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

Behavioral games

Manage private game links, consent, and completion

Distribute one-time seat links safely, record consent, monitor progress, and handle incomplete sessions responsibly.

The basic idea

Each human seat uses a high-entropy bearer link: whoever has it can act as that seat. The original token is shown at creation and only its hash is stored, so researchers should copy links immediately, distribute them privately, and never place them in public recruitment materials.

Example

Launch a human–model Trust Game, copy the human seat link into a secure participant message, monitor the session without opening the link yourself, and export only after completion and credit settlement.

How to do it

  1. 1

    Review the full configuration before launch because the session record is intended to preserve the protocol.

  2. 2

    Copy all human seat links at creation and store the participant-to-seat mapping in an approved secure location.

  3. 3

    Tell participants what is recorded, how payoffs work, and that the on-screen checkbox does not replace study-specific consent review.

  4. 4

    Monitor active and completed sessions, apply prespecified timeout rules, and export the final record without publishing bearer links.

What to watch for

  • Opening a participant link can accidentally occupy or act through that seat.
  • Private links cannot be recovered from the database after leaving the creation screen.
  • Unfinished sessions expire, and human free text may require stronger data protections than model output.

What a useful result looks like

Every human reaches the correct seat through a private link, gives recorded consent, completes the intended actions, and leaves an auditable session without exposing credentials.