← All experiments

No. 014 · Week 37 · Michael Taylor · Productized

Checks

An app for hosting personal benchmarks, where your agent runs pass/fail checks on real tasks.

Can each person have a benchmark built from their own tasks, with simple yes/no checks an agent can run?

Checks, image 1

See the rest of the write-up and 1 link.A free Every account opens this. Nothing to buy.