MaveraMavera Docs
Operator's Guide
Checking…
Use or share this pageSend the page itself, print it, or open its complete context in your AI workspace.

Walkthrough: your first study

Every click from blank screen to a result you can screenshot into a deck.

2 min readDocs build Updated Jul 26, 2026
Interactive product walkthrough

Run your first study

Complete every control from blank study to result and source lineage.

Simulation onlyNothing is saved or charged
1
Step 1 of 8Open Studies

Choose Studies from the sidebar.

Demo workspace / Mavera workspace
Local simulation
Mavera workspace

Good afternoon

Choose a surface from the sidebar to begin.

Demo workspace0 actions completed
WorkspaceDemo companySafe local simulation
Current surfacestudyFollow the highlighted action
Recent workspace activityStatus
Audience comparisonReady to review
Customer interview evidenceGrounded
Campaign pre-flightDraft
  1. 1
    Open StudiesChoose Studies from the sidebar.
  2. 2
    Start a studyCreate a new structured study.
  3. 3
    Write the decision questionState the decision the study should resolve.
  4. 4
    Choose the audienceSelect the population that should answer.
  5. 5
    Choose the methodSelect a message test, pricing read, MaxDiff, or survey.
  6. 6
    Set the sampleMove the sample-size control and see the estimate update.
  7. 7
    Run the studyApprove the local plan and start the simulation.
  8. 8
    Read the evidenceOpen the result, uncertainty, and source-lineage panels.

This walks the exact clicks. Nothing assumed. ~5 minutes of your time, 1–3 minutes of Mavera's.

Open Mave

Go to app2.mavera.io and sign in. You land on the chat. If you see a sidebar with Mave / My Research / Workflows / Files on the left, you're in the right place.

Type your question like a human

Click the box at the bottom that says "Ask Mave a question…" and type what you actually want to know. For example:

Test which of these two taglines lands better with busy dog owners: "Know where the good boy is" vs "GPS peace of mind, no subscription"

Press Enter or click Ask Mave.

Approve the plan

Mave replies with a plan card: what she'll build, what she'll run, and what it will cost in credits — before anything is charged. Read it. If it looks right, click Approve. If not, just tell her what to change ("make the audience urban only", "use 100 people") — she'll re-plan.

Watch it run

You'll see live progress: the audience being built, then the study fielding. A normal study takes 1–3 minutes. You can leave — the run continues, and the conversation stays in your sidebar.

Read the result

The result card shows:

  • The headline — e.g. "Variant A wins 64% to 36%, driven by the no-subscription angle."
  • The shares — calculated from recorded synthetic responses.
  • The grounding badge — how real this is (see below).
  • Quotes — verbatim synthetic respondent language you can use as creative hypotheses.

Hover the badge: category-modeled means the audience is built from category knowledge. Treat the direction as signal, the exact digits as directional.

Ask the follow-up (this is where it gets good)

Don't start over. In the same chat, keep going:

"Why did the losers reject Variant B?" "Run the same test but only with people who currently pay for a subscription." "Turn this into a one-page summary I can send my client."

Every follow-up uses everything that came before.

If the run seems stuck

Runs longer than ~5 minutes for a simple study usually mean a big panel or a many-question study. Check the progress list in the conversation — each completed step shows a timestamp. Still stuck? Type "what's the status?" — Mave answers honestly.

API power workflows you can run from Mave

The best API-level operations explained as human prompts: compare, branch, export, track, and automate.

Walkthrough: run a focus group

From picking an audience to reading the room — every step.

On this page

Open MaveType your question like a humanApprove the planWatch it runRead the resultAsk the follow-up (this is where it gets good)