← back
Your Coding Agent Just Got Cloned And Your Brain Isn't Ready - Rustin Banks, Google Jules
Takeaway
Async cloud coding agents like Jules unlock parallel multitasking and multi-variation development, but require AI at both ends of the workflow to remain sane.
Summary
- Jules is Google's async coding agent launched at I/O; 40k public commits in first two weeks; each task gets its own cloud VM with cloned repo and tool access.
- Two parallelism patterns: multitasking (run N different backlog items concurrently) and multi-variation (same task with Jest vs Playwright, multiple drag-drop libraries) then pick the best.
- Demo on the AI Engineer Summit schedule site: parallel tasks added Jest tests, calendar export, AI summaries, accessibility audit, and Lighthouse fixes.
- Bookend AI is required: AI helps generate backlog tasks at the start and critic/merging agents handle the PR review burden at the end so humans aren't a bottleneck.
- Remote agents in the cloud unlock infinite scale and any-device development versus IDE-local agents.
- Success requires clear definitions of done so reviewers don't drown in PRs.
julesasync-agentsparallelism
Original description
Will the future engineer code alongside a single coding agent, or will they spend their day orchestrating many agents? Traditional development rewards synchronous focus. This session dives into the significant mindshift required to move from sequential coding to orchestrating parallel agents. We are the builders of ""Jules"", Google's massively parallel asynchronous coding agent (to be opened up in May). We'll share real-world insights from building Jules and explore how to rewire your brain for this powerful new ""post-IDE"" development paradigm. About Rustin Banks I'm Rustin, an AI Product Manager at Google Labs. I taught myself to program at age 12 using a compiler I purchased on AOL classifieds. As a teenager I hosted a popular bulletin board system (BBS) out of my cousin’s closet using salvaged 286 computers. I’ve always had a passion for making the world better using technology. When I saw AI write code I dedicated the rest of my career to AI coding. At Google labs I am lucky to explore the frontier of coding models and agents. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter