Agents In UseThese work & operations AI agent use cases include accounts involving Claudius. Each entry links its source and describes the task, reported outcome and human checkpoint.
Examples include “Claudius checks suppliers in a browser during shop operations” (Claudius); “Claudius runs an office shop and loses money” (Claudius).
In “Claudius checks suppliers in a browser during shop operations”, Researchers withheld payment-interface access to require human purchase checks; humans stocked shelves and helped resolve problems. In “Claudius runs an office shop and loses money”, Andon Labs performed physical work and acted as wholesaler; staff tested behavior. The experimental email tool did not send real email.
4 use cases
anthropic.comIn the next office-shop phase, Claudius gained browser access, CRM and better inventory context. It checked supplier prices and delivery details while human purchase approval remained mandatory.
Added
Claudiusanthropic.comAnthropic 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.
AddedClaudiusInvestigate public supplier information, compare it against procurement criteria, and prepare an evidence-backed shortlist.
Added
Grok BotReview incoming messages, gather missing context, and turn requests into a prioritized queue of draft actions.
Added
Hermes AgentExamples include “Claudius checks suppliers in a browser during shop operations” (Claudius); “Claudius runs an office shop and loses money” (Claudius). Open each entry for the steps and reported outcome.
In “Claudius checks suppliers in a browser during shop operations”, Researchers withheld payment-interface access to require human purchase checks; humans stocked shelves and helped resolve problems. In “Claudius runs an office shop and loses money”, Andon Labs performed physical work and acted as wholesaler; staff tested behavior. The experimental email tool did not send real email.
The sourced entries in this category name Claudius. Open each account to see the tools used and the author’s reported result.
These accounts document particular runs rather than establish safety for every task. The recorded human checkpoints are: In “Claudius checks suppliers in a browser during shop operations”, Researchers withheld payment-interface access to require human purchase checks; humans stocked shelves and helped resolve problems. In “Claudius runs an office shop and loses money”, Andon Labs performed physical work and acted as wholesaler; staff tested behavior. The experimental email tool did not send real email. Review the linked source and permissions before trying an adapted prompt.