notes to self
RSS FeedI'm a CTO and software engineer with a passion for building scalable, maintainable, and efficient systems. I love sharing my knowledge and experiences through writing, and this blog is a platform for that.
Stuff
-
Why Agents Make Good Actors
Published: at 11:00 AMAI agents are stateful, long-running, and mostly idle. That's not a quirk — it's a specification. The actor model was built for exactly this shape of work.
-
Inside the Bellman loop: how value actually propagates
Published: at 07:00 PMBellman equations are usually introduced recursively, and the recursion misleads programmers. The runtime is closer to iterative graph relaxation — value sweeping backward through a state graph until it stops moving.
-
Hardening AI Workflows with the Agent Governance Framework
Updated: at 11:00 AMHow to use the Microsoft Agent Framework (MAF) and Agent Governance Toolkit to build secure, governed, and Human-in-the-Loop AI workflows.
-
Inside Microsoft Agent Framework Harness Providers
Published: at 11:00 AMAn LLM in a loop is not enough for production work. This post breaks down the six problems every agent harness must solve — working memory, shared file access, plan/execute modes, task tracking, parallel sub-agents, and tool approval — and how the Microsoft Agents Framework implements them.
-
Inside the ReAct loop: how agents actually iterate
Updated: at 11:00 AMWhat actually happens inside one iteration of the ReAct loop — why the model is stateless, how the transcript grows, when the loop exits, and why the harness around the model is where the engineering value lives.
-
The Protocol Layer: Watching the Theory Play Out in Real Time
Published: at 11:00 AMGoogle's developer guide to AI agent protocols is framed as a tutorial. Read it through a Coasean lens and it's something more interesting — live evidence that the transaction costs making firms necessary are being eliminated, layer by layer, in the open.
-
The Firm in 2026
Published: at 10:00 AMReturning to Coase's original question — why do firms exist? — with fifteen posts of new machinery. The answer has not changed. The composition of the costs has.
-
The Physics of Flow
Published: at 10:00 AMQueuing theory reveals the hidden physics governing how work flows through organisations. Every boundary is a queue. High utilisation destroys responsiveness. And AI agents change the service rate — but not the dynamics.
-
Metcalfe's Law, Conway's Law, and the Networked Firm
Published: at 10:00 AMMetcalfe's Law governs the value of the external network, while Conway's Law governs the structure of the organization that builds and operates it.
-
Metrics Are Projection
Published: at 10:00 AMMetrics don't measure reality — they project it. As systems become more autonomous, projection design matters more than model intelligence.
Recent Posts
-
An introduction to reinforcement learning
Updated: at 11:00 AMThe orientation for working engineers before the rest of the series goes into algorithm internals. What RL is, the vocabulary, the Bellman idea, when to reach for it, and a map of the five posts.
-
Designing environments for RL
Updated: at 11:00 AMMost RL writing is about algorithms. In practice, environment design — the state, action, and reward decisions that sit between your system and the algorithm — is where projects succeed or fail. This is the part that almost never gets covered.
-
Securing MCP Pipelines with Agent Governance
Updated: at 11:00 AMHow to secure Model Context Protocol (MCP) tool usage in sequential agent workflows using Supply Chain Validation and Least-Privilege Sandboxing.
-
Securing Agent-to-Agent (A2A) Handoffs with the Agent Mesh
Published: at 03:00 PMHow to secure distributed multi-agent architectures using Zero-Trust Identity, IATP encryption, and Dynamic Trust Scoring in the Agent Governance Toolkit.