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

Getting started

Estimate and control LLM costs

Understand free estimates, prepaid credits, retry-aware reservations, final token charges, and result release.

The basic idea

AI Deliberator calculates an estimate without calling a model. The estimate uses model prices, expected input and output tokens, scheduled calls, repetitions, aggregation, mapping, and configured retry exposure. Actual charges settle from recorded usage.

Example

A short three-model decision can cost only a few cents, while a multi-item benchmark with repeated conditions can require many more credits. The builder shows the difference before launch.

How to do it

  1. 1

    Choose the models and protocol before treating the estimate as meaningful.

  2. 2

    Review estimated calls, provider cost, markup, and the displayed customer-credit requirement.

  3. 3

    Reduce turns, output limits, repetitions, variants, or expensive models when the estimate is too high.

  4. 4

    Keep enough prepaid balance to cover the estimate; if actual usage creates a balance due, results remain withheld until the balance is restored.

What to watch for

  • Estimates are planning ranges, not fixed quotes.
  • Retries are reserved conservatively but unused capacity is not charged as actual usage.
  • Collaborator activity is billed to the original experiment owner.

What a useful result looks like

The cost controls let you scale from inexpensive personal questions to preregistered research without launching an open-ended provider bill.