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

Continue a decision with follow-up questions

Update a council recommendation when you learn new facts without starting the reasoning from scratch.

The basic idea

A follow-up gives the next council the prior question and synthesis plus your new information. This makes the sequence cumulative while still asking models to identify what changed rather than simply repeat the first answer.

Example

After a council weighs a department-chair role, add that the term is six years, the staff is capable, and your children are leaving for college, then ask how those facts change the recommendation.

How to do it

  1. 1

    Open the completed, released run you want to continue.

  2. 2

    State only the new facts, corrections, or narrower question that should modify the earlier analysis.

  3. 3

    Run the same condition for continuity or intentionally choose another saved condition when comparison is the goal.

  4. 4

    Compare the new synthesis and map with the previous run, especially points marked new, carried forward, or revised.

What to watch for

  • Correct factual errors explicitly instead of assuming the council will infer the correction.
  • A follow-up is a new paid run because models receive and analyze additional context.
  • Do not keep extending a thread when a fundamentally different decision deserves a new experiment.

What a useful result looks like

Follow-ups convert one-off advice into an evolving decision record that responds to evidence and changing circumstances.