Structured Courses

PMs, growth teams, and analysts turning product ideas into reliable evidence.

Artifact

Experiment design memo plus review-board-ready readout.

Use case

Decide whether a product change should ship, iterate, rerun, or stop.

1. 1Experimental Design
2. 2A/B Testing at Scale
3. 3Bayesian Statistics in Practice

Data scientists and researchers making causal claims from messy product or operations data.

Artifact

Identification memo with diagnostics, sensitivity plan, and interpretation limits.

Use case

Judge whether observational evidence is decision-grade or needs a new experiment.

1. 1Causal Inference
2. 2Experimental Design
3. 3Bayesian Statistics in Practice

ML engineers and agent-system builders designing policies that learn safely.

Artifact

Offline policy improvement plan with reward, guardrails, OPE, and rollout criteria.

Use case

Improve a logged decision policy without deploying an unsupported optimizer.

1. 1Reinforcement Learning
2. 2Causal Inference
3. 3A/B Testing at Scale

Leaders building an organization-wide experimentation and decision-review capability.

Artifact

Operating model for risk-tiered experiments, metric contracts, and decision memory.

Use case

Scale learning velocity while keeping evidence, ethics, and business guardrails intact.

1. 1A/B Testing at Scale
2. 2Experimental Design
3. 3Causal Inference

Backend and ML engineers integrating adaptive experiments into applications or pipelines.

Artifact

Working experiment integration with assignment, observation, stopping rule, and decision framework.

Use case

Ship a production-grade experiment with bandit or A/B allocation and Bayesian analysis.

1. 1Reinforce OS
2. 2Experimental Design
3. 3Bayesian Statistics in Practice