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

Run a human deliberation condition

Insert live human contributors into an experimental conversation and compare human deliberation with AI conditions.

The basic idea

A human condition can test whether an observed effect is specific to model exchange or reflects deliberation more generally. Human timing, dropout, identity, compensation, and message visibility introduce design choices that do not arise in an all-model run.

Example

Compare a three-person human discussion with a three-model council using the same question, turn budget, visible history, outcome questionnaire, and stopping rule.

How to do it

  1. 1

    Create human seats and specify their order, visibility, timing, and required turns.

  2. 2

    Match exposure across arms on the dimension relevant to the hypothesis while documenting unavoidable differences.

  3. 3

    Distribute private seat links securely and test waiting, reconnecting, and completion behavior.

  4. 4

    Prespecify how timeouts, missing turns, withdrawals, and incomplete groups are analyzed.

What to watch for

  • Humans cannot be treated as interchangeable API calls.
  • Names, free text, and live presence may create identifiable research data.
  • A stalled participant can block a sequential chain unless a timeout rule exists.

What a useful result looks like

Human messages, timing, seat assignment, completion, and downstream responses are preserved in a condition that can be compared transparently with model-based arms.