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

Work and teams

Run a decision pre-mortem

Ask an AI council to imagine a failed plan, identify plausible causes, and convert them into mitigations and stop rules.

The basic idea

A pre-mortem temporarily assumes the plan failed and works backward. Multiple models are useful because failure modes are often distributed across operational, financial, human, legal, and reputational dimensions.

Example

Before launching a product, ask why adoption, reliability, unit economics, compliance, or customer trust might fail despite an initially promising plan.

How to do it

  1. 1

    Describe the plan, objective, deadline, and assumptions.

  2. 2

    Assign critics to different failure domains rather than asking every model for the same generic risk list.

  3. 3

    Require each risk to include an early warning sign, likelihood rationale, impact, and mitigation.

  4. 4

    Ask the chair to distinguish launch blockers from risks that can be monitored after launch.

What to watch for

  • Do not count imaginative scenarios as evidence that failure is likely.
  • Avoid a risk list so long that priorities disappear.
  • Assign a human owner and monitoring trigger to material mitigations.

What a useful result looks like

A pre-mortem should produce a shorter, prioritized risk register and concrete signals for changing or stopping the plan.