Tools of the Trade
Frameworks, SDKs, platforms, build-vs-buy.
26 posts · showing 11–20
-
The Case for a Local-First Agent Stack
The cost argument for local-first is weak and the ideology one is worse. The case that holds is dependency control — and it comes with a permanent operational tax nobody budgets.
-
What Runs Locally Today and What Still Won't Soon
Local handles the steps; hosted handles the orchestration. The agent loop is the hardest thing to localize, because it stresses all three local constraints at once.
-
When a Small Model Beats a Big One, and How to Tell
Sometimes "beats" means cheaper at acceptable quality — and sometimes it means genuinely better on the metric that matters. Four cases where smaller wins outright, and four where it looks like it should and doesn't.
-
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.
-
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.
-
Request, Worker, or Durable Execution? Hosting Models for Agents
Where a run lives decides how long it can be, whether it survives a deploy, and whether it can wait for a person. Pick by the longest wait it can hit — and keep state out of process memory so the answer can change.
-
Local Models for Agent Work: Where They Actually Fit
"Can a local model replace the frontier one?" is the wrong question. Which steps can move is the right one — and the comparison people skip is against a small hosted model, where most of the saving already lives.