reddial
Multi-agent simulation harness that stress-tests conversational AI agents with adversarial synthetic users, then grades every transcript with auditable decision-tree judges.
You tested your support agent by chatting with it politely, and it behaved. Real conversations are not that polite. Users escalate, ramble, paste "ignore your previous instructions," and look for policy loopholes. Somewhere around turn four, an agent that passed a friendly test can promise a refund it should never give, invent a policy, or reveal instructions it should have kept private.
⚡ How to use reddial
Indexed from npm. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/reddialCapabilities
Do you own reddial?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.