We Mapped 115 Microservices for Our Coding Agents — Kamalakannan Nandagopal, Postman
Source
youtube.com
Author
AI Engineer
Date
Why it matters
Coding agents struggle outside one repo. Postman grounded a graph of services and endpoints in code and telemetry, found 75% of PRs touched APIs, and showed a stale graph hurts results.
Key takeaways · AI-distilled
Postman runs 115 microservices with thousands of endpoints. Kamalakannan Nandagopal says docs go stale, and skills, MCPs and 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 → memory are only as good as their context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →, which tends to stay with one person.
Borrowing an insight from its go-to-market team that APIs are the context layer, Postman built an API context graph mapping every service, endpoint, implementation and call down to databases, groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → in code or production telemetry.
evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → built from real PRs and design decisions showed large gains on API discovery, redesign and impact assessment, and the agent produced a 21-page architecture review on its own.
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
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.
