diff --git a/src/sessions/2026-02-20.md b/src/sessions/2026-02-20.md
new file mode 100644
index 0000000..ff3d9e0
--- /dev/null
+++ b/src/sessions/2026-02-20.md
@@ -0,0 +1,20 @@
+---
+title: "Boosting F# Libraries with Automated Agentic AI"
+preview: "Boosting F# Libraries with Automated Agentic AI"
+isDraft: true
+date: 2026-02-20T14:00:00.000Z
+id: "2026/02/20"
+champion: "Don Syme"
+zoomLink: "https://us06web.zoom.us/j/88934875539?pwd=UT80ap4HuxTH2ERauowMRFNNkfWqoi.1"
+zoomPasscode: "agentic"
+company: "Microsoft / GitHub"
+youtubeId: ""
+---
+
+In this talk, Don explores how GitHub Agentic Workflows - a framework developed at GitHub Next - can be used to augment 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.