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
-
Your agents need identities, not API keys
Every AI agent is a non-human identity — most run on shared, long-lived API keys no IAM review sees. Per-agent identity and your credential blast radius.
-
Token FinOps: the third budget your agents are spending
Error budgets, context budgets — agents add a third: dollars. Agent tasks burn 5–30× chatbot tokens, and cost-per-token is the wrong metric.
-
Tracing the agent loop: OpenTelemetry's GenAI conventions, read like an SRE
Your agent is a distributed system wearing a chat interface. OpenTelemetry's GenAI conventions make it debuggable — what v1.41 covers and what's moving.
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 →