Skip to content
Quorum
Start free trial

Quorum Designer

Tested in minutes.
Never guessed.

Paste a Jira key. Designer reads the story, its epic and its linked tickets, drafts the full test suite and turns every rule the ticket forgot into a question before it turns into a bug. Your QA accepts every case before it reaches Jira.

Try Designer free for 7 daysSee how it works

One free trial per person. Card needed; cancel before day 7 and pay nothing. Works with the Jira Cloud you already have.

  • 1click from approved cases to Jira or your test tool. No copy‑paste.
  • 0business rules made up. Every gap becomes a question.
  • 100%of cases traced to an acceptance criterion, or flagged.
Accept & send to Jira
Test cases5 cases · 2 questions
  • TC-1

    Apply a valid percentage code

    PositiveHighAC1
  • TC-2

    Apply an expired code at checkout

    NegativeHighAC2Depends on assumption
  • TC-3

    Apply a code typed in lowercase

    EdgeMediumAC1Depends on assumption
  • TC-4

    Apply a discount larger than the order total

    Proposed
    EdgeMediumAC1
  • TC-5

    Reject a malformed code

    Edit proposed
    NegativeLowAC2

    Expected result

    Shows a generic error

    Shows "Code not recognized" under the field

Open questions
BlockingTC-2

When a code has expired, should checkout show an error or remove the code silently?

Show an errorRemove silently
AssumptionTC-3

I assume codes are case-insensitive, so SAVE10 and save10 are the same code. Confirm?

Chat
TC-3

Why is this an edge case and not a positive one?

AC1 never says whether codes are case-sensitive, so lowercase input is a boundary. I assumed it works and opened a question for you to confirm.

TC-2TC-5
The maximum length check is missing

Integrations

Designer sends approved cases where your team keeps them.

Available now

Or stop paying for one more tool and keep them in Quorum Reporter (coming soon).

Questions

It asks
before it guesses.

A missing rule is a question for your team, not a blank for the model to fill. Quorum finds the gaps in a story and asks about them, with concrete options to pick from.

BlockingAffects TC-2, TC-6

When a code has expired, should checkout show an error or remove the code silently?

Show an errorRemove silently

The ticket says “invalid codes show an error” but never mentions expired ones.

AssumptionAffects TC-3

I assume codes are case-insensitive, so SAVE10 and save10 are the same code. Confirm?

Usual for promo codes, but AC1 does not say so.

AnsweredUpdated TC-4

If the discount is larger than the order total, what is the final amount?

The total is capped at zero. Shipping is still charged.

Recorded on the story when you send, so devs and the PO see the decision too.

Blocking

The answer changes what a case should expect, and the ticket gives nothing to go on. Answer it or dismiss it before anything is sent.

Assumption

A safe convention, said out loud: “I assume X, confirm it.” Every case that relies on it is flagged, so nothing rests on a silent guess.

Only questions worth asking

Before it asks, the agent looks for the answer in the ticket, its epic and the linked issues. Related doubts arrive as one question, not five.

Answers flow into the cases

Pick an option or write your own. The agent proposes the matching edits to every case your answer touches.

How it works

Story in.
Test cases out.

Five steps on one screen: the story on the left, the cases in the middle, questions and chat on the right. You make the call at every step.

  1. 01

    Connect Jira

    Point Quorum at your Jira Cloud site with an API token, kept encrypted on the server. Choose where each project's test cases go: Jira, Xray, Zephyr, TestRail or Qase.

  2. 02

    Pick a story

    Find it by key or text with ⌘K. Before anything runs, you see what the agent will read: the epic, linked tickets and subtasks.

  3. 03

    Generate

    Cases and open questions stream in as they are written. Each case maps to an acceptance criterion, and any case that rests on an open question is flagged.

  4. 04

    Refine in chat

    Select cases, or a single step, and say what is off. The agent can push back with reasons, and every change it suggests waits for your approval.

  5. 05

    Accept and send

    Each accepted case lands where your team keeps tests: a sub-task or linked issue in Jira, a Manual test with its steps in Xray, a Zephyr test case linked for coverage, or a TestRail or Qase case tied to the story. Your answers go on the story as a comment, so the decisions are written down.

Review

Reviewed like
a pull request.

Traced to the ticket, diffed field by field, approved by a person. The bar your team already sets for code.

See the gaps before you send

Every case points to the acceptance criterion it covers, and criteria with no cases stand out. No criteria on the ticket? The agent drafts them from the description, marks them as inferred and asks you to confirm.

Proposals, not overwrites

The agent never touches a case directly. Edits arrive as a field-by-field diff, new cases as drafts, deletions with a reason. Accept or reject each one, or all at once.

Your selection is the context

Select a case, a few, or a single step, and the agent answers about exactly that. Select nothing and you are talking about the whole story.

In your test tool, not a spreadsheet

Accepted cases go to Jira, Xray, Zephyr, TestRail or Qase, tied to the story so you can find them again, with the ones ready for automation marked.

Compared

Fast is easy.
Right is the product.

Any chatbot can spit out fifty test cases. Some of them test rules nobody agreed on, and nothing tells you which. Quorum is the only one in this table that stops and asks.

  • Time to a reviewable suite

    Quorum Designer
    Minutes, with the open questions listed
    One-shot AI generators
    Seconds, then a cleanup pass to find the guesses
    Manual test design
    As long as the writing takes

  • The ticket leaves a rule open

    Quorum Designer
    Asks you, with concrete options
    One-shot AI generators
    Usually fills the gap with an assumption
    Manual test design
    Depends on who writes the cases

  • Link to acceptance criteria

    Quorum Designer
    Every case, plus coverage per criterion
    One-shot AI generators
    Varies by tool
    Manual test design
    If someone keeps the matrix

  • Changing a case

    Quorum Designer
    Proposed as a diff you approve
    One-shot AI generators
    Edit the output or regenerate
    Manual test design
    Edit by hand

  • Who signs off

    Quorum Designer
    The QA, case by case
    One-shot AI generators
    Up to your process
    Manual test design
    The QA

  • Where the cases end up

    Quorum Designer
    Jira or your test tool, tied to the story
    One-shot AI generators
    Exported or copied into your tool
    Manual test design
    Wherever the team keeps them

Pricing

About $1.30
per story designed.

Put your own number on an hour of QA time and do the math. Designer gives your QA a reviewed draft and the right questions in minutes, instead of a blank page.

  • $39a month for Pro. Compare it with what one hour of your QA's time costs you.
  • ~30stories a month worked end to end: generated, refined in chat and sent to Jira or your test tool.
  • 5places your accepted cases can go, tied to the story: Jira, Xray, Zephyr, TestRail and Qase.

Pro

For one QA engineer

$39/month

Or $390 a year, 2 months free.

  • Unlimited Jira tickets and sessions
  • Test case generation that asks about unclear rules instead of guessing
  • Chat with the agent; every change it makes is a proposal you approve
  • Send accepted cases to Jira, Xray, Zephyr, TestRail or Qase, tied to the story
  • Fair-use AI allowance that covers typical daily use; resets monthly
Start free trial of Designer Pro

Power

For heavy daily use

$79/month

Or $790 a year, 2 months free.

  • Unlimited Jira tickets and sessions
  • Test case generation that asks about unclear rules instead of guessing
  • Chat with the agent; every change it makes is a proposal you approve
  • Send accepted cases to Jira, Xray, Zephyr, TestRail or Qase, tied to the story
  • An AI allowance over 2.5 times the size of Pro’s, for many tickets a day; resets monthly
Start free trial of Designer Power

7 days free, then the plan you chose. One free trial per person, for whichever product you take first. Prices in US dollars, before taxes. See all pricing

Before you start

Try it on a real story.
Risk nothing.

7 days free, one free trial per person. A card is needed to start, nothing is charged during the trial, and cancelling takes a couple of clicks from the billing page.

  • Nothing written without you

    Quorum writes to Jira or your test tool only after a person accepts the case or the bug. No background agent, no surprise tickets.

  • Nothing to install

    No Marketplace app and no change to your Jira workflow. You connect Jira Cloud with your own API token.

  • Keep your current tool

    Designer sends accepted cases to Jira, Xray, Zephyr, TestRail or Qase. Nothing to migrate before you see results.

  • Your keys stay locked

    Jira tokens and tool keys are stored encrypted and sent only to the tool they belong to. Ticket content goes to the AI model only to produce your cases.

FAQ

Questions about Designer.

How long until I see results?
Minutes. Connect Jira with an API token, type a story key and the first cases start streaming in. There is nothing to install and no workflow to change.
What does it do when the story is unclear?
It asks. A rule the story leaves open becomes a question, blocking when the answer changes what a case expects, or an assumption stated out loud for you to confirm. It never fills the gap with a guess, and every case that rests on an open question is flagged.
Do we need to change how we write tickets?
No. Designer works from the stories you already have. If one has no acceptance criteria, the agent drafts them from the description, marks them as inferred and asks you to confirm.
Which test management tools does Designer send to?
Jira, Xray, Zephyr, TestRail and Qase, in their cloud editions. Stories always come from Jira, and each project picks where its cases go: Jira sub-tasks or linked issues with preconditions, steps and expected results; Xray Manual tests with their steps, linked for coverage; Zephyr test cases linked to the story; TestRail cases with the story in their References; or Qase cases attached to the story.
What is the difference between Pro and Power?
Only the monthly AI allowance. Both include everything Designer does; Power includes a much larger allowance, for people who work through many tickets a day.
What about tickets written in Spanish?
Cases and questions come back in the language of the ticket. A story in Spanish gets its test cases in Spanish.

Also from Quorum: Quorum Reporter

Coming soon

Then run them in Reporter.

Test management next to the AI that designed your cases: a repository with versions, manual runs step by step, plans, reports with coverage per story, and Jira bugs drafted for you to review.

Explore Reporter

Your next story deserves better than a guess.

Run Designer on a real ticket today and judge the cases yourself. Your first Quorum product is free for 7 days, with one free trial per person: if it does not save your QA time, cancel before it ends and pay nothing.

Try Designer free for 7 daysSee how it works