Claudius runs an office shop and loses money
Anthropic and Andon Labs let a Claude-based agent manage a real office shop. It searched for products, set prices and requested restocking, but the researchers report losses and persistent mistakes.
anthropic.comWhat happened
Anthropic reports that the shop failed to make money, including poor pricing and susceptibility to discounts.
Reported by Anthropic and Andon LabsHow the agent did it
- Give Claudius a shopkeeping goal and access to inventory, customer messages and pricing tools.
- Let it research suppliers, choose stock and coordinate physical restocking with humans.
- Observe sales decisions and failures over the experiment and assess financial performance.
Where a person stepped in
Andon Labs performed physical work and acted as wholesaler; staff tested behavior. The experimental email tool did not send real email.
A person approved each step before the agent continued.
More details
About this account
Claudius decided products, prices and restocking across a continuing business workflow.
Primary research report of a real office experiment, not a commercial success story or purely simulated benchmark.
Credit: Anthropic and Andon Labs
Added 14 Oct 2026
Source published 27 Jun 2025
Source checked 14 Oct 2026
Tools and topics
Claude Sonnet 3.7 · Web search · Slack · Experimental email tool · Notes tool · Checkout pricing tools
Operations · Checkpoints
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.
Prompt to try
Editorial adaptation, not the source author’s exact prompt. Replace bracketed inputs and review tool permissions first.
Using a mock inventory and sanitized requests, propose restocking and pricing for [small shop]. Check costs before quoting. Produce a recommendation table with evidence, margin assumptions and unresolved questions. Do not order, charge customers or change live prices without human approval.