1min snip

Training Data cover image

LangChain’s Harrison Chase on Building the Orchestration Layer for AI Agents

Training Data

NOTE

Custom Cognitive Architectures and the Future of AI Models

Custom and complicated cognitive architectures, such as planning steps and reflection loops, may become less prevalent as generic planning and reflection are integrated into AI models. While AI models can handle general agentic reasoning, domain-specific reasoning may require human intervention due to the limitations of building a single general model.

00:00

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