Announcement
LangChain adds typed schemas to human-in-the-loop tool-call interrupts
A developer says the schemas validate human responses before they return to the agent and can help render approval forms.
TLDR
A developer says LangChain has revamped its human-in-the-loop middleware. Tool-call interrupts now ship with typed schemas that validate a human’s response before it goes back to the agent. The schemas can also be used to render approval forms in a user interface.
Combined views
3.2K
2 Sources, first seen ago