What it does
The example chooses a worker, rates risk and decides whether a person should approve the task before Herdr creates a workspace.
Benchmarks & research
Jev + Herdr: Practical AI Agent Orchestration
A practical guide and prototype for putting Jev triage in front of Herdr-managed coding agents.
Bookmark: Jev + Herdr: Practical AI Agent Orchestration
Keep this in your collection.
Leave a noteWhat would you try with this?
: Jev + Herdr: Practical AI Agent Orchestration
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
Your developer can adapt this guide to sort tasks for automated workers. The prototype code sends a new task to TypeSafe, an outside AI service. It asks the service to choose the best worker and rate the risk.
If the service labels an action dangerous, the script pauses and waits for a person. To run this test, your developer needs an access key that connects the software to TypeSafe.