Segment 16: Ryo Lu (Cursor): designing Cursor 3, Baby Cursor, and software that feels like play

• Timestamp: 05:33:27
• Duration: 22m 41s
• Livestream range: 05:33:27 → 05:56:08
• Transcript evidence: 44 chunks, about 3136 words

Actionable Insights

1. Turn designing Cursor 3 into an operating checklist. Turn the speaker’s idea into a concrete workflow: define the user, the input, the tool boundary, the review step, and the failure condition.
2. Separate capability from accountability. The recurring lesson in this chapter is that more capable AI changes who does the work, but not who owns the outcome. When applying it to agentic coding and software delivery, write down what the system may do autonomously and what still requires explicit human judgment.
3. Instrument the loop before scaling it. The useful operating loop is: capture context, let the tool act, review the result, preserve the learning, and tighten the next run. Write down acceptance criteria and review notes early so the workflow can be audited later.
4. Design for the failure mode, not the demo. The polished demo version of designing Cursor 3, Baby Cursor, and software that feels like play is less important than the places it breaks: weak context, unsafe permissions, weak evaluation, unclear ownership, latency, or poor human review.
5. Convert this into a agentic software delivery checklist. The durable takeaway from Ryo Lu (Cursor) is to turn “designing Cursor 3, Baby Cursor, and software that feels like play” into explicit operating rules: what the system may do, what it must prove, what evidence a reviewer needs, and where a human must stay accountable. The next useful artifact is a short checklist or eval case that someone can actually run.

What they actually use/show that is worth copying

• GitHub PR workflow: The agent is embedded in the existing delivery workflow. That makes review, testing, and handoff happen where the team already works.
• Slack agent factory: The agent is embedded in the existing delivery workflow. That makes review, testing, and handoff happen where the team already works.
• ChatGPT / AGI builder stack: The valuable part is preserving editability and taste. The tool is useful when it keeps design intent alive instead of producing generic one-shot output.
• Google shopping/travel UX: This is a concrete mechanism from the talk. The useful question is whether it reduces friction, improves reliability, or makes human review easier in a real workflow.
• Vercel framework/docs ergonomics: This is a concrete mechanism from the talk. The useful question is whether it reduces friction, improves reliability, or makes human review easier in a real workflow.
• Simular computer-use agents: The infrastructure choice affects product behavior. Latency, cost, routing, and model availability shape what kind of agent experience is actually possible.
• Cursor / Baby Cursor: The harness is the product. Model capability becomes dependable only when planning, tools, execution, review, and rollback are explicit.

Core thesis

Ryo Lu (Cursor) uses this chapter to make a specific argument about designing Cursor 3, Baby Cursor, and software that feels like play. The useful pattern is not just the named product or institution; it is how the segment exposes the new operating model for agentic coding and software delivery: humans keep taste, accountability, and deployment judgment while agents or models absorb more of the execution loop.

The chapter starts from this evidence: “Um, today I’ll share how we’re designing Cursor to bring designers, engineers back to our roots when making software felt more like play rather than being stuck in rigid roles, tools, or processes. also share how our design process became more fluid as we designed cursor with cursor.” That opening matters because it frames the segment as a concrete slice of the broader AIE Singapore Day 1 theme: agentic systems are moving from novelty demos into production workflows, institutions, creative tools, infrastructure, and embodied systems. The analysis should therefore be read as a nested talk-level packet, not as a generic summary of the entire livestream.

Comment insights

The extracted YouTube comments do not provide reliable speaker-specific audience reactions for Ryo Lu (Cursor). So this section should not pretend there is detailed sentiment about the talk. The useful audience-facing read is instead content-based: this segment is valuable for viewers who care about designing cursor 3, baby cursor, and software that feels like play, especially the concrete implementation choices and operating constraints called out in the transcript.

Deep research

The research value of this talk is the practical architecture behind designing Cursor 3, Baby Cursor, and software that feels like play. Ryo Lu (Cursor) is not only making a broad claim; the useful details are the concrete mechanisms named in the transcript: GitHub PR workflow, Slack agent factory, ChatGPT / AGI builder stack, Google shopping/travel UX, Vercel framework/docs ergonomics, Simular computer-use agents.

The main question to take away is how those mechanisms change the workflow. What becomes cheaper, what needs a stronger checkpoint, and what must remain human-owned? For this talk, the strongest evidence is in the speaker’s examples rather than in generic AI optimism. Use the named tools and operating choices as the starting point for further research, then validate whether the same pattern fits your own environment, security constraints, and evaluation loop.

Verdict

• The talk contains a specific operating lesson about designing Cursor 3, Baby Cursor, and software that feels like play: Agree. The speaker gives enough segment-level evidence to extract concrete implications rather than treating it as generic conference commentary.
• The named tools/examples should be copied blindly: Disagree. They are useful design references, but each needs to be checked against local security, data, latency, cost, and human-review requirements.
• The most valuable part is the concrete workflow detail: Agree. The strongest takeaways are the mechanisms, constraints, and examples the speaker actually names.
• The implementation details are transcript-supported: Agree. This page cites details such as GitHub PR workflow, Slack agent factory, ChatGPT / AGI builder stack, Google shopping/travel UX.
• Human accountability disappears when agents improve: Disagree. The recurring production pattern is to move execution into tools while keeping ownership, review, and failure handling explicit.

Screen-level insights

• 5:35:11 — opening frame: Ryo Lu (Cursor) frames the talk around designing cursor 3, baby cursor, and software that feels like play, with the useful setup being: “personal computing. He wrote the code that made it real. There’s a famous quote from him. The best way to predict the future is to invent it. He built working systems to prove his ideas. From UI to interaction models to the runtime, they were all one craft.”
• 5:35:44 — GitHub PR workflow: The talk shows or names this as part of the actual workflow. The relevant evidence is: “whole. Then something really weird happened, especially in the last decade. We’ve forked ourselves. We split into specialized roles. The designers owns the vision makes the mocks. The engineers implements the mocks.”
• 5:36:47 — Slack agent factory: The talk shows or names this as part of the actual workflow. The relevant evidence is: “they weren’t real. And then the PMs and collaboration also kind of scattered. You have Jira tickets that nobody wants to update. You have Google Docs for specs. And then we made notion for weeks and planning, Slack for everything else.”
• 5:34:08 — ChatGPT / AGI builder stack: The talk shows or names this as part of the actual workflow. The relevant evidence is: “software. In the beginning, software design and engineering were the same thing. There were no splits. The people who imagined software also built it. Design and code were the same craft. The material was the code itself.”
• 5:36:47 — Google shopping/travel UX: The talk shows or names this as part of the actual workflow. The relevant evidence is: “they weren’t real. And then the PMs and collaboration also kind of scattered. You have Jira tickets that nobody wants to update. You have Google Docs for specs. And then we made notion for weeks and planning, Slack for everything else.”
• 5:51:14 — closing implication: The later part of the talk turns the idea into a practical takeaway: “turn into the first PR that an engineer can build on top of in the real codebase. And it looks crazy good. It has a desktop. It has some wallpapers, themes, and we even built like a tool inside Baby Glass where you can generate mockups and videos.”

Verification notes

Verified against the extracted transcript for Ryo Lu (Cursor)’s talk on designing Cursor 3, Baby Cursor, and software that feels like play. The supported claims in this page are based on concrete tools/artifacts named in the talk: GitHub PR workflow, Slack agent factory, ChatGPT / AGI builder stack, Google shopping/travel UX, Vercel framework/docs ergonomics, Simular computer-use agents, Cursor / Baby Cursor. I treated auto-caption wording cautiously, kept only details that are explicitly present in the segment transcript, and avoided importing claims from adjacent speakers or from the overall conference description.