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

Choose Likert, slider, and questionnaire formats

Match response controls to the construct being measured and produce outputs that remain interpretable.

The basic idea

The control should reflect the measurement claim. Likert choices work well for labeled ordered judgments; sliders allow finer-grained responses but can imply precision that participants do not possess. Open text captures explanation but requires a coding plan.

Example

Measure agreement on a five- or seven-point labeled Likert scale, confidence on a bounded 0–100 slider with visible endpoints, and an optional open-text explanation.

How to do it

  1. 1

    Name the construct before choosing the control.

  2. 2

    For Likert items, provide balanced ordered labels and keep direction consistent.

  3. 3

    For sliders, show the current value, meaningful endpoints, range, and step size.

  4. 4

    Preview keyboard, touch, required-state, and exported-value behavior before publishing.

What to watch for

  • A 0–100 slider does not automatically provide ratio-scale measurement.
  • Avoid double-barreled questions that ask about two things at once.
  • Preserve item wording, response labels, order, and coding in the study manifest.

What a useful result looks like

Each response has an understandable participant-facing control and a documented numeric or textual representation suitable for the planned analysis.