High Signal Podcasts Evidence ledger
Method
Browse
← Back to evidence

Evidence receipt / belief

Published · transcript-backed

Alessio Fanelli: belief

6 Sept 2023 Latent Space The Point of LangChain — with Harrison Chase of LangChain

“The difference I think at the Databricks keynote, you said chains are like predetermined steps and agents is models reasoning to figure out what steps to take and what actions to take.”

— Alessio Fanelli

Source trail

Everything needed to verify it.

Speaker
Alessio Fanelli
Attribution
Verified speaker
Claim type
belief
Recorded
6 Sept 2023
Publisher
Latent Space

Transcript context

…No, thanks for coming. That was a good one. And on the website, you list like RAG, which is retrieval of bank debt generation and agents as two of the main goals of LangChain. The difference I think at the Databricks keynote, you said chains are like predetermined steps and agents is models reasoning to figure out what steps to take and what actions to take. How should people think about when to use the two and how do you transition from one to the other with LangChain? Like is it a path that you support or like do people usually re-implement from an agent to a chain or vice versa? Yeah.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.

Search evidence