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

Work and teams

Map a stakeholder disagreement

Use models to represent competing positions, uncover shared assumptions, and identify evidence that could move a dispute.

The basic idea

The goal is not to simulate people or declare a winner. It is to represent the strongest version of each documented position, locate the actual points of disagreement, and separate value conflicts from factual uncertainty.

Example

A faculty group may disagree about program growth because members weight prestige, teaching load, student access, finances, and research capacity differently.

How to do it

  1. 1

    Describe each position in neutral language and identify the evidence its supporters cite.

  2. 2

    Assign advocates to steelman different positions and a fact-checker to isolate empirical claims.

  3. 3

    Use blinded peer identities when model prestige could influence later responses.

  4. 4

    Ask the chair for shared ground, irreducible value differences, and a decision procedure.

What to watch for

  • Do not attribute motives that stakeholders have not expressed.
  • A model-generated compromise may satisfy nobody if constraints are missing.
  • Share the map with real stakeholders for correction before acting on it.

What a useful result looks like

The deliberation should make the disagreement more precise and identify whether more evidence, negotiation, or legitimate authority is needed.