Instructor and workshop mode

Run live training from the DoOperator Education course kits

Facilitation guides, worked examples, rubrics, and team exercises for teaching experiments, causal inference, Bayesian workflow, A/B testing, and adaptive policy systems.

Teach judgment by making artifacts criticizable

Every workshop should end with a concrete artifact and a review standard. The point is not to cover every method; it is to help learners produce work that another person can inspect, challenge, and improve.

  1. Frame

    Choose one decision and name the artifact the group will produce.

  2. Draft

    Teams complete the core worksheet: estimand, model, policy, or review-board design.

  3. Critique

    Swap artifacts and identify invalidation risks, weak assumptions, and missing guardrails.

  4. Revise

    Teams update the artifact and write the decision implication in plain language.

  5. Archive

    Save the artifact, critique, and unresolved questions as decision memory.

Five ready-to-run training modules

Each guide includes 60-minute and 90-minute agendas, discussion prompts, facilitator notes, common failure modes, and review standards.

Workshop

Experimental Design

PMs, analysts, researchers, and operators turning ideas into review-ready experiments.

Artifact
Experiment design memo
Format
60 or 90 minutes
Workshop

Causal Inference

Analysts and product teams making causal claims from observational data.

Artifact
Identification memo
Format
60 or 90 minutes
Workshop

Reinforcement Learning

ML engineers, data scientists, and operators designing adaptive policies.

Artifact
Offline policy improvement plan
Format
60 or 90 minutes
Workshop

Bayesian Statistics

Analysts, researchers, and decision-makers using models under uncertainty.

Artifact
Model criticism report
Format
60 or 90 minutes
Workshop

A/B Testing at Scale

Experiment platform teams, growth leaders, PMs, and analysts running many tests.

Artifact
Experiment review-board operating model
Format
60 or 90 minutes

Use the course kits as decision-memory practice

A simple cohort can run across five sessions: experiment design, causal identification, Bayesian model criticism, adaptive-policy safety, and experiment governance. Learners leave with a portfolio of artifacts instead of a pile of notes.

Run cohorts without waiting for custom software

These templates give facilitators a lightweight operating system for teams, submissions, reviews, revisions, and decision-memory archives.

Template

Cohort workspace template

Shared roster, session plan, artifact tracker, review norms, and completion standard for multi-session cohorts.

Open template →
Template

Submission and review workflow

Lightweight intake, triage, peer review, revision, and archive process for live workshops.

Open template →