German tech media t3n: Iterating an AI agent through everyday language, without a development team
The t3n team published the complete process of building an advertising order-entry AI agent with Claude: using 10 real orders as samples, correcting errors in natural language within Slack, iterating to version 12 of the instructions within 24 hours, and skipping test boards to go live directly; manual effort dropped from up to 40 minutes for large orders to just 5–10 minutes for verification.
Advertising operations at German tech media outlet t3n involve a repetitive workflow: every closed deal generates a PDF order confirmation listing all services purchased by the client (such as podcast sponsorships or two sponsored articles). Each service requires a separate task, subtask, and deadline to be created in the Asana project management tool. As of mid-August 2026, this work was done manually by the campaign execution team, taking up to 40 minutes per large order.
Instead of relying on development resources, the t3n team asked Claude what materials were needed to automate this process. They provided brief process documentation and 10 real order confirmations, instructing Claude to compare its output against orders the team had already manually entered. From these discrepancies, the first version of the instructions emerged in a single afternoon.
The first version was insufficient for daily use. The team continued working in a Slack thread, pointing out errors in plain language, which Claude incorporated into its own instructions with each correction. After 24 hours, the instructions reached version 12. A key prerequisite was that the toolchain was already in place: Claude was connected to internal company tools, and the Asana board featured fixed fields and templates.
In mid-August, the agent went live with real orders; the team never created a test copy of the board. Since then, it has been sufficient to tag Claude in the Slack thread with the order confirmation. The agent automatically creates the tasks, while the team verifies the output: less than five minutes for simple orders, and up to ten minutes for large ones. The team reported no errors penetrating daily operations during the initial two-plus months.