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

Getting started

How to choose models for an AI council

Select a useful mix of OpenAI, Gemini, Claude, Grok, and DeepSeek models without adding diversity for its own sake.

The basic idea

Model diversity is useful when different training, reasoning styles, or provider families can surface different assumptions. More models also mean more calls and context, so the best roster is the smallest group that supplies meaningful contrast.

Example

For a difficult policy question, use three models from different providers. For a homogeneous reconsideration control, repeat separate instances of the same model instead.

How to do it

  1. 1

    Start with three distinct provider families for a general-purpose deliberation.

  2. 2

    Match model capability to the stakes and complexity of the question rather than automatically choosing the most expensive roster.

  3. 3

    Use named roles such as analyst, critic, and fact-checker when you need functional diversity in addition to model diversity.

  4. 4

    Check the free estimate before launching; model choice, context length, turns, and output limits all affect price.

What to watch for

  • Five similar models do not guarantee five independent perspectives.
  • A cheaper model can be useful as a critic or verifier even when a stronger model chairs the result.
  • Provider availability and supported parameters can change.

What a useful result looks like

A deliberate roster balances perspective, capability, latency, and cost while keeping the comparison interpretable.