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

Behavioral games

Run a Stag Hunt Game

Study coordination between a high-value joint outcome and a safer individual action.

The basic idea

Stag Hunt represents assurance and strategic coordination: mutual stag choice gives the largest coordinated payoff, while hare is safer when a player doubts the other will coordinate. The payoff matrix should preserve both the reward for coordination and the relative security of hare.

Example

Compare whether models and humans coordinate on stag after no communication, selected prior messages, or a deliberative exchange.

How to do it

  1. 1

    Assign two seats and set the stag, hare, and mismatch payoffs.

  2. 2

    Check that mutual stag is attractive while hare remains the safer response to expected noncoordination.

  3. 3

    Choose identity, communication, repetition, and feedback conditions deliberately.

  4. 4

    Report action pairs, successful coordination, payoffs, and transitions between strategies across rounds.

What to watch for

  • Different payoff matrices can shift risk dominance.
  • Communication turns the study into a communication-and-coordination treatment.
  • Repeated games can reflect learning or reputation rather than one-shot assurance.

What a useful result looks like

The result distinguishes successful high-payoff coordination, safe-action coordination, and failed coordination for each configured actor pair.