All posts
Everything published here, newest first.
316 posts · showing 261–270
2026
10 posts-
Agents That Wait: Callbacks, Webhooks, and Long-Running Tools
A twenty-minute export breaks the assumption that tools return quickly. Handles, in-loop polling, and true suspension — plus the expiry field that stops suspended runs leaking forever.
-
Fan-Out, Fan-In: Parallelism Inside a Single Agent
Twelve independent checks shouldn't cost twelve turns, each re-sending the whole context. Three levels of parallelism inside one agent — and the fan-in is where the pattern usually goes wrong.
-
Why Two Identical Runs Give Different Answers
Same input, different result. Four things cause it, only one is a bug — and the most common culprit is that the input wasn't actually identical.
-
When the Worker Needs to Ask the Supervisor a Question
A blocked worker with no channel back will guess, and the guess is invisible in what it returns. Making "needs input" a result type costs nothing — and the questions it logs are a to-do list for your delegation template.
-
Migrating Model Versions Without Breaking Your Agent
The new model is better at nearly everything and different at everything, and tool selection is what shifts first. Replay a frozen eval set against both — and put the cost-per-task row in the comparison.
-
Model Routing: Using the Cheap Model for the Cheap Steps
Classification, extraction, and formatting move to a cheaper tier safely. Tool selection and planning don't — and the failure looks like a tool-description bug, so you'll debug the wrong thing for a week.
-
The Data-Cleaning Agent and the Column It Silently Dropped
It normalized the phone numbers, standardized the country codes, and quietly deleted 412 rows that looked untidy. Any task phrased as "make this better" reads as permission to remove what doesn't fit.
-
Designing a Kill Switch That Works Mid-Run
Killing the process leaves side effects in an unknown state. A stop that works checks between steps — before every model call and before every tool call — and the difference matters most at 2am.
-
Building an Eval Set From Production Traces
Hand-written cases test what you thought of. A user rephrasing the same request three times is a labelled failure sitting in your logs — here's how to turn a week of traces into a suite that catches the real ones.
-
Run, Session, or Global? Scoping Agent Memory Correctly
Too-small a scope produces a visible annoyance; too-large produces a silent wrong answer. One question assigns any fact correctly, and one rule keeps multi-tenant reads from becoming an incident.