Humans helped prioritize 38 ideas, then agents implemented the changes, trained models, debugged failed runs, and evaluated the results.
Ryan DrapeauMachine learning engineer, Intelligent Commerce · Practitioner, 
Stripe
Post: Stripe developer blog, Stripe developer blog, October 19, 2026.
Ryan Drapeau, Machine learning engineer, Intelligent Commerce. Works on Intelligent Commerce at Stripe and wrote the post; an employee describing results the employer chose to publish.
Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-10-31).
Exact match in the article body. The post is dated 2026.10.19 and lists Ryan Drapeau and Sai Samant as authors, so Drapeau is a co-author rather than the sole author. The post does not attribute this sentence to either one individually.
Ryan Drapeau (Stripe), “Stripe developer blog”, Stripe developer blog, 2026-10-19. https://stripe.dev/blog/scaling-radar-fighting-fraud-with-agent-assisted-machine-learning Archived at https://the-ai-record.com/passages/stripe-humans-helped-prioritize-38-ideas-then-agents-2026
Something wrong? Report a correction. JSON: /api/v1/passages/stripe-humans-helped-prioritize-38-ideas-then-agents-2026.json