Featured framework
SRAL: A Framework for Evaluating Agentic AI Architectures
State, Reason, Act, Learn: a four-part lens for evaluating whether an agent's architecture survives production, not just the demo.
Read the frameworkAakash Sharan
Former Global Head of Professional Services, then VP of Services and Solution Architecture, Lightbend (Akka) 13 years in distributed systems creator of the SRAL framework
I design and evaluate agentic systems where architecture, not the model, decides what survives production.
Currently building an infrastructure company for agentic commerce. I write about AI systems that think, act, and recover under pressure, and the engineering patterns that make them work at scale.
10 years97 essays1 frameworkDOI'dopen-source
Start here
-
SRAL Framework: The Four Questions I Ask About Every AI Agent
The framework I evaluate every agent with: State, Reason, Act, Learn. The mental model the rest of the blog builds on.
-
The Observer Left: What Agentic Checkout Does to Attribution
How AI shopping agents break the measurement commerce runs on. The problem space I'm building in.
-
Declared State Is Not Observed State
The distributed-systems idea under most of my writing: a system's report of itself is a claim, not a measurement.
-
Why Your AI Agent Keeps Making the Same Mistakes
Why your AI agent keeps repeating the same mistakes. Learning is distilling what to do differently, not storing what happened.
Recent writing
AllSelected essays
-
The Harness Is the Control Plane: A Distributed Systems View of Agent Failures
My core thesis in full: the runtime, not the model, is the agent.
-
Agent Cost Is a Scheduling Problem, Not a Billing Problem
Agent cost read as a scheduling problem, admission control and backpressure, not a billing dashboard.
-
The Buyer Left
What "consumer behavior" even measures once an agent, not a person, makes the purchase.
-
How Vector Databases Fail (And What Architects Must Design For)
The vector-database failure modes that only surface in production, and what to design for.