WhatsApp AI Agent
LiveConversational AI over WhatsApp powered by the Generic Agentic Runtime shell (ADR-038). Replaces command rules with LLM intelligence: every inbound message drives a ReAct planning loop that can use connector tools to take real actions, then replies directly in the chat.
2 capabilities
WhatsApp AI Agent is an AI agent that runs as an isolated pod on Zervanor, in the same runtime as your workflows (operations). Conversational AI over WhatsApp powered by the Generic Agentic Runtime shell (ADR-038). Replaces command rules with LLM intelligence: every inbound message drives a ReAct planning loop that can use co Your connectors become its tools — deploy it in a few clicks, with agent hosting included in the plan.
Runs as an isolated pod, in the same runtime as the workflows.
Capabilities 2
Actions this agent can use in your workflows.
send_message
Send a WhatsApp text message to a phone number or JID
run
Run the AI agent against a natural-language goal (webhook mode).
Frequently asked questions
What does WhatsApp AI Agent do?
Conversational AI over WhatsApp powered by the Generic Agentic Runtime shell (ADR-038). Replaces command rules with LLM intelligence: every inbound message drives a ReAct planning loop that can use co
How is WhatsApp AI Agent run?
The engine runs it as an isolated pod; no separate infrastructure, and it sits in the same runtime as the workflows.
Which tools can WhatsApp AI Agent use?
Every action of your certified connectors becomes one of its tools (2+ capabilities) — for example: send_message, run.
Where does the agent run?
In the same runtime as the workflows, as an isolated pod — not on separate infrastructure and not as a separate product.