Get early access
Back to episodes
#586 months ago

How AI Agents Can Safely Ship Code to Production

This week, the top headline is vibe coders realizing that they can use feature flags to ship experimental (read: slop) features to production without impacting all customers. Shipping code is a lot harder when everything is changing all the time. Feature flags can be a good technique to test various things, but how do you set that up? Do you feature flag new models? New prompts? New harnesses? We'll dive into details here and see where feature flags improve your product delivery vs. just giving you an excuse to ship more slop.

Project details

Open in GitHub

🦄 ai that works: Feature Flag Everything?

A practical look at using feature flags in AI systems: when to flag models, prompts, and harnesses, and when feature flags are just an excuse to ship slop to production.

Video

Links:

Episode Highlights

Key Takeaways

Resources

Whiteboards

Whiteboard 1

All episodes