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

Participant studies

Measure human–AI advice reliance

Measure whether people retain or revise an answer after solo AI, council, hybrid, or human advice.

The basic idea

Advice reliance is more informative when the participant commits to an initial answer and confidence before exposure. A matched revised answer then reveals switching, confidence change, and—when an answer key exists—whether revision improved accuracy. Self-reported influence complements but does not replace behavioral change.

Example

Ask for an initial policy classification and confidence, show the assigned deliberative or non-deliberative interaction, then repeat the classification and ask how much the interaction influenced the final answer.

How to do it

  1. 1

    Write one answerable judgment prompt and choose open, multiple-choice, or bounded numeric response.

  2. 2

    Add an answer key only for objectively scorable tasks.

  3. 3

    Choose whether a rationale is necessary and consider the extra burden it creates.

  4. 4

    Prespecify switching, confidence change, correctness change, or influence as outcomes before collecting data.

What to watch for

  • A changed answer is not automatically a better answer.
  • Correctness change requires a defensible answer key.
  • The AI transcript should be retained for later coding of advice content and agreement.

What a useful result looks like

Each participant has paired initial and revised judgments, confidence, response time, influence, optional rationale, and derived arm-level summaries.