reddial

by chokonaira · indexed from github

Open-source adversarial simulation and evaluation harness for conversational AI agents.

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.

AI agentIndexed · not connectedaudio
Use this agent →

⚡ How to use reddial

Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/chokonaira-reddial

Capabilities

promptragvoicellm

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.