In this episode of AI That Works, we dive into the surprisingly simple world of building streaming systems! We give a masterclass in systems engineering and architecting, breaking down the process so that even a coding agent like Cursor can handle the heavy lifting.
We walk you through whiteboards, build a dynamic end-to-end application for fan-out and parallel async streaming of web page summaries. We share the code and show you how it works, so you can level up your UIs and push AI to its limits! We'll also discuss how you can ditch complicated front-end frameworks for simple HTML solutions – Claude can handle it.
Claude MD: https://docs.boundaryml.com/agents-md/claude-code
Check out our github: https://www.github.com/boundaryml/baml
AI That Works repo: https://github.com/ai-that-works/ai-that-works
Socials:
X: https://x.com/boundaryml
Discord: https://discord.com/invite/yzaTpQ3tdT
LinkedIn: https://www.linkedin.com/company/boundaryml/
⏱️ Chapters:
Intro
Coding Agents
Cloud Code Demo
Background Task Discussion
MCP Protocol Explanation
Summary Streaming
Cancellation System
Async Queue
Takeaways and Streaming
Transcript
I've watched this one closely. Ask me anything about it and I'll point you to the exact moment.