LLMOps at Scale: Patterns from over 1,365 Production Deployments

Our Q&A will happen on Discord so come join us there and ask questions live (#podcasts channel)! https://discord.gg/jnuKWGg5

Check out our lu.ma calendar for more events: https://luma.com/calendar/cal-8ImWFDQ3IEIxNWk

Want to learn more?

Join the final cohort of our Building AI Applications course in Q1, 2026:
https://maven.com/hugo-stefan/building-ai-apps-ds-and-swe-from-first-principles?promoCode=search

00:00 Overview of LLMOps at Scale
01:32 Evolution of AI and Data Science
03:31 Discussion on Agent Systems
04:38 Advancements in Model Performance
07:15 Challenges and Strategies in Agentic Systems
19:36 Context Engineering in AI
34:18 Cost and Latency Considerations: Time and Money, People!
38:40 User Experience and Agentic Systems
39:50 Exploring the LLMOps database with an MCP Server
41:24 LLMOps Database Statistics and Case Studies
44:25 Tool Calling and Context Pollution
48:32 Re-architecting Agent Systems
58:31 Agent Skills vs MCP Servers
01:05:19 Emerging Tools and Systems
01:12:38 Final Thoughts and Takeaways

Видео LLMOps at Scale: Patterns from over 1,365 Production Deployments канала Vanishing Gradients