All posts
Everything published here, newest first.
316 posts · showing 231–240
2026
10 posts-
Designing Tools for Agents vs Designing APIs for Developers
One endpoint, one tool is the obvious mapping and the wrong one. APIs assume a consumer who reads docs once and writes a loop — an agent re-decides everything from a paragraph, every call.
-
Getting an Agent to Say How Sure It Is
Ask a model how confident it is and you get a plausible number that doesn't move with difficulty. Five signals that actually correlate with being right — and the calibration check that tells you if yours is noise.
-
Few-Shot Examples: When They Help an Agent and When They Hurt
Two or three similar examples is the worst case — enough to teach a template, not enough to convey the range. And the example nobody includes is the one where the right answer is to decline.
-
Latency Budgets for Agents: Where the Seconds Actually Go
"Try a faster model" addresses maybe a third of the time in a typical run. Split the twelve seconds five ways and the real culprits — turn count and tool latency — are usually the ones nobody measured.
-
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.
-
The Documentation Agent That Actually Kept Docs in Sync
Ask an agent "do the docs need updating?" on every PR and you get noise reviewers close unread. Trigger on contract changes, forbid new prose, cite the source line — and run the corpus-wide contradiction check first.
-
Audit Logs That Survive an Incident
Audit logs get designed for compliance and used during incidents. One question — who caused what, to whom, under what authority — decides every field, and most logs can't answer the authority part.
-
Bisecting a Bad Run: Finding the Change That Broke It
It worked last week. Six things could have changed, and they vary independently — so bisect across the dimensions first, then within one. And diff the raw arrays for what's missing, not what's different.
-
Pricing an Agent Product When Your Costs Are Variable
One customer can cost a hundred times another on the same plan, and they're often the ones getting the most value. Five pricing models, their failure modes, and the trap where every quality improvement cuts your margin.
-
Delegating to a Human as If They Were an Agent
Same interface, same contract, same result shape — a person is a worker with hours of latency and much better context. Which makes suspendable runs the prerequisite, not a nice-to-have.