In this talk, Don explores how GitHub Agentic Workflows - a framework developed at GitHub Next - can revolutionise F# library development through automated performance and test improvements. The approach introduces "Continuous Test Improvement" and "Continuous Performance Improvement" where AI agents automatically research, measure, optimise, and re-measure code performance in a continuous loop, all while maintaining human oversight through pull request reviews and goal-setting. This semi-automatic engineering approach represents a fundamental shift in software development: from manual coding to AI-assisted completions, to task-oriented programming, and now to event-triggered agentic workflows. Don will demonstrate practical applications in F# libraries, showing how these workflows can identify performance bottlenecks, generate benchmarks, implement optimisations, and verify improvements - all while preserving code correctness through automated testing. Learn how this emerging technology could transform how we maintain and optimise F# libraries, making high-performance code more accessible to the entire F# community.

In this report, F# contributor Tomas Petricek explains many of the key features of the F# language that make it a great tool for data science and machine learning. Real world examples take you through the entire data science workflow with F#, from data access and analysis to presenting the results. You'll learn about: How F# and its unique features—such as type providers—ease the chore of data access The process of data analysis and visualization, using the Deedle library, R type provider and the XPlot charting library Implementations for a clustering algorithm using the standard F# library and how the F# type inference helps you understand your code The report also includes a list of resources to help you learn more about using F# for data science.