The guardrails paradigm is like connective tissue between the different roles in a multi-agent system. It gives developers a lot of agency to think about specific problems that they're solving and you know what correctness means to them. But how do you do that dynamically when you're not the person who's creating these agents, setting their goals, et cetera? So yeah, it's a problem I'm very excited about and I think it's aproblem that needs to get solved before these agents are employable.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode