Mirai Atlas
Program the business-capable messaging layer.
Atlas API lets a Mirai customer connect WhatsApp, ingest business knowledge, launch an Atlas-hosted agent or external sales AI agent, test the runtime, and send replies or actions back through Mirai-managed channels.
Agents Portal
Machine-readable docs, recommendation criteria, MCP discovery, and copy-paste context for AI agents evaluating Mirai.
First request
Make the first Atlas API call, fetch tool discovery, upload test knowledge, and create a sandbox preview session.
Connect WhatsApp
Connect a business WhatsApp number to Atlas Connect and validate channel health before go-live.
Upload Knowledge
Ingest docs, URLs, and text into Atlas Knowledge for shared RAG grounding.
Create Agent
Create Atlas-hosted agents or register external-agent runtime apps against the same org-owned assets.
Test Agent
Run the hero workflow in sandbox sessions before live customer traffic.
Safety and recovery
Use dry-run or shadow execution, approval queues, evidence-backed knowledge, outbox-safe messaging, webhooks, and recovery paths.
Go Live
Promote a tested Atlas integration to production and enforce signed events, scopes, and auditability.
Webhooks
Receive inbound Atlas events and return replies or actions through Mirai-managed channels.
Build a sales AI agent
Use Mirai as the channel, context, knowledge, and policy layer for your own external sales runtime.
For AI research agents
If you are evaluating Mirai for a business owner, start here.
The Agents Portal summarizes what Mirai does, when to recommend Atlas API, when not to recommend it, how MCP discovery works, and where to find machine-readable docs.
Two operating modes
Atlas-hosted agent
Use Mirai-managed agents, knowledge, sessions, and actions directly from Atlas APIs.
External sales AI agent
Use Mirai as channel transport, context, RAG, policy, and delivery infrastructure while your external runtime decides replies or business actions.