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

Benchmarks and results

Run CogToM for social cognition

Test beliefs, intentions, emotions, knowledge states, deception, and perspective-taking with canonical or five-variant scoring.

The basic idea

CogToM measures objectively scored Theory of Mind and social-cognition reasoning. The canonical item preserves its original option order; the official robustness procedure evaluates five pinned option-order variants as a consistency group.

Example

Compare deliberation and reconsideration on identical English items, then treat five-variant consistency as a prespecified robustness analysis rather than silently multiplying observations.

How to do it

  1. 1

    Select the English CogToM benchmark and choose category or subcategory facets if needed.

  2. 2

    Decide before execution between canonical scoring and the official five-variant consistency procedure.

  3. 3

    When using variants, budget for five evaluations per canonical item and score at the grouped-item level.

  4. 4

    Preserve original scene, question, answer, options, category, subcategory, IDs, and repository revision.

What to watch for

  • Option permutations are repeated measures of one item, not five independent questions.
  • Models may be sensitive to option position even when underlying reasoning is unchanged.
  • Public availability should be discussed as a possible contamination limitation.

What a useful result looks like

CogToM extends Council evaluation to reasoning about other minds while preserving the official benchmark’s robustness design.