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

Design an LLM deliberation experiment

Move from an interesting council demonstration to a reproducible comparison with explicit conditions and outcomes.

The basic idea

A credible experiment specifies what varies, what is held constant, how outcomes are scored, what unit is assigned, and how failures are handled before results are inspected. The protocol builder records those choices in the experiment.

Example

Compare heterogeneous deliberation with matched homogeneous reconsideration on the same benchmark items, calls, prompts, token budgets, and scoring rules.

How to do it

  1. 1

    Write the theoretical claim and the contrast needed to test it.

  2. 2

    Define one primary outcome and label exploratory outcomes as secondary.

  3. 3

    Create named conditions with explicit model rosters, turns, information sharing, aggregation, parameters, and failure rules.

  4. 4

    Choose assignment, repetitions, seeds, compute matching, and stopping rules, then lock the protocol before execution.

What to watch for

  • Changing the protocol after seeing outcomes undermines confirmatory interpretation.
  • Equal rounds do not necessarily mean equal calls, tokens, or cost.
  • Public benchmarks may have training contamination, which should be documented rather than hidden by rewriting items.

What a useful result looks like

The experiment workspace becomes a reproducible specification rather than a collection of informal prompts.