#frameworks
Every post tagged "frameworks".
26 posts · showing 11–20
-
Model, Loop, Harness: Three Layers and Who Owns Each
Three layers, three change rates, three skill requirements. Conflating the loop and the harness is why loop bugs get fixed with prompt edits — and why domain experts can't fix domain problems.
-
Lock-In Risk in Agent Tooling, and How to Keep Optionality
The API call is trivially portable — the coupling forms in four other places, and the worst one isn't technical at all. One question tells you how exposed you are.
-
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.
-
Will Open-Source Harnesses Eat Commercial Coding Tools?
The premise is right — the loop is a few hundred lines. The conclusion is too fast, because the loop isn't the product, and one of the real advantages is 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.
-
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.
-
The Compounding Loop: Agents Building Agent Infrastructure
Agents are good at building the harness that makes agents useful — well-specified, verifiable plumbing. The loop is real, and it has a hard boundary at everything requiring judgment about what to build.
-
From Prompt Edit to Signal in Under a Minute
A six-minute iteration buys you ten experiments a day; a thirty-second one buys a hundred. Four fixes, about an afternoon of work, and the seam that everything else depends on.
-
Tracing Standards for Agents: What Fits and What's Missing
A run is a trace and a turn is a span — the mapping is cleaner than expected. Two things break: payloads far too big for span attributes, and sampling that discards exactly the runs you need.