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

Compare deliberation with homogeneous reconsideration

Design the key comparison between models exchanging information and repeated same-model reasoning under matched exposure.

The basic idea

Homogeneous reconsideration addresses the objection that improvement might come from extra inference rather than cross-model exchange. Separate instances or turns of the same model receive matched opportunities while the heterogeneous arm contains distinct models.

Example

Match both arms on items, number of scheduled calls, visible history, output limits, aggregation, and scoring, changing only whether the roster is heterogeneous or repeated same-model instances.

How to do it

  1. 1

    Create the deliberation arm with distinct model providers.

  2. 2

    Duplicate the schedule and replace the control roster with repeated slots of the same model.

  3. 3

    Match information exposure and ensure that reconsideration is not accidentally denied the context available to deliberation.

  4. 4

    Predefine whether conclusions concern one focal model, several model families, or an average treatment effect.

What to watch for

  • One homogeneous model is not evidence about every model family.
  • Deterministic settings can make repeated instances less independent.
  • Aggregation must be matched or explicitly treated as another factor.

What a useful result looks like

The comparison helps distinguish the value of heterogeneous exchange from the value of simply spending more computation.