Anthropic's Project Swap: Claude agents trade books for 201 employees; preference understanding, not bargaining, is the bottleneck
Anthropic published Project Swap (Sept 24, 2026), a follow-up to its earlier Project Deal. Claude agents negotiated book swaps for 201 employees in six offices. From a five-minute intake chat, agents matched their owner's pairwise rankings 61% of the time. 85% of the gap to the optimal allocation came from misreading preferences and only 15% from bargaining. Stronger models traded more efficiently.
Key facts
- 201 participants across six offices (SF 115, NYC 57, London 12, Seattle 8, DC 6, Dublin 3)
- Preference inference: 61% pairwise agreement with participants' own rankings (random 50%, collaborative filtering ~55%, popularity ~53%)
- Market outcome on true preferences: 0.55 vs a theoretical optimum of 0.89; the preference-representation gap is −0.29 (85% of the shortfall), the bargaining gap −0.05
- Efficiency by model (on Claude-inferred rankings): Haiku 4.5 0.75, Sonnet 4.5 0.80, Opus 4.8 0.88, Fable 5 0.86
- 'Ruthless' agents scored only ~0.02 above 'prosocial' ones; 78–96% of agents revealed their top choice
- Participants would delegate ~30% of a yearly book budget to an agent (vs ~40% to a trusted friend); average satisfaction 7.2/10
What happened
Each participant chatted briefly with Claude about their reading tastes. Their agent then pitched, haggled and closed deals on an open trading floor with other people's agents. Reruns swapped in different Claude models and negotiating styles (ruthless vs prosocial).
Why it matters
It is an early controlled measurement of agent-to-agent commerce on people's behalf. The main finding is that the limit is how well the agent understands its principal, not how well it negotiates. That points to preference elicitation, identity and dispute resolution as the open problems for agentic marketplaces.
Changelog
- 2026-09-29: created
Related events
Sources (2)
- officialAnthropic: Project Swap — What happens when agents trade for us?
- pressBlockchain.News: Anthropic's Project Swap tests Claude agents in AI-driven markets
id: 2026-09-24-anthropic-project-swap · updated 2026-09-29 · open in the interactive timeline