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

Create and read 95% confidence-interval plots

Turn selected outcomes into editable whisker plots and interpret estimates, uncertainty, titles, notes, and labels responsibly.

The basic idea

A point estimate describes the observed difference; a 95% confidence interval describes uncertainty under the analysis assumptions. The figure should show the outcome, unit, conditions, sample definition, and whether the interval is paired, clustered, or otherwise adjusted.

Example

Plot mean quality-adjusted considerations for deliberation and reconsideration with condition labels, sample sizes, editable notes, and a clearly named y-axis.

How to do it

  1. 1

    Select the dependent variable and conditions to display.

  2. 2

    Choose the estimand and interval method appropriate to the assignment and repeated-measures structure.

  3. 3

    Edit the title, subtitle, axis labels, condition names, and notes in plain language.

  4. 4

    Check the plotted values against the underlying table before exporting or publishing.

What to watch for

  • Overlapping intervals do not directly test the difference between two conditions.
  • A narrow interval can still center on a biased estimate.
  • Exploratory figures should not be relabeled as preregistered confirmatory outcomes.

What a useful result looks like

The editable figure communicates effect size and uncertainty without forcing readers to reconstruct the result from prose.