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

Research design

Define outcomes and dependent variables

Use the Outcome Builder to define what will be measured, when, at what unit, and with which scoring rule.

The basic idea

An outcome is not merely a label such as quality. It needs an observable unit, scale, direction, aggregation, missing-data rule, scoring method, timing, and rubric. One outcome should be explicitly primary.

Example

Use exact-match accuracy as the primary outcome for a benchmark study and decision-space breadth or quality-adjusted considerations as prespecified secondary outcomes.

How to do it

  1. 1

    Choose the construct the study is actually intended to explain.

  2. 2

    Select the unit: answer, item, model, round, run, or participant.

  3. 3

    Define the scale, direction, aggregation, missing-data policy, scorer, and measurement timing.

  4. 4

    Write a rubric specific enough that an independent analyst could implement it, then lock the outcome manifest.

What to watch for

  • Do not switch the primary outcome after inspecting results.
  • An LLM-scored outcome needs validation and uncertainty analysis.
  • A count of considerations measures breadth, not necessarily truth or benefit.

What a useful result looks like

The Outcome Builder creates a machine-readable definition that can flow into scoring, figures, and the experiment record.