Mavera DocsOperator's Guide
Checking your Mavera sessionLoading workspace audiences and API keys…
Checking…Use or share this pageSend the page itself, print it, or open its complete context in your AI workspace.
Intermediate: turn inputs into decisions
Use your files, evidence settings, comparisons, and reusable workflows to stop starting from scratch.
Interactive product walkthrough
Turn work into a reusable workflow
Describe the repeatable job, inspect the plan and cost, then save it.
Simulation onlyNothing is saved or charged
1
Step 1 of 6Open Workflows
Choose Workflows from the sidebar.
Mavera workspace
Good afternoon
Choose a surface from the sidebar to begin.
Demo workspace0 actions completed
Recent workspace activityStatus
Audience comparisonReady to review
Customer interview evidenceGrounded
Campaign pre-flightDraft
- 1Open WorkflowsChoose Workflows from the sidebar.
- 2Start a workflowCreate a workflow from a plain-language brief.
- 3Describe the recipeExplain the repeatable job and its required output.
- 4Build the planTurn the brief into ordered steps and gates.
- 5Review cost and stepsInspect inputs, estimated credits, and approval points.
- 6Save the workflowSave the local recipe so it can be reused.
At this level you stop asking isolated questions. You create a chain: real inputs → audience → qualitative read → quantitative test → deliverable.
The intermediate loop
| Move | Where | Why it changes quality |
|---|---|---|
| Ingest customer material | Ingest | Turns transcripts, tickets, reviews, or CSVs into grounded evidence and audiences |
| Control the lens | Mave → ◈ Lens | Makes time, evidence, and output expectations explicit on the request |
| Compare audiences | Audiences / API | Shows where segments diverge instead of averaging everyone together |
| Branch an insight | Insight tools | Tests whether a conclusion survives a changed assumption |
| Save a workflow or skill | Workflows / Skills | Lets the team run the same good process again |
Use the Research Lens
In the Mave composer, open ◈ Lens before you send:
- Time: Point in time — ask how a group would have behaved before a category change, launch, or historical event.
- Evidence: My evidence first — privilege your uploaded files and Context. Mave flags what is modeled.
- Evidence: Current sources — separates dated, cited real-world facts from simulated audience responses.
- Output: Decision brief — ends with a recommendation, caveats, and cheapest next step.
- Output: Client deliverable — ends with a report-shaped artifact.
Prompt: create an audience from a slice in time
Prompt2 fields left
Research Lens: Time = Point in time. Build an audience of [who] as they existed in [month/year or period]. Use only the category conditions, media environment, prices, and customer expectations available at that time. State every historical assumption, separate sourced facts from modeled assumptions, and tell me what present-day knowledge you deliberately excluded.
Unfilled variables remain in brackets.
Prompt: turn customer files into a decision
Prompt1 field left
I uploaded a completed customer study. Extract a source-quoted dossier, identify the most important tension, and propose a separate synthetic comparison for [decision]. Keep the original human evidence and the new modeled responses clearly labeled.
Unfilled variables remain in brackets.