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

Build an independent model ensemble

Collect several model answers without peer exposure, then aggregate them by vote, confidence, judge, or no aggregation.

The basic idea

An independent ensemble is different from deliberation: models do not see one another before answering. It is a useful product configuration when social influence is undesirable and a useful experimental arm when reviewers ask whether diversity alone explains the effect.

Example

Three provider-diverse models answer the same item independently, after which a prespecified majority vote or blinded judge produces the final answer.

How to do it

  1. 1

    Choose the independent ensemble template.

  2. 2

    Keep information sharing set to none for every answer-producing turn.

  3. 3

    Choose an aggregation rule that matches the answer format and research claim.

  4. 4

    Record ties, missing answers, confidence use, and judge identity in advance.

What to watch for

  • A judge adds another model call and can introduce its own bias.
  • Majority vote is poorly defined for open-ended answers without normalization.
  • Do not describe an ensemble as deliberation when no model sees another’s contribution.

What a useful result looks like

The ensemble supplies a clear baseline for the value of roster diversity without interaction.