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

Benchmarks and results

Run PolicyBench for public-policy reasoning

Study policy understanding and application using the preserved U.S. PolicyBench configuration and structured facets.

The basic idea

PolicyBench can test whether a Council effect extends beyond hard science into policy reasoning. The imported source preserves jurisdiction, policy name, question type, classification, explanation, reasoning level, original ID, and provenance.

Example

Focus a primary analysis on U.S. understanding and application items while retaining memorization items in the raw authoritative dataset for transparent secondary work.

How to do it

  1. 1

    Confirm that PolicyBench is marked cleared for the intended use before execution.

  2. 2

    Select the U.S. jurisdiction and the prespecified understanding or application levels.

  3. 3

    Choose item count, sampling, seed, protocol arm, and replications.

  4. 4

    Report malformed and ineligible source records in the flow diagram rather than silently dropping them.

What to watch for

  • License review status controls whether the dataset can be launched in the product.
  • Original numeric IDs restart by level; composite IDs prevent collisions while preserving the source ID.
  • Items without valid answer keys cannot enter objective scoring.

What a useful result looks like

The benchmark supports an auditable cross-domain test of heterogeneous deliberation on public-policy questions.