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

Research design

Duplicate and pilot an experiment

Copy a complete design safely, test one benchmark item end to end, and scale only after the path passes.

The basic idea

A copied experiment should preserve the design while starting with no participants or observations. A one-item pilot then checks the real protocol, providers, scoring, storage, and billing boundary at minimal cost before a larger reservation is made.

Example

Duplicate a preregistration draft, alter one treatment arm, then run one filtered PolicyBench item before launching the planned sample.

How to do it

  1. 1

    Open the source experiment and select Duplicate full design.

  2. 2

    Review the new draft: protocol, outcomes, benchmark, models, and participant design are copied, but locks and collected data are not.

  3. 3

    Choose the intended arm, subset, and scoring mode, then select Run 1-item pilot.

  4. 4

    Inspect every model attempt, the pass or attention-needed message, reserved estimate, provider cost, and final charge before scaling.

What to watch for

  • Collaborators, participant links, sessions, responses, and prior runs never carry into the copy.
  • A pilot validates the execution path; one item cannot estimate a treatment effect or dataset accuracy reliably.
  • Human-turn conditions require participant testing rather than an unattended benchmark pilot.

What a useful result looks like

Researchers can create design variants quickly and catch provider, scoring, persistence, or billing failures before committing a large sample or budget.