Tag
AI Architecture
15 articles tagged with AI Architecture.
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.
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.
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.
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.
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.
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.
Build for the Model That Doesn't Exist Yet
Your AI product market fit depends on a model that has not shipped yet. Build your product architecture for the capability curve, not today's snapshot.
Voice Agent Playbook: AI Phone Calls in Production
I built AI voice receptionists that handle real phone calls for real businesses. Latency, conversation flow, graceful handoff. Here's what actually matters.
Your RAG Pipeline Is a Product Decision, Not an Engineering One
Chunking, retrieval, and grounding are not engineering details. They are product decisions that determine whether your AI feature helps or hallucinates.
The AI Usage Gap Is a Product Architecture Problem
Most AI tools are deployed but unused. The friction isn't capability. AI lives in a separate tab instead of where work happens. Build inline, not destination.
Your Agent Evals Are Vibes. Here's How to Make Them Infrastructure.
Most teams evaluate agents with manual chats and gut feel. A practical framework for eval suites that let you ship, starting with 20 examples, not 20,000.
The 2,500% Audit Tax: The Math That Will Kill Your Multi-Agent P&L
A manager model checking every worker output increases unit cost by 2,500%. The fix: a spot-check architecture that can save 75% of your token margin.
Stop Building AI Agents. Start Building SOPs Wrapped in Code.
A 5-step agent at 95% accuracy per step is only 77% reliable. The path forward isn't better agents, it's narrower ones. Three rules for workflows that ship.
Stop Picking Winners in the Model Race. Build the Router Instead.
Building for a single model is technical debt with a short shelf life. The winning strategy is orchestration, evals, and governance, not leaderboard loyalty.
3 Agentic AI Patterns from Google's Playbook
Strip the vendor marketing from Google's AI Agent Handbook and three stack-agnostic architectural patterns emerge that every product builder should steal.