RAG in R that actually works
End-to-end with ragnar, vector search/BM25, chunking strategies, and vitals evaluation.
Ship production-grade R workflows that blend tidymodels with modern LLMs—from tool-calling and RAG to Shiny deployment and evaluation. Join the waitlist for early access and launch updates.
We’ll send early access, syllabus updates, and pilot opportunities. No spam—unsubscribe any time.
We’ve assembled a world-class group across the UK, Germany, the Netherlands, France, Switzerland, and the U.S. to ensure R users can confidently integrate ML + LLMs into production.
Common requests we hear (and what you’ll get):
End-to-end with ragnar, vector search/BM25, chunking strategies, and vitals evaluation.
Register R functions with ellmer, query structured data with querychat, and orchestrate NL → tidymodels pipelines.
Package models with vetiver, wrap in Shiny, monitor cost/latency, and add simple observability.
LDA, penalized regression, trees/ensembles, proper CV/tuning—so you don’t need a separate ML course.
“LLMs open up new ways to extend your analyses in R… I’m excited to teach how to use LLMs with tidymodels to take your modelling further.”
Independent R consultant with 15 years in R; PhD in Statistics. Core maintainer of Apache Arrow for R and author of Scaling Up with R and Arrow (CRC Press, 2025). Deep experience deploying R in production across pharma, public health, academia, and startups.
“LLMs are reshaping modeling—exploration is faster, communication clearer, and workflows more powerful. Let’s pair tidymodels with modern AI.”
Financial economist turned data scientist and product manager. Builds interactive dashboards, automated reporting, and custom R/Python packages; extensive experience with CI/CD and Shiny deployments (Docker, ShinyProxy, Posit Connect, GCR).
Your path from fundamentals → production:
Lead instructor for our 3-part Shiny Series, co-designed with Dr. David Granjon.
Your warm-up path into modern R and the tidyverse.
Two-course R bundle on Bayesian modeling with Stan.
Monthly R/Shiny/LLM/Tidy membership track—coming soon.
Yes. 12–25 hours total with short, focused clips (2–10 minutes). Case study projects add a practical layer with an easy to reproduce workflow for our Google Cloud powered virtual machines directly on our platform. No setup, join and learn right away from experts in the area.
Tidyverse + basic Shiny comfort recommended. If you’re rusty, start with BreeZing through the Tidyverse.
Upper-undergrad/grad students and working R/analytics pros who want reproducible, deployable ML+LLM workflows.
Join the waitlist to get early access and launch updates.