AI agents are all the rage right now, and companies are rushing to find creative ways to put them to work. Especially compelling is multi-agent orchestration, in which swarms of agents, each armed with a particular set of skills, collaborate as a team to accomplish complex tasks.

What if you were told that much of what you learned about agentic AI was either wrong or incomplete? That a typical agentic app could run several times faster and be orders of magnitude less expensive and more robust if it were architected differently? That’s the promise of CodeGen agents: agents that utilize tools by generating code rather than by relying on the LLM tools protocol. Learn what CodeGen agents are, how to write them, and how to use them to write agents that scale. It might just change the way you think about agentic AI.