Self-paced course · Intermediate · 98 lessons

MODEL IT. PROMPT IT. SHIP IT.

SynergiZing ML & LLMs in R

Go from a tidymodels ML pipeline to a deployed, evaluated RAG app running inside Shiny, production-grade R and LLM systems you can ship.

An agent can produce an answer. This course is about proving the answer is grounded in your data.

Who it is for. R users who can write dplyr and want to build real ML and LLM systems. Comfort with the tidyverse is assumed; no prior ML or LLM experience needed.

$499 Enroll now One payment, lifetime access. Included with Membership.
Why take this

Three things you leave with.

A full tidymodels ML pipeline, trained, tuned, and evaluated

A production RAG pipeline with proper retrieval and evaluation

A deployed model API and a working Shiny + LLM chatbot

Not for you if
  • You've never written R, this assumes working tidyverse comfort
  • You want a Python course, this is R, end to end
  • You want theory and math derivations, this is applied and production-focused
  • You want a five-minute prompting tutorial, this builds ML foundations first, then goes deep on LLMs
Play with the data

Run the code, in your browser.

The chart on this page, drawn by code you can edit. R runs on webR and Python on Pyodide; nothing loads until you press Run, and nothing you type leaves the page.

This chart is the code's result. Run recomputes it in your browser.
Average wOBA at each age, weighted by plate appearances, with a 90% band and a fitted curve; the marker is the fitted peak.

Edit me: Set degree to 3 and run again. Does the peak move?

Data: Hitter aging (aging.csv). Simulated for practice by AthlyticZ (agents/sim_data.py, seed 20261109). License CC BY 4.0.

The code runs in your browser on webR or Pyodide; nothing you type leaves the page.

What you get

Everything that exists for this course, and nothing that does not.

  • Every lesson98 lessons in 21 sections, yours to keep
  • Project files and codeEvery notebook, dataset and finished build, to keep and adapt
Nic Crane
Your instructor Nic Crane

PhD · Consultant @ NC Data Labs

Teaches the course the way the work is done in the role above. The team page lists everything they teach here.

Also teaches Ask the Box Score Anything.

Christoph Scheuch
Your instructor Christoph Scheuch

PhD · Associate Researcher @ Humboldt-Universität zu Berlin

Teaches the course the way the work is done in the role above. The team page lists everything they teach here.

The problem

Language models are now part of the analytics stack, and the analyst who can combine them with classical ML in R, with evaluation, is rare.

Three decisions it teaches
  1. Where an LLM belongs in an R pipeline and where it does not
  2. How to build retrieval over your own documents and measure whether it works
  3. How to put an evaluation harness around anything a model produces

The artifact. An R pipeline that combines ML and LLM tools over sports data, with the evaluation that says how well it works.

Curriculum

98 lessons in 21 sections. Every lesson is yours to keep.

Foundations of AI in R2 items
  1. ML vs LLMs
  2. AI Ecosystem in R
From Viz to Models3 items
  1. Play by Play Data
  2. Exploration via Visualization
  3. Logistic Regression
Model Evaluation and Testing6 items
  1. Training and Test Sets
  2. Model Specifications and Workflows
  3. Making Predictions
  4. The Confusion Matrix and Basic Metrics
  5. Advanced Evaluation Techniques
  6. Overfitting and Test Evaluation
Resampling and Model Tuning6 items
  1. Introduction to Cross-Validation
  2. Working with Resampling Results
  3. Comparing Models with Cross-Validation
  4. Introduction to Hyperparameter Tuning
  5. Selecting and Finalizing Models
  6. Tuning Multiple Parameters
Predicting Continuous Outcomes4 items
  1. From Classification to Regression
  2. Linear Regression in Tidymodels
  3. Random Forests for Regressions
  4. Evaluating Regression Models
Preprocessing with Recipes4 items
  1. Why Preprocessing Matters
  2. Essential Recipe Steps
  3. Preparing and Applying Recipes
  4. Recipes in Workflows
Regularized Regressions4 items
  1. The Problem of Overfitting
  2. Ridge, Lasso, and Elastic Net
  3. Tuning Regularized Models
  4. Interpreting Regularized Coefficients
Workflow Sets for Model Comparison4 items
  1. The Challenge of Fair Model Comparison
  2. Creating Workflow Sets
  3. Tuning Workflow Sets
  4. Selecting and Finalizing the Best Workflow
Neural Networks4 items
  1. Why Neural Networks?
  2. Building Your First Neural Network
  3. Tuning Neural Networks
  4. Deeper Networks and Practical Considerations
Deployment of Machine Learning Models4 items
  1. Why Deployment Matters?
  2. Deploying Models with Vetiver
  3. Exporting Models with Orbital
  4. Monitoring and Maintaining Deployed Models
From ML to LLMs2 items
  1. A Gentle Introduction to LLMs
  2. Data Science Principles
Chat Basics4 items
  1. Introduction to LLMs
  2. Getting Started with Ellmer
  3. Conversations, Roles, and Tokens
  4. System Prompts
Prompt Engineering5 items
  1. Introduction to Prompt Engineering
  2. Adding Context and Instructions
  3. Handling Missing Data
  4. Fewshot Prompting
  5. Structuring and Storing Prompts
Structured Output4 items
  1. Introduction to Structured Output
  2. Extracting Data Frames
  3. Handling Missing Fields
  4. Batch Processing
Multimodal Input3 items
  1. Multimodal Input Introduction
  2. Hallucination with Plot Interpretation
  3. Extracting Data from Images
Model Selection5 items
  1. Model Selection Introduction
  2. Working with Proprietary Models
  3. Local Models Intro
  4. Running Local Models with Ollama
  5. Local Models in R
Tool Calling5 items
  1. Introduction to Tools
  2. Data Query Tools I
  3. Data Query Tools II
  4. Bio Retrieval Tools
  5. User Control Safety
NLP with Mall4 items
  1. Introduction to Mall
  2. Text Summarization
  3. Extracting Information
  4. Text Classification
Retrieval-Augmented Generation7 items
  1. Introducing RAG and Ragnar
  2. Document Processing
  3. Retrieval via BM25
  4. Retrieval via Embeddings
  5. Hybrid Retrieval
  6. Registering Retrieval Tools
  7. Context Augmentation
Model Evaluation with Vitals8 items
  1. Introduction to Evals
  2. Evaluation Data Sets
  3. Running First Evaluation
  4. Viewing Eval Results
  5. Comparing Models
  6. Statistical Comparison
  7. RAG Evaluation Design
  8. Running RAG Evaluation
LLM Apps10 items
  1. LLMs Data Exploration
  2. Text to SQL
  3. Querychat
  4. Querychat System Prompt
  5. Customizing Querychat
  6. Chatbots with Shinychat
  7. Tool Calling Part 1
  8. Tool Calling Part 2
  9. RAG in Chatbots
  10. Explaining Model Predictions
Curriculum

Every section, every lesson.

From the academy course record, in the order it is taught. The first section is open; the rest fold out.

98 lessons in 21 sections. Every lesson is yours to keep.

Foundations of AI in R2 items
  1. ML vs LLMs
  2. AI Ecosystem in R
From Viz to Models3 items
  1. Play by Play Data
  2. Exploration via Visualization
  3. Logistic Regression
Model Evaluation and Testing6 items
  1. Training and Test Sets
  2. Model Specifications and Workflows
  3. Making Predictions
  4. The Confusion Matrix and Basic Metrics
  5. Advanced Evaluation Techniques
  6. Overfitting and Test Evaluation
Resampling and Model Tuning6 items
  1. Introduction to Cross-Validation
  2. Working with Resampling Results
  3. Comparing Models with Cross-Validation
  4. Introduction to Hyperparameter Tuning
  5. Selecting and Finalizing Models
  6. Tuning Multiple Parameters
Predicting Continuous Outcomes4 items
  1. From Classification to Regression
  2. Linear Regression in Tidymodels
  3. Random Forests for Regressions
  4. Evaluating Regression Models
Preprocessing with Recipes4 items
  1. Why Preprocessing Matters
  2. Essential Recipe Steps
  3. Preparing and Applying Recipes
  4. Recipes in Workflows
Regularized Regressions4 items
  1. The Problem of Overfitting
  2. Ridge, Lasso, and Elastic Net
  3. Tuning Regularized Models
  4. Interpreting Regularized Coefficients
Workflow Sets for Model Comparison4 items
  1. The Challenge of Fair Model Comparison
  2. Creating Workflow Sets
  3. Tuning Workflow Sets
  4. Selecting and Finalizing the Best Workflow
Neural Networks4 items
  1. Why Neural Networks?
  2. Building Your First Neural Network
  3. Tuning Neural Networks
  4. Deeper Networks and Practical Considerations
Deployment of Machine Learning Models4 items
  1. Why Deployment Matters?
  2. Deploying Models with Vetiver
  3. Exporting Models with Orbital
  4. Monitoring and Maintaining Deployed Models
From ML to LLMs2 items
  1. A Gentle Introduction to LLMs
  2. Data Science Principles
Chat Basics4 items
  1. Introduction to LLMs
  2. Getting Started with Ellmer
  3. Conversations, Roles, and Tokens
  4. System Prompts
Prompt Engineering5 items
  1. Introduction to Prompt Engineering
  2. Adding Context and Instructions
  3. Handling Missing Data
  4. Fewshot Prompting
  5. Structuring and Storing Prompts
Structured Output4 items
  1. Introduction to Structured Output
  2. Extracting Data Frames
  3. Handling Missing Fields
  4. Batch Processing
Multimodal Input3 items
  1. Multimodal Input Introduction
  2. Hallucination with Plot Interpretation
  3. Extracting Data from Images
Model Selection5 items
  1. Model Selection Introduction
  2. Working with Proprietary Models
  3. Local Models Intro
  4. Running Local Models with Ollama
  5. Local Models in R
Tool Calling5 items
  1. Introduction to Tools
  2. Data Query Tools I
  3. Data Query Tools II
  4. Bio Retrieval Tools
  5. User Control Safety
NLP with Mall4 items
  1. Introduction to Mall
  2. Text Summarization
  3. Extracting Information
  4. Text Classification
Retrieval-Augmented Generation7 items
  1. Introducing RAG and Ragnar
  2. Document Processing
  3. Retrieval via BM25
  4. Retrieval via Embeddings
  5. Hybrid Retrieval
  6. Registering Retrieval Tools
  7. Context Augmentation
Model Evaluation with Vitals8 items
  1. Introduction to Evals
  2. Evaluation Data Sets
  3. Running First Evaluation
  4. Viewing Eval Results
  5. Comparing Models
  6. Statistical Comparison
  7. RAG Evaluation Design
  8. Running RAG Evaluation
LLM Apps10 items
  1. LLMs Data Exploration
  2. Text to SQL
  3. Querychat
  4. Querychat System Prompt
  5. Customizing Querychat
  6. Chatbots with Shinychat
  7. Tool Calling Part 1
  8. Tool Calling Part 2
  9. RAG in Chatbots
  10. Explaining Model Predictions
What is included

What is yours when you enroll.

  • Lifetime access Every module and lesson, yours to keep and revisit, forever.
  • Project files and code Every notebook, dataset, and finished build, to keep and adapt.
  • All future updates New lessons and refreshes as the tools move, at no extra cost.
  • Self-paced Start today, go at your own pace, no cohort to wait for.

Refunds. If you enrolled and it is the wrong course for you, write to michael@athlyticz.com and a person will answer.

Questions

The ones that stop a purchase.

Is this included with Membership?

Yes. Membership includes this and the entire course catalog, plus the live Masterclass. If you plan to take more than a couple of courses, Membership is the better math.

Is this too advanced, or too basic, for me?

R users who can write dplyr and want to build real ML and LLM systems. Comfort with the tidyverse is assumed; no prior ML or LLM experience needed. If the "not for you" list above reads like you, start elsewhere; if the outcome at the top reads like something you could use next week, it is pitched right.

What exactly do I get, and for how long?

21 modules · 99 lessons · 4 phases. Every lesson, the project files and code, and all future updates. Lifetime access: it is yours to keep.

Is it self-paced?

Yes. Start today and go at your own pace, with lifetime access to every lesson and all future updates.

SynergiZing ML & LLMs in R

Go from a tidymodels ML pipeline to a deployed, evaluated RAG app running inside Shiny, production-grade R and LLM systems you can ship.

This course $499 one payment, lifetime access

21 modules · 99 lessons · 4 phases, the project files, and every future update.

Enroll now
Membership $2,999 a year

This course, the whole catalog, and the Masterclass: every live session and every recording.

Get Membership