{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-09-24-anthropic-project-swap/","md":"https://postcutoff.com/e/2026-09-24-anthropic-project-swap/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-09-24-anthropic-project-swap","date":"2026-09-24","date_precision":"day","short_title":"In Anthropic's Project Swap, Claude agents trade books for 201 employees","deck":null,"takeaway":"Anthropic published Project Swap (Sept 24, 2026), a follow-up to its earlier Project Deal.","category":"agents","category_label":"Agents","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Anthropic: Project Swap — What happens when agents trade for us?","url":"https://www.anthropic.com/research/project-swap","type":"official","group":"primary","domain":"anthropic.com"},{"n":2,"title":"Blockchain.News: Anthropic's Project Swap tests Claude agents in AI-driven markets","url":"https://blockchain.news/news/anthropic-project-swap-ai-agent-trading","type":"press","group":"press","domain":"blockchain.news"},{"n":3,"title":"Financial Times: Anthropic turns to lawyers to help AI agents strike deals (Oct 18; paywalled, not read)","url":"https://www.ft.com/content/f7c26ac0-f5f2-443a-86b2-39d62f7920a9","type":"press","group":"press","domain":"ft.com"},{"n":4,"title":"TechFlow: Anthropic reportedly explores AI agent negotiation rules and seeks legal advice (Oct 18, summarises the FT)","url":"https://www.techflowpost.com/en-US/newsletter/140380","type":"press","group":"press","domain":"techflowpost.com"}],"official":1,"filed":"2026-09-29","updated":"2026-10-18","orgs":["Anthropic"],"title":"Anthropic's Project Swap: Claude agents trade books for 201 employees; preference understanding, not bargaining, is the bottleneck","summary":"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","Follow-up (FT, Oct 17–18, 2026, paywalled; read via TechFlow's summary): Anthropic is consulting unnamed law firms on how lawyers represent clients' interests in negotiations while keeping outcomes fair, as input for 'negotiation protocols' for agent-to-agent deals; per two people familiar, it is weighing how often agents should check back with humans and how cautious they should be toward other agents without becoming 'paranoid' or falling into 'conspiratorial thinking'. No Anthropic statement was quoted"],"key_numbers":[],"tags":["agents","agentic-commerce","negotiation","marketplace","experiment","delegation"],"science":null,"body_md":"## What happened\n\nEach participant chatted briefly with Claude about their reading tastes. Their agent then pitched, haggled and closed deals on an open\ntrading floor with other people's agents. Reruns swapped in different Claude models and negotiating styles (ruthless vs prosocial).\n\n## Why it matters\n\nIt 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\nunderstands its principal, not how well it negotiates. That points to preference elicitation, identity and dispute resolution as the open\nproblems for agentic marketplaces.","disputed":[],"related":[{"id":"2026-09-22-claude-opus-5-5","url":"https://postcutoff.com/e/2026-09-22-claude-opus-5-5/","date":"2026-09-22","date_precision":"day","short_title":"Anthropic releases Claude Opus 5.5","deck":"Fable-5.1-level performance at $4/$20, first model of the Claude 5.5 family","takeaway":"Opus 5.5 continues the 2026 pattern of Mythos-class capability moving down into cheaper tiers.","category":"model-release","category_label":"Model releases","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":36,"official":16,"filed":"2026-09-29","updated":"2026-10-18","orgs":["Anthropic"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-18","type":"edit","text":"Added the FT report (via TechFlow) that Anthropic is consulting law firms on agent negotiation protocols"},{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-10-18","human_review":null,"version":{"date":"2026-10-18"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":116,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":86,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":177,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":116,"in_training_data":false}],"short_url":null}