Track
Pick the main thing your team wants to learn. I can weave in related examples, but the quote is anchored on one track.
Context engineering and coding agents For software teams, data scientists, and technical leads. Applied AI
Practical workflows for using coding agents without losing taste, review discipline, or code ownership.
Usually covers prompt/context design, repo navigation, task decomposition, verification, and team norms.
Generative AI for work For teams or leaders who need a useful mental model. AI literacy
A grounded introduction to what modern AI systems are good at, where they fail, and how to use them in everyday work.
Can be technical or non-technical depending on the audience.
Bayesian marketing mix modeling For marketing, analytics, and measurement teams. MMM
A focused track on media contribution, saturation, adstock, uncertainty, calibration, and decision-making.
Best for teams that already work with marketing or business outcome data.
Python for analysis or software work From first notebooks to maintainable project structure. Python
For people moving from Excel, MATLAB, Stata, SAS, or ad hoc notebooks into Python.
Can focus on data analysis, package hygiene, testing, APIs, or modern developer workflows.
Building Bayesian statistical models with PyMC Probabilistic modeling from assumptions to diagnostics. PyMC
For analysts and scientists who want to build models, not just run procedures.
Usually includes generative thinking, priors, likelihoods, MCMC intuition, diagnostics, and PyMC workflows.
Applied data science and machine learning Modeling, validation, and useful predictions. Data science
A hands-on track around the full modeling loop: framing, data prep, baselines, supervised learning,
evaluation, leakage, interpretability, and communicating results.
Deep learning from intuition to implementation Neural networks as models you can reason about. Deep learning
Builds from simple models to neural networks with enough math to understand what is happening.
Can cover embeddings, optimization, architectures, and practical training/debugging.