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

Configure experimental conditions and independent variables

Control model rosters, turns, information sharing, order, roles, prompts, parameters, aggregation, and failure handling.

The basic idea

The independent variable should be the smallest meaningful difference between conditions. The guided protocol builder makes each condition explicit so deliberation is not confounded with extra calls, different models, longer prompts, or a stronger aggregator.

Example

Create a heterogeneous deliberation arm and duplicate it as a control, then change only the roster to repeated instances of one model while matching turns and token limits.

How to do it

  1. 1

    Name each arm for the scientific contrast it represents.

  2. 2

    Specify every model slot, including repeated instances of the same model and any functional role.

  3. 3

    Build the exact turn schedule, information visibility, speaking order, and identity visibility.

  4. 4

    Set prompts, parameters, aggregation, repetitions, assignment, compute matching, stopping, retries, exclusion, and analysis policy.

What to watch for

  • A control that differs on several dimensions cannot isolate deliberation cleanly.
  • Provider settings are not universally supported, so record defaults and exceptions.
  • Large schedules and retries increase both cost exposure and failure probability.

What a useful result looks like

Each arm becomes an executable, hashed protocol that can be inspected before and after the run.