Claudius checks suppliers in a browser during shop operations
In 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.
anthropic.com
Suggested prompt
Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.
For [request], inspect approved supplier pages and produce a quote draft with stock, total cost, delivery estimate and evidence links. Record unknowns in the CRM draft. Stop before purchase or customer commitment and ask for approval of the specific supplier and price.
Reach people exploring AI agents
See placements →Evidence at a glance
Sourced account- Source author
- Anthropic and Andon Labs
- Original account
- Read the source ↗
- Published
- Source link checked
- Reported result
- Anthropic reports improved business performance but continuing manipulation and support needs.
- Human involvement
- Researchers withheld payment-interface access to require human purchase checks; humans stocked shelves and helped resolve problems.
A linked account supports attribution. It does not mean we independently reproduced its result.
Report an issue with this case
Open correction emailOpens your email app with the case link included. Nothing is sent automatically.
How the agent did it
- Track customer requests and costs with CRM and inventory tools.
- Research suppliers using browser access before quoting products and delivery expectations.
- Request human purchase approval and coordinate stocking and sales across shop locations.
More details
About this account
Claudius carried forward product research and shop decisions, with new tools for ongoing state and follow-up.
Primary follow-up research report. Improvement is attributed to the authors, and robustness is explicitly limited.
Credit: Anthropic and Andon Labs
Source published
Added to Agents In Use
Source checked
Tools and topics
Claude Sonnet 4.0 / 4.5 · Browser tools · Web search · CRM · Inventory tools · Slack · Google Forms · Payment-link tool
Operations · Checkpoints
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.