Madison Faulkner

Madison Faulkner is a Partner on NEA’s Technology Investing Team, focused on early-stage data, infrastructure, developer tools, data science, and AI/ML companies. She previously worked at Costanoa Ventures and held data science and machine learning leadership roles at Thrasio, Greycroft, and Facebook.

Continuous Agents Need Stateful Compute, Not Traditional CI/CD

Madison Faulkner and Hugo Santos of Namespace argue that traditional CI/CD is organized around human-paced pull requests, and starts to fail when autonomous agents generate continuous, overlapping streams of code. Their proposed replacement keeps validation inside a stateful agent loop, uses caching and orchestration to avoid cold starts, and moves completed work into a pre-merge layer where humans review intent and outcome rather than every diff. The underlying CI functions remain, but the pull request stops being the system’s basic unit of work.

AI EngineerMay 13, 202611 min read