Google’s AlphaEvolve: The AI agent that reclaimed 0.7% of Google’s compute – and how to copy it

Its architecture – controller, fast-draft models, deep-thinking models, automated evaluators and versioned memory – illustrates the kind of production-grade plumbing that makes autonomous agents safe to deploy at scale. Until then, AlphaEvolve is a best-practice template: If you want agents that touch high-value workloads, you’ll need comparable orchestration, testing and guardrails. Google won’t put a price tag on the reclaimed 0.7%, but its annual capex runs tens of billions of dollars. A high-level overview of the AlphaEvolve agent structure. Over repeated cycles, the agent’s memory of success and failure grows, so it proposes better patches and wastes less compute on dead ends.