Docs AI Tooling is Better (and Better for Us) than You Think
summary
Shows a working Kappa RAG chatbot wired to docs Slack courses and GitHub that serves about 3,000 queries/day and 14,000/month while flagging answers as uncertain ~5–7%. It returns explicit citations to source pages, exposes dashboards of question clusters, and yields concrete followups—Jira tickets to fix gaps. No wholesale doc rewrites required, ingestion is automatic for markdown sites, and the analytics-driven feedback loop demonstrably improves docs and support workflows.
AI-written summary · about
chapters (13)
- 0:00Intro
- 1:16Temporal
- 2:01Current state of AI
- 5:32Center track
- 6:50Constructive engagement
- 8:44Automating the wrong jobs
- 10:18Retrieval Augmented Generation
- 11:52Kappa AI
- 16:22The Kappa Sources Page
- 17:53Valid Citations Only
- 24:39Kappa Insights
- 26:55Conclusion
- 29:36QA Session
related talks
24mDocumentation and AI: How to write right now
23mDocumentation in the Age of AI: Why Docs Are a Product
30mHow to Win Docs and Influence Robots: Improving Robot Accuracy Through Better Docs
20mCase Study: Drupal gets smarter with AI driven Bot
39mWhat I Learned Building an AI Documentation Auditor (And What It Found in 500+ Pages of Docs)
36mGENAI-Powered chatbot to increase team efficiency
27mAI-Enhanced API Documentation [...]
43mA journey from static documentation to generative AI