CI/CD Is Dead, Agents Need Continuous Compute and Computers — Hugo Santos and Madison Faulkner

AI Engineer · Beginner ·🤖 AI Agents & Automation ·4h ago
Traditional CI/CD was built for humans pushing one or two diffs a week. Scale to thousands of autonomous agents opening PRs continuously and you get runner saturation, cold Docker builds on every branch, cache thrash, and a merge queue that starts behaving like a serialized database lock where time-to-commit becomes the actual bottleneck. Madison Faulkner and Hugo Santos (Namespace) lay out what replaces it: no PRs, just intent and plan fed into an agent loop with fast inline validation. Changes queue in a premerge layer where humans review intent-plus-outcome rather than diffs. The end state they're pointing toward is agents exploring multiple commits in parallel for the same plan, a multiverse where the tip of the repo is a moving target and the inner loop needs to be stateful and fast enough to keep up. Speaker info: - https://x.com/madsfaulkner - https://www.linkedin.com/in/madisonhfaulkner/ - https://www.linkedin.com/in/hugomgsantos/
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

Anthropic courts a new kind of customer: small business owners
Anthropic expands customer base to small business owners, offering new opportunities for AI adoption
TechCrunch AI
How I Built an Autonomous AI SIEM With 10 Neural Networks in 3 Months
Learn how to build an autonomous AI SIEM using 10 neural networks in a short period of time and why it matters for efficient security monitoring
Medium · Machine Learning
Can AI Help Swiss SMEs Survive the Productivity Challenge?
Discover how AI can boost productivity in Swiss SMEs and learn actionable steps to implement AI solutions
Medium · AI
OpenAI’s Agent Traces Just Made Pretty Demos Dangerous
OpenAI's Agent Traces makes demo support safer by allowing inspection of tool-call history, reducing potential support debt
Medium · AI
Up next
Introducing the W&B Agent, an AI Research Assistant built directly into W&B
Weights & Biases
Watch →