It speaks through WhatsApp
Kapso receives messages and sends replies through the official WhatsApp API, without rebuilding Meta plumbing.
Use Kapso for the WhatsApp infrastructure around your agent: official API access, message triggers, Workflows, webhooks, MCP, and human handoff.
A WhatsApp AI agent reads a customer message, uses business context and tools, then replies, waits, or hands off. In Kapso, it can run inside Workflows or connect from your own app over APIs and webhooks.
Kapso receives messages and sends replies through the official WhatsApp API, without rebuilding Meta plumbing.
Run Workflows, functions, webhooks, MCP tools, and external services from the conversation.
Escalate approvals, complaints, sensitive data, and low-confidence replies to a human.
From inbound message to reply or takeover.
A customer sends a message to your official WhatsApp number.
Kapso normalizes the event and delivers it to your app, workflow, or agent.
Your AI agent reads context, calls tools, and decides the next action.
When judgement is needed, route the conversation to a person with context.
Models are easy to call. Production WhatsApp needs events, logs, tools, approvals, and humans around the model.
Receive customer messages, delivery updates, failures, and read status events through webhooks.
Send text, media, templates, reactions, locations, buttons, lists, and WhatsApp Flows.
Use Kapso WhatsApp MCP for live WhatsApp operations and CLI for shell workflows.
Keep ownership, history, and context available when a human takes over.
Create agents with WhatsApp triggers, Agent nodes, functions, waits, branches, MCP tools, and handoff.
Use sandbox projects, templates, approvals, logs, and human review for real-user sends.
Pick the surface that matches your architecture. Keep the first agent narrow and observable.
Use WhatsApp triggers, Agent nodes, functions, conditions, wait steps, and handoff when Kapso should own orchestration.
Workflow triggersUse the WhatsApp API and webhooks when your agent runtime already lives in your app.
API referenceUse Kapso WhatsApp MCP for live WhatsApp operations and CLI when shell access is the right interface.
Kapso WhatsApp MCP docsAgents should not trap customers. Kapso keeps the thread, owner, and operational context available when automation pauses.
Limit autonomy, ground answers, and make every operation reviewable.
Require opt-in, templates, and approval for real-user outreach.
Ground replies in docs, support articles, CRM records, and product data.
Track messages, webhooks, workflow runs, handoff, and retries.
The decisions teams make before putting an AI agent on WhatsApp.
No. A chatbot usually follows a fixed tree. An agent can use models, tools, memory, and workflow rules while staying inside WhatsApp policy and approval gates.
Yes. Use approved templates when required, and put sensitive real-user sends behind human approval.
Yes. Kapso provides WhatsApp conversations, webhooks, inbox tooling, workflow hooks, and logs so your app can pause automation and assign an owner.
Yes. Kapso Workflows can start from WhatsApp messages, use AI agent nodes, call tools, run functions, branch with conditions, wait for replies, and hand off to humans. Developers can also connect external agents through APIs, webhooks, CLI, and MCP.
Yes. Agents can use Kapso WhatsApp MCP for live WhatsApp operations and the Kapso CLI when they have shell access.
Connect WhatsApp, receive replies, call tools, and hand off when a person should take over.