Agents for Humans

Automated excerpt

Not because it was told not to in a system prompt, but because it cannot. Only a plain Python function, triggered strictly by a human clicking Approve, can execute any writes. A date-matching check happily paired two unrelated date columns together because it only asked "does this look like a date," never "should these two go together. " Neither of these is a dramatic bug, but both would've been mortifying to demo if I hadn't caught them.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.