Update talk

src/content/events/2024-12-03-apidays-paris.md

@@ -3,10 +3,16 @@ action: to speak about
 layout: "../../layouts/Event.astro"
 title: AIAPI
 event: API Days
-start_date: 2024-11-13T12:20:00.000Z
-end_date: 2024-11-14T12:20:00.000Z
+start_date: 2024-12-04T12:20:00.000Z
+end_date: 2024-12-06T12:20:00.000Z
 venue: 'CNIT Forest, Paris'
 pres_url: https://www.apidays.global/paris/
 ---
 
-TBD
+API documentation is generally predictable, follows common patterns, and is one of the least interesting tasks in a documentation project. It's also a task that has had a degree of automatic generation tools and practices for some time.
+
+It sounds like a perfect use case for AI-assistive tools!
+
+In this presentation, I look at general and specialised tools that help you generate API documentation from code and text-based prompts. I look at how you can train them to be more precise and accurate as well as the potential problems and pitfalls to look for in bringing any generated docs into production for end users.
+
+Some of these include tools you already have access to, such as GitHub Copilot and Gemini, and specialised tools, such as DocuWriter. I also cover how to test generated output to ensure it's accurate.