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

Getting started

Use the Consideration Map

Read distinct considerations, supporting evidence, materiality, disagreement, and verification status after a council run.

The basic idea

The map measures the decision space discussed by the council. It extracts distinct, decision-relevant points and anchors them to transcript evidence. It does not prove that every point is true or that a larger number automatically means a better decision.

Example

A career decision map might separate compensation, commute, term length, staff capability, family timing, reputation, and exit options rather than blending them into one generic pros-and-cons paragraph.

How to do it

  1. 1

    Begin with the decision frame so you know what supports and opposes refer to.

  2. 2

    Scan high-materiality points first, then inspect disputed or single-source points.

  3. 3

    Open the evidence quotation and verify that the cited model and turn actually raised the point.

  4. 4

    Use missing or weakly supported areas to formulate the next question rather than treating the map as a verdict.

What to watch for

  • More considerations can reflect verbosity rather than breadth, which is why duplicates and unsupported points are filtered.
  • Corroboration means multiple sources raised a point; it is not independent factual verification.
  • A map can omit nuance when the underlying transcript is ambiguous.

What a useful result looks like

The map turns a long conversation into an auditable inventory of what was considered, contested, and left unresolved.