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

Collaborate and preserve a reproducible experiment record

Invite collaborators, keep owner billing intact, lock manifests, preserve source revisions, and retain an auditable run history.

The basic idea

Collaboration should not blur responsibility. The experiment creator remains the billing owner; invited users gain access to that experiment but cannot silently become owners or rewrite locked scientific definitions.

Example

A principal investigator creates and funds a benchmark experiment, invites a collaborator to run it, and preserves the protocol, outcome definitions, benchmark revision, sample seed, attempts, scores, and costs.

How to do it

  1. 1

    Create the experiment under the account that should own billing and data controls.

  2. 2

    Invite collaborators by their verified account email.

  3. 3

    Review and lock outcome and protocol manifests before confirmatory execution.

  4. 4

    Record benchmark source revision, filters, seed, option-order mode, failures, exclusions, token use, and final scoring.

What to watch for

  • Collaborator runs charge the original owner’s balance.
  • Unlocking is recorded and must occur before a changed protocol can be saved.
  • Deleting an experiment removes its associated workspace record, so export needed evidence first.

What a useful result looks like

The resulting record makes it possible to explain who ran what, under which locked design, against which data revision, and at what cost.