AI Deliberator
Guides
How to use AI DeliberatorView all 58 guides

Getting started

Evaluate and export a Council runHow to ask a better decision questionHow to choose models for an AI councilRun your first AI councilUse the Consideration MapContinue a decision with follow-up questionsEstimate and control LLM costs

Everyday decisions

Use an AI council for a career changeEvaluate a leadership role or promotionThink through a relationship decisionDecide whether to move to a new cityCompare degrees, certificates, and education optionsAnalyze a major purchaseUse live evidence mode

Work and teams

Use deliberation for a business strategy decisionSupport a hiring decision responsiblyPrioritize a product roadmapRun a decision pre-mortemMap a stakeholder disagreementAnalyze a policy proposal

Research design

Duplicate and pilot an experimentDesign an LLM deliberation experimentDefine outcomes and dependent variablesConfigure experimental conditions and independent variablesCompare deliberation with homogeneous reconsiderationBuild an independent model ensembleUse randomization, replications, and compute matching

Participant studies

Build a participant interaction studyDesign pre- and post-interaction questionnairesChoose Likert, slider, and questionnaire formatsAdd attention, manipulation, and exposure checksAnalyze and export participant-study resultsBuild a composable experiment timelineMeasure human–AI advice relianceAdd process tracing and cognitive tasksRun a human deliberation conditionBuild a human–AI hybrid deliberation chainRun a text, image, or video stimulus experimentRun a learning and tutoring experimentPlan a powered participant studyMonitor recruitment, cost, and attrition

Behavioral games

Design a behavioral economics gameRun a Dictator GameRun an Ultimatum GameRun a Trust or Investment GameRun a Prisoner’s DilemmaRun a Public Goods GameRun a Stag Hunt GameConfigure game payoffs, incentives, and feedbackManage private game links, consent, and completion

Benchmarks and results

Select benchmark questions and subsetsRun MMLU-Pro in AI DeliberatorRun PolicyBench for public-policy reasoningRun CogToM for social cognitionCreate and read 95% confidence-interval plotsCollaborate and preserve a reproducible experiment recordAnalyze sentiment and quantitative text metricsCompare two Council runs
Workspace

Participant studies

Add process tracing and cognitive tasks

Collect interpretable timing and task-performance diagnostics without invasive surveillance.

The basic idea

Process data should be proportional to the scientific question. Stage duration, focus loss, response latency, trial accuracy, and false starts can test attention or cognitive load without capturing raw keystrokes, cursor trajectories, network identity, or device fingerprints.

Example

After an AI interaction, run five choice-reaction trials and compare browser-timed response latency and accuracy across council and solo-AI conditions while retaining focus-loss counts as a sensitivity diagnostic.

How to do it

  1. 1

    Choose simple reaction time when speed alone matters or choice reaction when speed and response selection matter.

  2. 2

    Use enough trials for a stable summary without making the study exhausting.

  3. 3

    Treat browser timing as client-recorded and inspect device or environment sensitivity in analysis.

  4. 4

    Export raw trials and report exclusions, trimming, and aggregation rules.

What to watch for

  • Browser and device differences add measurement noise.
  • Focus loss has many benign causes and should not be treated as proof of inattention.
  • Do not add invasive tracking merely because the browser permits it.

What a useful result looks like

The study exports trial-level latency, accuracy, false starts, stage events, and privacy-preserving focus diagnostics tied to participant and condition.