#agent-design
Every post tagged "agent-design".
112 posts · showing 41–50
-
The Loop Decisions You Only Make Once
Most agent design choices are cheap to revise. Six aren't — and in every case the answer that ages well is the same one, for the same reason.
-
Context Engineering Is the Job Now
Not prompt writing — that's the visible part and the small one. The work is deciding what reaches the model, in what form, at what moment, and it's where most agent failures start.
-
The Moat Isn't the Model — It's the Loop Around It
"The model isn't the moat" is now widely said and stops one step short. What compounds shares a property — it accumulates from watching real usage, which is why it's invisible from outside.
-
What a Harness Actually Is, and Why It's the Real Product
A model takes messages and returns tool calls. Everything else is the harness — and it explains almost all the variance between agent systems that share the same model.
-
IDE Assistants vs Agent Harnesses: Different Products, Different Futures
They get discussed as one category and have opposite requirements on latency, context, failure cost, and model tier. One is commoditizing into a feature; the other's differentiators aren't AI capabilities at all.
-
What Falling Inference Costs Change About Agent Design
Relaxed cost pressure mainly buys back the verification steps you declined. It doesn't rehabilitate filling the context or adding turns — those were quality problems wearing a cost disguise.
-
The Cost of Choosing Your Model Too Early
The choice is rarely the mistake — the accumulated compensations are. Prompts absorb quirks, the harness papers over weaknesses, and none of it looks like coupling until you try to change something.
-
Matching Model Tier to Task: A Practical Table
"Simpler tasks get cheaper models" isn't actionable, because simplicity isn't the predictor. Two properties are — and one row of the table overrides all the others.
-
Should You Always Reach for the Flagship Model?
"Always use the cheapest model that works" has costs that don't appear in a token bill. The case for flagship-by-default is stronger than usually admitted — and there's a cheaper optimization people skip first.
-
Why Benchmarks Keep Rising While Deployments Stay Hard
Both reports are accurate. Benchmarks test well-posed, self-contained, checkable problems — and almost none of deployment difficulty is any of those things.