What we think
Ideas from building real AI
Research, playbooks and hard-won lessons from shipping AI products that hold up in production — not just in the demo.
The agentic SaaS playbook
Agents are not a feature you bolt on — they are an architecture. Here is how we design SaaS products where the agent is a first-class citizen, not a demo.
Read the pieceMore thinking
Playbooks & perspectives
Evals before demos
A demo proves an AI feature can work once. An eval proves it works the thousandth time. We do not ship AI without one — and neither should you.
Read moreRAG that survives production
Retrieval-augmented generation is easy to prototype and hard to keep honest. The difference is in the retrieval, not the generation.
Read morePricing AI features
AI features have a cost of goods that traditional software never did. Price them as if every request is free and the unit economics will quietly bleed you.
Read moreDesigning AI people trust
Trust in an AI product is not won with a clever model. It is won with honesty about what the system knows, what it is doing, and when it is unsure.
Read moreWhy small teams ship faster
The bottleneck in software is rarely typing speed. It is coordination. Small, senior, cross-functional teams simply have less of it to lose.
Read moreWant this thinking applied to your product?
Tell us where you are and where you want to be. We'll come back with a concrete plan — no jargon, no lock-in.