Loading post…
CursorMichael TruellExplainer
The third era of AI software development
Summary
The post describes a third era of AI-assisted software development, in which autonomous agents handle larger tasks over longer timescales while developers define problems and review results. It traces a progression from Tab autocomplete, to synchronous prompt-and-response agents, and then cloud-based agents running on separate virtual machines. These agents can iterate and test for hours, returning logs, video recordings, and live previews that make parallel work and artifact-based review practical. Cursor reports that 35% of its internally merged pull requests are created by agents operating autonomously in cloud VMs, and that agent users now outnumber Tab users two-to-one after usage grew more than 15x in a year. The post says broader adoption still depends on reliable tests, environments, tools, and context, while developers shift toward decomposition, review, and feedback rather than line-by-line guidance.
Context
AI-assisted development is shifting from keystroke-level autocomplete and synchronous agent interactions toward autonomous agents that can work independently on larger tasks over longer periods. The post frames this as a move from writing code directly to building and supervising a software-production factory.
Approach / What changed
Cloud agents run independently in virtual machines, allowing developers to delegate tasks and run multiple agents in parallel. Agents iterate and test for hours, then return reviewable artifacts such as logs, video recordings, and live previews; developers provide initial direction, tools and context, problem breakdowns, review criteria, and feedback.
Takeaways
Cursor reports that 35% of its internally merged pull requests are created by agents operating autonomously in cloud VMs.
Cloud agents return logs, video recordings, and live previews, making parallel agent work practical without reconstructing every session from scratch.
Wider adoption still faces reliability challenges: flaky tests, broken environments, and incomplete access to the tools and context agents need.
Source and freshness
- Source
- cursor.com
- Published
- Added to Yomu
- Last updated
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.