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

Everyday decisions

Think through a relationship decision

Organize emotions, recurring patterns, needs, safety, repair attempts, and future compatibility without pretending AI replaces human support.

The basic idea

Relationship questions often arrive as a long account of frustration. That context can be useful, but the council should distinguish a bad incident from a repeated pattern, identify each person’s needs, and avoid diagnosing people it has never assessed.

Example

Ask whether to continue, pause, or end a relationship after describing the recurring conflict, efforts at repair, shared commitments, boundaries, and what a workable relationship would require.

How to do it

  1. 1

    Describe specific behaviors and patterns rather than attaching clinical labels.

  2. 2

    Name your nonnegotiable needs, boundaries, and evidence of change or non-change.

  3. 3

    Ask models to consider repair, separation, counseling, and a time-bounded evaluation where appropriate.

  4. 4

    Use the map to distinguish emotional pain, practical entanglement, compatibility, trust, and safety.

What to watch for

  • AI cannot know the other person’s private intentions.
  • If there is abuse, coercion, stalking, or immediate danger, prioritize qualified local help and safety planning.
  • Do not share intimate information you do not have permission to disclose.

What a useful result looks like

The result can widen the options and clarify boundaries, but the user remains responsible for the decision and for obtaining human support when needed.