Written from your specs AI Test Case Generator Map the coverage, then write the cases you pick Do the test once Record a Test Beta Get readable steps and Playwright + pytest scripts It can only read MCP server Let Claude, ChatGPT or Cursor read your test data Compare Test Management OracleAI Pricing Blog Docs Login Start free
AI Test Case Generator

Every tool writes test cases now. Hawzu shows you what they miss.

You see up to forty scenarios and what's missing first, then pick the ones worth writing.

Reads RequirementsCanon documentsPasted contextPDFWord (.docx)Markdown & text
Writes Step / expected resultGherkin (BDD)
Hawzu's AI coverage map — scenarios grouped by lens, depth scored per requirement, and one requirement reporting no scenarios proposed

The coverage map on real requirements. R5 has nothing proposed.

How a run works

Map the coverage. Then write the tests.

You check the list of scenarios first. Steps are written only for the ones you tick.

Stage 01

The coverage map

One line per scenario, with its lens and the requirement it tests.

Stage 02

The test cases

Full steps for the scenarios you ticked.

A generated test case expanded — priority, test type, the requirement it covers, a precondition, and three steps each with its expected result

Stage two. A full case with an expected result on every step.

What it actually does

Drafts that are quick to check

It only links to requirements you gave it

A case written from an attached document isn't linked to any requirement.

It would rather write less

When your source is thin, you get fewer scenarios and a note saying why.

It knows what you already have

It checks the test cases you already have and proposes what's missing.

Focus lenses

The half of testing a spec never writes down

Specs say what should happen. They rarely say what happens when two people do it at once.

What the spec states
  • Functional The behaviour working as described
  • Negative Invalid input, refused actions, failure states
  • Edge cases Boundaries, empty states, odd sequences
  • End to end Journeys crossing the whole behaviour
What the spec assumes
  • State transitions Every legal move — and the moves that aren't
  • Concurrency Two actors on the same item at once
  • Permissions Acting without the role, or on another tenant's data
  • Failure & recovery Interrupted midway, dependency down, retried
  • Data integrity Totals matching parts, references surviving deletion
  • Integration The other side is slow, absent, or returns an error
Built-in safeguards

The rules it can't talk itself out of

  • Every case traces to your source

    It won't make up details that aren't in what you gave it.

  • Gaps are reported, not hidden

    Requirements with nothing proposed are named on screen.

  • Long documents are flagged

    If a source is too long, you're told how much of it was used.

  • Your Canon is used by default

    Cases follow the specs you've shared with Hawzu. You can switch it off per run.

  • It writes test cases. That's all it writes.

    It won't create requirements, suites or releases. It saves nothing you haven't ticked.

The shape of one run

How much one run can handle

40 scenarios per map 30 by default
20 test cases per run written 10 at a time
10 requirements per run in one brief
3 documents attached one PDF, up to 8 MB
Thursday, 4:40 PM

The Refunds v2 spec lands as a PDF. You drop it in, tick six requirements and press Generate.

  • Scenarios mapped 32 across 9 lenses
  • Nothing proposed for REQ-118
  • You tick and write 12 cases, edited, added

The real finding was REQ-118. Nobody had written down what happens to a partial refund on a cancelled order.

Generated cases are ordinary cases

Once you add them, they work like any case you wrote by hand. A small AI tag shows where they came from.

Questions

Generating test cases with AI: FAQ

How do I generate test cases with AI in Hawzu?

Open the Repository and choose Draft test cases with Oracle. Pick up to ten requirements, paste a spec or attach up to three documents. Hawzu maps up to forty scenarios first. Tick the ones worth testing and it writes full test cases. Nothing is saved until you accept them.

Can AI write test cases from a requirements document or a PDF?

Yes. Attach Word, Markdown or text files, or one PDF up to 8 MB, or paste the text. If your project has Canon documents, the generator reads those too by default, and every draft shows which document and section it came from.

Will it duplicate test cases we already have?

It checks the test cases already linked to your requirements and skips scenarios they cover, so the map shows what's missing instead of repeating what you have.

How do I write good test cases with AI?

Start from specific requirements — rules, limits and error cases, not just feature names. Review the scenario map before anything is written, because that's where gaps show. Then check each draft against its source tag before you accept it.

Is the AI test case generator free?

It's on every plan, including the free plan for five people, within a monthly AI allowance. One credit covers about twelve written test cases. See pricing.

Give it a spec. See what you're missing.

Every AI feature on every plan. Free for five people, $20 per member after — no credit card.

Talk to Us

Tell us about your QA setup. We'll get back to you within 24 hours.

Book a demo

Pick a time that works — we'll confirm by email and send a calendar invite.

Select a date

Available times

Times shown in your timezone: —