Posted inBlog
When the Agent Has to Work for the Whole Team
The early mental model of an AI coding agent was simple: one developer, one terminal, one conversation. That framing holds up well enough for solo work. It starts to crack…
Posted inBlog
Harness Engineering: Making Your Whole Team Ship with AI Agents
For a while, the story of AI coding agents was mostly an individual one. A developer found a setup that worked for them, tuned their prompts, built out a personal…
Posted inBlog
The Case for Deleting Your AI Layer (And What to Actually Cut)
When practitioners first adopted coding agents like Claude Code, the instinct was to write rules for everything. Spell out every convention. Patch every reasoning gap. The `CLAUDE.md` file became a…
Posted inBlog
The Unchecked Deloitte’s Report that Costed Them A$97,587.
For a while, the working assumption was that AI-generated content was easy to spot — rough edges, repetitive phrasing, a certain hollow confidence. The fix seemed obvious: polish the output,…
Posted inBlog
When the Agent Says It’s Done and It Isn’t: Three Checks Worth Running
For most of the short history of agentic AI, the working assumption has been that the main failure mode is an obvious one: the agent crashes, returns an error, or…
Posted inBlog
Why Enterprise AI Needs a Lean Dynamic Ontology
For years the dominant narrative around enterprise AI was a data problem. Organizations were told they needed more of it, cleaner versions of it, better pipelines to move it around.…
Posted inBlog
AI in Software Architecture: What 46 Studies Show
For a long time, software architecture was the part of development that resisted automation most stubbornly. Code generation tools could produce boilerplate; static analysis could flag smells. But the high-level…
Posted inBlog
Designing Languages for Agents, Not Humans
For decades, source code has been a text file — a sequence of characters that humans write, compilers parse, and version control tracks line by line. That arrangement made sense…
Posted inBlog
The Floor Is Rising: Which Level of AI Builder Are You?
Every time a major lab ships something new, the same thing happens in builder communities. A wave of anxiety rolls through. People start asking whether their projects are now pointless.…
Posted inBlog
Somebody Else’s Definition of Done: How to Actually Evaluate an Agent Skill
A writing skill was installed to help with design decisions — color palettes, layout choices, that kind of thing. It activated correctly. The output was technically fine. But every suggestion…