
MCP + Skills: The New Interface for Engineering Work
There’s a type of cognitive overhead that engineers have normalized so completely they stopped noticing it.
Read on Substack →
Prompt engineering, system design, and building AI products that hold up past the demo. Cross-posted from Substack.

There’s a type of cognitive overhead that engineers have normalized so completely they stopped noticing it.
Read on Substack →

Most teams add streaming to their AI products because it feels faster.
Read on Substack →

Every company I’ve worked with has the same problem dressed in different clothes.
Read on Substack →

Traditional SaaS has a comforting property: infrastructure costs are largely fixed.
Read on Substack →

There’s an idea that circulates in AI engineering circles called “caveman prompting.” The premise: write your instructions in stripped-down, telegraphic English — almost no grammar, no courtesy, just the bare intent — and the model will still deliver.
Read on Substack →

Getting the architecture right is necessary.
Read on Substack →

The previous chapter made the case for workflows.
Read on Substack →

Agents are everywhere in the AI conversation right now.
Read on Substack →

Every week there’s a new framework, a new model, a new tool that promises to change how you build AI products.
Read on Substack →

Most AI products look great in a demo.
Read on Substack →