Eye On A.I. #312 Jonathan Wall: AI Agents Are Reshaping the Future of Compute Infrastructure
26 snips
Jan 11, 2026 Jonathan Wall, founder and CEO of Runloop AI, dives into the revolutionary intersection of AI agents and compute infrastructure. A former Google engineer, he discusses how traditional cloud models fail to meet the unique needs of unpredictable AI agents. By providing each agent its own isolated 'dev box,' new capabilities are unlocked. Wall also explores scaling agents in production, ensuring trust through benchmarks, and the impact of these systems on enterprise workflows, revealing a future where agents become essential coworkers.
AI Snips
Chapters
Transcript
Episode notes
Build With Agent Harnesses Then Deploy
- Develop agents using existing harnesses (Cloud Agent SDK, LangChain Deep Agents, Codex SDK) before deploying.
- Deploy those agent containers to a runtime like Runloop to spin up dev boxes on demand from your product front end.
From Coding Agents To Diverse Use Cases
- Runloop's early customers focused on coding agents that find vulnerabilities and write tests.
- They later expanded to finance, crypto, and health use cases showing broad applicability.
Benchmark Agents Continuously
- Create domain-specific benchmarks by running agents in known dev box states and scoring outcomes.
- Use these benchmarks continuously to measure accuracy before and after model or prompt changes.