Editing graph state Review We discussed motivations for human-in-the-loop: (1) Approval - We can interrupt our agent, surface state to a user, and allow the user to accept an action (2) Debugging - We can rewind the graph to reproduce or avoid issues (3) Editing - You can modify the state We showed how breakpoints support user approval, but don't yet know how to modify our graph state once our graph is interrupted! Goals Now, let's show how to directly edit the graph state and insert human feedback.
Autonomy
Semi-autonomous
Sandbox-aware
No declared sandbox guidance
Network access
Unspecified
Filesystem access
Unspecified
Permissions declared
Not declared
Pattern
Autonomous loop
Models
gpt-4oclaude-3-5-sonnetgpt-3.5-turbo