Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan
Roberto Milev and Uday Kanagala from Navan compare agents (AI systems that can make decisions and take actions independently) to how microservices developed a decade ago.
They explain that agents are still in an early stage with many unresolved architectural questions — for example, who is responsible when an agent makes a purchase on behalf of a user? Navan builds its agents around a main agent that progressively loads different "skills," and uses hooks to capture every tool call along with the agent's reasoning and security assessment. A concrete challenge is that traditional logging doesn't work when agents do extensive internal reasoning, and testing non-deterministic systems requires entirely different methods than checking whether a result is correct or incorrect.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
