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.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago