I build agentic AI systems that work in production
-
Building Ambi- the white whale: an agent that writes its own features
Part 3: The white whale. The feature I wanted most, and never really got — ambi writing its own features. It worked in a demo. Then it learned to suppress its own failure notifications.
-
Building Ambi- The everything-machine
Part 2 This is part 2 of Building Ambi — the story of building a personal AI assistant three times over. Part 1 is here. Ambi grew the way side projects do. There was never a plan. Every time I wished it could do one more thing, I taught it to. And every time I…
-
From Demos to Deployment: What Day Two of Google Cloud Summit London Taught Me About Building
June 18, 2026 · London If Day 1 of Google Cloud Summit London was about the architecture of the agentic era — the data platform, the governance, the case studies — Day 2 was about the thing the builders actually do with it. The framing shifted from “here’s the platform” to “here’s what you can…
-
From Intelligence to Action: What Google Cloud Summit London Told Me About the Agentic Era
June 17, 2026 · London I spent today at Google Cloud Summit London, and if I had to distil the whole event into a single sentence it would be this: the era of passive intelligence is over. That’s not a marketing line I’m borrowing — it’s the actual framing Google used in the opening keynote,…
-
Building Ambi- it started with my son
Part 1 I build AI systems for a living. One evening my son asked what that actually means, so I told him: I build machines that can think a little, use tools, have a conversation. He went quiet for a second. Then he said, “You should build one for yourself.” And before I could answer:…
-
Stop Blaming the Agent: Why Your AI Coding Projects Fail Without Guardrails
I had to throw away a few of my code projects recently. And I’m not talking about little throwaway experiments — these were real projects I’d invested time in. They got to a point where they were really unmanageable. There was a lot of duplicated code, a lot of duplicated processes, and honestly, it just…
-
The AI-First Product Development Revolution: Stop Retrofitting, Start Building for Agents
AI agents are here, and they’re not just a passing trend. While we speculate on the next great leap in artificial intelligence, a powerful reality has taken hold: Large Language Models (LLMs) equipped with agentic frameworks are proving incredibly adept at using tools to execute complex, task-based activities. This new paradigm, however, has caught many…
-
How to make existing applications more intelligent using LLMs
AI is everywhere, and companies are trying to label their products to ensure they do not get left behind in the race. This is a fair attempt, as most of the general public sees that a product using AI feels more advanced and innovative. However, we need to make sure we are implementing AI in…
-
AI ready web applications
OpenAI released the operator feature to the public on 23/01/2025. This feature will allow an AI agent to leverage a web browser to browse web applications and perform tasks while confirming essential decisions with the user. This feature can have many benefits, but this made me think that we may need to give a little…
-
Coldstart improvements in legacy dotnet applications
Before we dive into the details, let’s clarify what a cold start is. Cold start refers to a problem where a system or its part was created or restarted and is not working at its normal operation[1]. I’m going to talk about how quickly a web application can handle a request from the cold. It’s…