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

Select benchmark questions and subsets

Choose item counts, categories, reasoning levels, jurisdictions, sampling methods, and seeds without changing source questions.

The basic idea

Subset selection should follow the scientific question. AI Deliberator preserves authoritative source items and exposes structured facets so a study can focus on a domain without silently rewriting or deleting benchmark content.

Example

Sample only chemistry items from a broad benchmark, or select PolicyBench understanding and application items from the U.S. configuration.

How to do it

  1. 1

    Select and save a cleared benchmark in the experiment.

  2. 2

    Choose relevant facets such as category, subcategory, level, jurisdiction, policy name, or question type.

  3. 3

    Set the requested item count and choose random, balanced, or all-item sampling.

  4. 4

    Save a seed, review the selected count and cost estimate, and preserve the resulting manifest.

What to watch for

  • Post-hoc subset selection can inflate apparent performance.
  • Small category samples have wide uncertainty.
  • Malformed or unscorable source records remain documented but are ineligible for execution.

What a useful result looks like

A pinned subset can be regenerated from source revision, facets, method, item count, and seed.