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

Research design

Use randomization, replications, and compute matching

Set assignment units, reproducible seeds, repeated trials, blocking, and fair compute constraints across conditions.

The basic idea

Stochastic model outputs and heterogeneous item difficulty create variance. Replication estimates that variance; random assignment prevents systematic allocation differences; blocking can improve balance; compute matching keeps a treatment from winning merely because it used more resources.

Example

Randomize benchmark items equally across arms within category blocks, repeat each item-condition cell, and match estimated provider cost or model calls.

How to do it

  1. 1

    Choose whether assignment occurs by item, participant, or entire run.

  2. 2

    Save a seed and allocation rule that another analyst can reproduce.

  3. 3

    Select repetitions based on the estimand and expected variance, not a convenient round number.

  4. 4

    Choose whether to match calls, turns, token budgets, or estimated cost and document what remains unmatched.

What to watch for

  • Repeated calls are not human participants and should not be described as such.
  • Blocking variables must be measured before assignment.
  • More replications can become expensive quickly, especially with option-order variants.

What a useful result looks like

These controls make treatment comparisons more stable, auditable, and resistant to accidental compute advantages.