#deep-dive
Every post tagged "deep-dive".
107 posts · showing 21–30
-
What Ten Years of Agent Tooling Might Look Like
Specific capability predictions age badly; layer predictions age better. Which parts commoditize, which stay differentiated — and the one prediction here most likely to be wrong.
-
The Skills That Were Always the Job
Almost nothing on the durable list is new. These are what experienced engineers always said mattered — the economics just didn't reward them proportionately until now.
-
Positions Worth Revising About Agents
Eight beliefs that are reasonable on their face and don't survive production. Every correction points the same direction — which makes it a useful prior for the next problem.
-
When to Stop Improving an Agent
There's always another failing case, so without a stopping rule the work either never ends or ends arbitrarily. The signal isn't the error rate — it's effort per point of improvement.
-
The Economics of an Agent-Heavy Team
Several line items move and only one of them is tokens. The savings are real, land on a single term, and are partly consumed by four others that grow — which is why big speedups produce modest delivery gains.
-
The Documentation Problem Agents Create
Documentation has two audiences with different needs, and generated docs that restate the code become negative value the moment they drift — a confident wrong answer with an authoritative source attached.
-
Open Source After Cheap Contributions
Contribution effort rationed demand for maintainer attention. That rationing is gone and the attention is unchanged — but the filters that work test for something effort was only ever a proxy for.
-
Compliance and Audit for Agent-Written Systems
The audit questions don't change — who's responsible, how do you know it's correct, show me this case. They become answerable differently, and an actor field saying "agent-service" answers the first one not at all.
-
Security Review When Nobody Wrote the Code
Human vulnerabilities carry a tell — hurried code, an obvious shortcut. Generated code is uniformly careful-looking, so scanning for the suspicious part stops working. But its consistency cuts both ways.
-
Why Your Codebase Will Grow Faster Than Your Understanding
Writing code built understanding as a byproduct, which is why "the team knows the system" used to be true without anyone planning it. That coupling broke and only one of the two rates changed.