Blog
Long-form thinking on engineering, agentic systems, RAG, MVPs, and the practice of shipping software.
An honest production guide. What each frontier model is best at, where they fail, and how to pick without lock-in.
AI in healthtech isn't blocked by tech anymore — it's blocked by regulation, liability, and clinical workflow integration. A 2026 status report.
When does hiring win? When does a studio win? An honest framework that doesn't pretend the answer is always one or the other.
Fractional CTOs are sold as a magic bullet for pre-CTO startups. Sometimes they are. Often they aren't. Here's how to tell.
RAG demos are everywhere; reliable RAG is rare. The parts that actually decide whether your retrieval works in production.
Companion to our Agentic Development 2026 piece. The 3 patterns that earn their keep — and the 3 we've seen kill projects.
Grounding is the difference between an LLM that hallucinates and one you can ship. Here's what it actually means in 2026 and how to wire it into your product.
What separates the voice agents people accept from the ones they hang up on. A 2026 stack guide for shipping voice CX that doesn't trigger fight-or-flight.
Who's selling what, who's actually shipping, and what founders should look for when hiring an AI partner in India today.
