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.

Intelligence workspace

One place for comparisons, time slices, persistent personas, stress tests, trackers, Autopilot, current signals, and verified deliverables.

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

Use the Intelligence workspace

Open Intelligence and complete one full comparison from selection to decision.

Simulation onlyNothing is saved or charged
1
Step 1 of 7Open Intelligence

Choose Intelligence 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 surfacecompareFollow the highlighted action
Recent workspace activityStatus
Audience comparisonReady to review
Customer interview evidenceGrounded
Campaign pre-flightDraft
  1. 1
    Open IntelligenceChoose Intelligence from the sidebar.
  2. 2
    Choose CompareOpen the audience comparison workspace.
  3. 3
    Choose Audience ASelect the first named workspace audience.
  4. 4
    Choose Audience BSelect a different audience.
  5. 5
    Ask one shared questionWrite one decision-shaped question for both audiences.
  6. 6
    Run the comparisonStart the local comparison.
  7. 7
    Read convergence and splitOpen the overlap, divergence, and next-move panels.

Open Intelligence in the main navigation. The left rail moves from quick, bounded work to advanced recurring systems.

CapabilityStart whenYou get
Compare audiencesTwo segments may need different treatmentShared themes, polarizing themes, computed similarity and gaps
Point-in-time audienceThe historical moment changes the answerA dated audience brief with exclusions and assumptions
Persistent personasYou need longitudinal interviewsA named synthetic person with an explicit memory digest
Branch + flip testA conclusion feels fragileA before/after movement verdict computed from real responses
Track a signalYou need to know when a result movesScheduled waves and threshold alerts
Overnight researcherUseful uncertainty is piling upCapped background research queued for review
Current signalsReal-world context might change the decisionTimestamped events plus honest freshness/confidence states
Evidence + deliverablesWork must leave the chatDossiers, exports, and self-verified PDFs

The honesty rule

Fresh facts, synthetic responses, and computed results are different evidence classes. Mavera keeps them separate. A model can explain a movement; code computes the movement.