Showing 1–12 of 21 articles tagged AI Architecture
Industry & Markets
Physical AI Is Leaving the Browser
Digital agents were the first act. Physical AI is the next product frontier: robots, sensors, factories, vehicles, and supply chains.
28 May9 min read
Read →
AI Product Building
AI Software Quality Needs a Factory Again
AI software quality is a production discipline. Code got cheap, but review, evals, rollback, and observability did not.
22 May8 min read
Read →
AI Strategy & LeadershipDeep dive
AI Is a Five-Layer Cake. Pick the Slice That Keeps Paying.
Energy, chips, systems, models, applications. Every layer matters. Only one pays compounding returns. A framework for picking yours.
29 Apr11 min read
Read →
AI Product BuildingDeep dive
I Try to Jailbreak Every AI Chat I Use. Most of Them Let Me.
Six production chat surfaces, a habit of breaking every AI chat in the wild, and the defence-in-depth stack that keeps your prompts contained.
24 Apr16 min read
Read →
AI Product BuildingQuick read
The Ticket Is the New Prompt
Chat is the wrong interface for AI agents in professional software work. A well-written issue is a better agent instruction than any prompt.
1 Apr5 min read
Read →
AI Strategy & LeadershipDeep dive
Agentic AI Security: Why 97% Detection Is a Failing Grade
A 97% attack detection rate sounds fine until an agentic system has tool access, private data, and a path to action. Then it is a breach rate.
23 Mar10 min read
Read →
AI Product Building
Tests Pass. Does It Think?
When AI writes the code, green CI isn't enough. The new discipline is understanding and defending the choices the model made — not just the ones you made.
2 Mar8 min read
Read →
AI Product Building
Fred Brooks Is Dead. Rewrite the Damn Thing.
The 'never rewrite' doctrine was based on rewrite cost. AI has collapsed that cost to days. Pre-launch rewrites are now a product strategy, not a failure.
23 Feb7 min read
Read →
AI Product BuildingDeep dive
AI Didn't Kill Coding. It Killed Typing.
AI coding is the sixth abstraction layer in 80 years. Every previous layer was dismissed as not real programming by the practitioners of the one below.
11 Feb10 min read
Read →
AI Product BuildingDeep dive
How to Measure an AI Product (When Traditional Metrics Lie)
DAU, time-in-app, and NPS were built for a world where humans do the work. AI products need different metrics. A framework for what to measure and why.
9 Feb10 min read
Read →
AI Product Building
The Bitter Lesson Kills Your Orchestration Layer
Scaffolding gives you 10-20% gains that the next model wipes out. The bitter lesson for product builders: give the model tools and a goal, not a workflow.
6 Feb8 min read
Read →
AI Product Building
The Winning Agent Had No Better Model. It Got Shit Done.
Weekend build to 145K GitHub stars to acquisition in weeks. The pattern: agents that execute locally instead of chatting in a browser window win on adoption.
30 Jan9 min read
Read →