Skip to content
All tags

#genie

2 posts
aideep-diveReading Stanford CS224V Agentic AI

Task-Agent Evaluation Beyond Human-Like Answers | Stanford CS224V Lecture 4

CS224V splits task-agent evaluation into state updates and complete interaction: isolate the semantic parser, then test task completion, grounded queries, and valid actions with real users.

#cs224v#stanford#agent-evaluation#task-oriented-dialogue#genie
aideep-diveReading Stanford CS224V Agentic AI

Building Task-Oriented Agents with Genie Worksheets | Stanford CS224V Lecture 3

Genie Worksheets declare task capability as a form-like specification. A contextual semantic parser updates formal dialogue state while the runtime controls queries, actions, and responses.

#cs224v#stanford#task-oriented-dialogue#semantic-parsing#genie