Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
Delayed AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → actions break the user-versus-service-principal identity model, and logs stop working once agents emit this much reasoning. Navan's answer: per-tool-call guardrailsThe checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.Full definition →, hooks that emit goal and confidence, and trajectory scoring instead of output assertions.
videoGuardians of the State: An Air-Gapped AI Fortress for Consumer Data — Rachna Srivastava, DFPI
videoFrom Tokenmaxxing to Trusted Throughput — Mingsheng Hong, Ironclad
videoAgentic Sites: Building Hyper Personalized Websites — Carlos Sanchez, Adobe
videoTribal Dungeons of Global Shipping: AI Agents at Global Scale — Dmitry Buykin, Maersk
