Evolution of agentic surfaces — Gagan Bhat & Isabella Kai He, Anthropic
Summary
Sonnet 4.5 developed what Anthropic's Applied AI team came to call context anxiety: approaching its context window limit, it would wrap work up early and stop with room to spare. They built context re
Related topics
Transcript Excerpt
[music] >> All right. Hi everyone. Thank you for joining us today. I'm Gagan. >> And I'm Isabella. >> We're both members of technical staff here at Anthropic at the Applied AI team. Our team sits at the intersection of product, research, and go-to-market. And we spend a lot of our daytime building agents, evaluating Claude, and finding ways to make it better in different use cases. >> We're here today to talk about how the surfaces for building agents has evolved in the last 3 years. What our teams have learned building agents both internally at Anthropic and externally with our enterprise customers along the way. I'll hand it off to Gagan to kick us off. >> So, here's the plan. We'll first start off by talking about how we've seen agentic surfaces evolve all the way from the Messages API …
More from ai.engineer
- LLM Knowledge Bases: a practical guide — Ben Holmes, Warp
- The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans — Corey Gallon, Rexmore
- Building Closed-Loop Evals for a Multimodal Agent at Scale — Soumya Gupta & Jai Chopra, Uber
- Loop Engineering from First Principles — Kyle Mistele, HumanLayer
- Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex