#human-in-the-loop
Every post tagged "human-in-the-loop".
64 posts · showing 11–20
-
Designing an Agent You Can Redirect Mid-Run
Twelve files into forty, you realize the approach is wrong. Let it finish or kill it — both bad, and the third option had to be designed in before the run started.
-
The Screening Agent That Could Only Be Right
Every available metric said it was working — and every one of them was computed only from the candidates it advanced. The decision destroys the evidence needed to evaluate the decision.
-
The Skills That Were Always the Job
Almost nothing on the durable list is new. These are what experienced engineers always said mattered — the economics just didn't reward them proportionately until now.
-
Working With an Agent as a Pair, Not a Vending Machine
Describe, wait, review, repeat — the mode most people start in and the one that hits a ceiling fastest. The difference is fifteen seconds spent on what you know that isn't written down.
-
When to Stop Improving an Agent
There's always another failing case, so without a stopping rule the work either never ends or ends arbitrarily. The signal isn't the error rate — it's effort per point of improvement.
-
How to Run an Agent Pilot That Produces a Decision
Most pilots end without a decision because they were designed to produce a demo. Write the threshold before you build — and sort the failures by cause, because "no-go" and "fix one thing" look identical in the average.
-
Open Source After Cheap Contributions
Contribution effort rationed demand for maintainer attention. That rationing is gone and the attention is unchanged — but the filters that work test for something effort was only ever a proxy for.
-
Hiring Engineers When Take-Home Tests Are Meaningless
The signals didn't get noisier — they stopped measuring what they proxied for. The replacements test the right thing and are more subjective, which is a cost that lands on specific people.
-
What Changes for Product Managers
A role that existed partly to ration scarce engineering capacity changes when capacity stops being scarce — and the discipline of saying no gets harder, not easier.
-
Why "Just Add an Agent" Fails as a Product Strategy
Usage goes curious, then low, then the feature sits there — and the team upgrades the model, which doesn't help, because capability was never the problem.