notes from the field
Making cloud run itself,
one agent at a time.
Hands-on writing on agentic infrastructure, MCP, and reliability — from someone shipping it in production at a Fortune-500 aviation platform, not theorizing about it. By Ajin Baby.
Right now:
Latest field notes
-
Context engineering: the window is a budget, not a bucket
The context window is the working memory of every agent you ship, and most teams treat it like a junk drawer. Context engineering as a discipline: four operations (write, select, compress, isolate), a token budget you actually allocate, the failure modes that bite at scale, and a worked SRE example.
-
Agent sprawl is your next production incident
Every team shipping AI agents in 2026 is quietly recreating the microservices sprawl of 2015–2020 — faster, and with worse observability. Why agent sprawl is structurally the same failure, what's different this time, and the governance surface that contains it before it pages you at 3am.
-
No anonymous inference endpoints — the MCP security principle you're probably violating
In 2026 the NSA and NIST both put MCP and AI agents on notice: the protocol that lets your agents act is also a centralized funnel for prompt injection and privilege abuse. Why 'no anonymous inference endpoints' is the principle most teams break by default, and how token exchange (RFC 8693) plus policy-as-code closes it.
Tools I build in the open
Who's writing this
Ajin Baby — 15 years making cloud platforms reliable, 2x founder before that. Azure AI Engineer, Neo4j Certified, IEEE member. More about me →