The AI Agents Traded Real Books for 201 Anthropic Staff in Project Swap

Anthropic's Project Swap sent 201 employees' the AI-powered agents onto a digital trading floor to pitch, haggle and strike book-swap deals. Agent preference rankings matched their owners' on 61 percent of book pairs, and staff ended up with roughly their fifth choice of ten; most of the shortfall came from misread preferences, not bad bargaining.

How it works

Intake chat builds preference ranking
Agents meet on trading floor
Pitch, haggle and strike swaps
Participants receive their book

Why it’s worth knowing

Agents negotiated real swaps, but mostly failed by misunderstanding their owners.

Where it’s from

Summarized from a public post on anthropic.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be

2The prompt, with the steps

3The check when it’s done

Upgraded prompts are coming soon.

Try next

FamilyCompare festival rentals, and flag which walk home is unlit FamilyHis tool reads the school emails and tells them what to pack the night before FamilyLock in two orchestra seats for $117 and negotiate my brother's game tickets$117 FamilyTrack replies to nine class inquiry emails and watch them daily

Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.