Agents work across the experiment lifecycle. Engineers review hypotheses and results and decide what to deploy.
StripePublished by the organization itself (post), no named author
Post: Scaling Radar: Fighting fraud with agent-assisted machine learning, Stripe developer blog, October 19, 2026, at Giving agents the experiment lifecycle.
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, 2026-11-08).
Exact match under 'Giving agents the experiment lifecycle' on Stripe's developer blog, so these are the organization's own words.
Stripe, “Scaling Radar: Fighting fraud with agent-assisted machine learning”, Stripe developer blog, 2026-10-19, at Giving agents the experiment lifecycle. https://stripe.dev/blog/scaling-radar-fighting-fraud-with-agent-assisted-machine-learning Archived at https://the-ai-record.com/passages/stripe-agents-work-across-experiment-lifecycle-engineers-2026
We built Agentic MLE, short for machine learning engineer, to take on more of that work. It’s a set of tools and instructions that lets AI agents operate in Stripe's existing ML infrastructure, carrying an experiment from an idea to a result: explore the data, implement a feature, compute its historical values, train a model, and evaluate it against a baseline.
StripePublished by the organization itself (post), no named author
Post: Scaling Radar: Fighting fraud with agent-assisted machine learning, Stripe developer blog, October 19, 2026, at Giving agents the experiment lifecycle.
In a controlled comparison, the new configuration improved recall by over 8%, translating to an estimated tens of millions of dollars a year in additional fraud prevention for Stripe’s merchants.
StripePublished by the organization itself (post), no named author
Post: Scaling Radar: Fighting fraud with agent-assisted machine learning, Stripe developer blog, October 19, 2026, at Learning from a fraud attack.
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.
We organized this knowledge into reusable procedures for the platform and model-specific documentation that an agent loads for the task at hand.
StripePublished by the organization itself (post), no named author
Post: Scaling Radar: Fighting fraud with agent-assisted machine learning, Stripe developer blog, October 19, 2026, at Giving agents the experiment lifecycle.
Something wrong? Report a correction. JSON: /api/v1/passages/stripe-agents-work-across-experiment-lifecycle-engineers-2026.json