Resources
Everything we have written down
Two kinds of writing. Trends are technical and dated — what changed, and what the research actually says. The blog is evergreen and commercial — what it costs, how long it takes, and which decisions matter.
Trends
What is changing in engineering
Technical write-ups of the shifts reshaping how software gets built — agentic coding, MCP, context engineering and more. Each cites the research behind it.
Spec-driven development: writing the specification as the source of truth
Spec-driven development treats the specification as the source of truth and code as its output. Where that works, where it does not, and the tooling behind it.
Context engineering: the discipline that replaced prompt engineering
Why context engineering replaced prompt engineering: retrieval quality, position bias, compaction and trust boundaries, grounded in the long-context research.
Vibe coding: what it is, where it works, and where it costs you
What vibe coding is, where it is genuinely the right call, and the measured risks — including package hallucination rates and slopsquatting attacks.
Blog
Straight answers about building software
For founders, operators and the people signing off engineering spend. What things cost, how long they take, what to build first, and where budgets go wrong.
Is AI-generated code safe to ship?
What AI-generated code changes about your engineering risk, the four questions to ask your team, and the two metrics that reveal review becoming a formality.
Why AI features take five times longer than the demo suggested
The demo took two days; shipping took four months. Where that time goes, why it is nobody's fault, and the questions that get you a realistic timeline.
Should your startup build AI features?
How to tell a genuine AI use case from a defensive one, what inference actually costs to run, and the failure modes that cost customers rather than money.
Got something you are trying to scope?
Tell us the problem and we will give you an honest read on what it takes — including whether it should be smaller than you are planning.