline questions:
   • Extract & segment — reads the document (or issue) and breaks it into candidate features.
   • Draft feature file(s) — writes the Gherkin draft(s).
   • Enrich from screenshots — for PDFs with embedded images, folds in details (fields, dialogs, expected screens) the text alone missed. Skipped for non-PDF sources or text-only PDFs.
   • Verify against your site — only when the project has a test site URL: replays the drafted path in a live browser and corrects screen names, labels, and invented data against what's actually there.
   • Finalize the draft(s).
5. Review the drafted features, or cancel and keep the draft as-is.

An Excel or CSV import treats each row as a candidate test case; a Word/PDF/text/Markdown import treats the document as prose and segments it by described behavior. One import can split into multiple feature files. See Import for the import panel reference.

The Issue Gets A Comment Back

When you import from a GitHub issue or a Jira story, TestVibe posts one comment on that ticket as soon as the import starts, then rewrites that same comment as the work moves. It is never a thread of separate updates — the ticket always shows the current state and nothing else.

The comment says	It means
Drafting tests from this story…	The import is reading the ticket and writing Gherkin.
TestVibe needs one answer before it can draft these tests.	The agent paused on a question. Open the import in TestVibe and answer it.
N test features drafted — waiting for your approval.	The draft is ready to review. Nothing is generated until you press Generate.
Approved — generating the tests…	Generation is running.
Running the tests against the app…	The generated tests were dispatched as a run.
Done.	The verdict, with the pass/fail counts and a link to the run.

After you approve a story's draft for generation, successful generation can continue to a run and report the result back to the ticket. A missing requirement, verification failure, or service error can still need attention; read the current import and run status.

Bring In Raw Gherkin

If you already have Gherkin text you want to keep verbatim, create a Gherkin test in the target group and paste your content into the editor. This skips Assistant drafting and keeps your wording exactly.

Review After Import

After importing, open each feature and check:

Review	Why it matters
Feature name	It should match the behavior being tested.
Scenarios	Each scenario should be focused and testable.
Steps	Steps should use visible UI details and expected outcomes.
Background	Shared setup should apply to every scenario.
Test data	Data should exist or be created during the test.

Imported Gherkin may need cleanup before generation. Imported descriptions are drafts to review, not a guarantee that the application supports every requested step.

Common Cleanup

• split very long scenarios
• replace vague steps with visible actions and results
• remove implementation notes that are not user behavior
• add missing Then assertions
• move repeated setup into Background
• update old labels or page names to match the current app

Next

Improve imported content with Write good test instructions, then generate code with Generate Playwright code.