Blog
Notes, thoughts, and deep dives on AI, systems architecture, and software engineering — from over a decade building products.
Showing 1–10 of 41 posts
-
Jev Returns a Type, Not a String
JEV returns typed values with probabilities instead of text. What that changes for AI model routing: the control plane, the failure modes, the benchmarks.
-
SEO Is a Distributed System
How search ranking actually works: the crawl subsystem and its budget, the inverted index, canonicalisation as clustering, and the ranking cascade.
-
Answer Engine Optimization Is an Architecture Problem
AEO as systems architecture: the indexing and query planes, chunking as the unit of ranking, why citation is separate from retrieval, and measuring lift.
-
Implementing Wizards the Right Way
Building multi-step wizards: Duolingo's one-question onboarding, Stripe Connect's branching, and the anti-patterns that make users quit.
-
How to Make an MVP in the AI Era
What an MVP needs now that AI makes building nearly free: the traps to avoid, and why the constraint moved to testing assumptions with real customers.
-
10 Event-Driven Architecture Questions That Separate Architects from Framework Users
Ten questions that separate framework users from distributed-systems engineers: idempotency, ordering, sagas, observability, and when not to use events.
-
Beyond Email: Dual-Channel SMS Catching, 14 MCP Tools, and Email Analysis in Postwire
Postwire v0.2 adds SMS catching with Twilio webhooks, 14 MCP tools for AI agents, and Litmus-style email analysis to the local mail catcher.
-
Introducing Postwire: A Tiny SMTP Mail Catcher for Developers and AI Agents
Why I built Postwire: a single-binary SMTP mail catcher in Rust with a REST API and MCP server for automated testing and AI agents.
-
Make the Hard Decision Before the Product Fails
Most products don't die suddenly — they die from delayed decisions. A guide to failure signals, premortems, and perish/pivot/persevere rules.
-
AI Didn't Cause Every Layoff. Management Did.
How much of the AI layoff era is automation, and how much is management using AI as the excuse for decisions that were already coming?