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

Participant studies

Run a text, image, or video stimulus experiment

Show participants standardized communication material before assigning solo-AI, council, human–AI, or human interaction conditions.

The basic idea

Traditional communication experiments begin with a controlled stimulus and measure responses after exposure. The stimulus, media description, interaction task, condition assignment, transcript, exposure timing, and questionnaire should be preserved together so treatment delivery remains auditable.

Example

Show everyone the same campaign message with a photograph or YouTube advertisement, then randomly assign them to discuss it with one model, an AI council, a human–AI chain, or a human-only condition before measuring attitude change.

How to do it

  1. 1

    Enable the shared stimulus and add the heading, text, optional HTTPS image, or YouTube link.

  2. 2

    Provide accessible image text and a neutral media description or verified transcript; model conditions receive this text context because they do not watch the embedded player.

  3. 3

    Add the standardized interaction task and configure the four desired condition templates in the Guided Condition Builder.

  4. 4

    Preview the participant path, lock the protocol, run a small test, and verify stimulus-opened, stimulus-completed, exposure time, assignment, transcript, and questionnaire fields in the export.

What to watch for

  • A media description can introduce framing that is absent from the original stimulus.
  • Remote images disclose a participant's network request to the image host; use a controlled HTTPS host and avoid tracking URLs.
  • YouTube playback, advertisements, captions, region restrictions, and recommendation overlays can vary across participants.

What a useful result looks like

Each participant receives the same versioned material, an auditable randomly assigned interaction, and the planned outcomes, with exposure timing available for delivery and attrition checks.