Staff Applied AI Engineer. I build AI agent systems that hold up in production, from orchestration and durable workflows to MCP/A2A. Writes The AI Engineering Brief.
TIL: How PyTorch, GGUF, ggml, and llama.cpp Actually Fit Together
If you have ever dabbled in running local LLMs, you have probably seen acronyms like PyTorch, GGUF, ggml, and llama.
TIL: Claude Shannon's six ways to get unstuck
In his 1952 talk on creative thinking, Claude Shannon describes constructive dissatisfaction: seeing something that works and suspecting there’s
TIL: Six ways to cut LLM costs
1. Prompt caching. Put stable instructions, examples and tool schemas before changing inputs. An identical prefix can reuse earlier computation;
Claude Code
Claudialect
an ode to Claude’ese
Agentic Architecture
The Next Wave of AI Engineering Is About Everything Around the Model
As AI models improve, the engineering challenge shifts to agent harnesses, data quality, evaluations, memory and security. Here's what it takes to build reliable AI systems.
jev
What is Jev? A Simple Primer on AI That Makes Decisions
Jev is a new kind of AI model designed for fast, structured judgments rather than open-ended responses. This nontechnical primer explains how Jev turns fuzzy decisions into probability-backed outputs that software can use.
TIL: The AI Wall
Gen AI helps people in adjacent roles perform almost like experts, but it can't close the gap for people far from the domain. Here's what the AI wall means.
AI Agents
Defining an AI Agent
An attempt to nail down the definition of the constantly evolving term: AI Agents
TIL: What’s actually different about GGUF and ONNX?
What GGUF and ONNX actually contain, what they expect from the runtime, and why choosing between them is not simply a question of quantisation or hardware.
Codex
How I code with Claude Code
I have been coding with Claude Code for over a year now, and somewhere along the way I have developed
One agent or many?
A practical guide for AI engineers choosing between single-agent and multi-agent systems, based on task structure, context and coordination costs.
Loop Engineering
From Prompt Engineering to Loop Engineering
If you spend any time watching this space, you have watched this vocabulary turn over three times in about a
Cognitive Debt
Who Still Understands the Code?
AI coding agents make you dramatically faster. The cost they carry is quieter: a slow erosion of how well you understand the software you are shipping. Here is how I have come to think about that trade, and how I try to stay on the right side of it.
AI Engineering
Designing teams for an agentic world
AI coding agents are changing the economics of software development and the shape of engineering organisations. Here is how leaders should rethink build-versus-buy decisions, talent, team structure, platform strategy, and AI governance.
Agent Memory
The Frontier of Agent Memory: From Recall to Experience
Part 3 of a 3 part series post about AI Agent memory architecture.
Speculative Decoding
Trading cheap guesses for expensive forward passes
Query, Key, Values
How to think about Q, K, and V vectors in the Attention layer of a Large Language Model
How Modern Agent Memory Architectures Work
Part 2 of a 3 part series post about AI Agent memory architecture.