What is a Generative AI Agent?

Generative AI Agents represent the current frontier of LLM technology, enabling dynamic interactions and intelligent workflow automation. However, the complexities of architecting and deploying these agents can be daunting. In this live session, Patrick Marlow demystifies the process, guiding you through the critical decisions and trade-offs involved in building production-ready agents.

Explore the full spectrum of Agent development, from the core components like Models, Tools, and Orchestration Frameworks to the strategic choices between managed and DIY approaches. The session wraps up with a live demo and Q&A.

[lucface]

Heck yeah. Stoked to play around with it

[AI-Wire]

How can we start building with these right now?

[ibgib]

10:47 - "Models No native tool implementation. Tools can be implemented via custom integrations." "Agents Tools are natively implemented in Agent architecture"
15:00 - "the point is you're building essentially a shim between the agent and the API interface" (speaking on the "Extension" construct)

So how is building a shim to an API different than building an integration?

[Gringohuevon]

It doesn't work with complex apis