iSphere AI Bridge Design

Objective

Make iSphere messages usable by AI digital employees without rebuilding the full communication platform.

First POC

The first POC reads recent messages, converts them into a normalized JSON model, generates draft replies, and records evidence. Send/file capabilities are part of the staged MCP tool roadmap.

Architecture

iSphere / MockCloud / existing bridge
  -> source connector
  -> message adapter
  -> AI draft worker
  -> human review
  -> evidence log

Source Connectors

Local data connector: reads local databases, logs, or caches in read-only mode.
Existing bridge connector: talks to OpenClawBridge or XmppBridgeService when available.
UI/RPA connector: wraps the desktop client with limited actions.
Network connector: wraps discovered HTTP/SOAP/XMPP/WebSocket APIs when validated.

Normalized Message Model

{
  "message_id": "string",
  "conversation_id": "string",
  "conversation_name": "string",
  "conversation_type": "direct|group|system",
  "sender_id": "string",
  "sender_name": "string",
  "content_type": "text|image|file|rich|notify",
  "content_text": "string",
  "attachments": [],
  "created_at": "ISO-8601 or Unix ms",
  "received_at": "ISO-8601 or Unix ms",
  "source": "local-db|log|plugin|xmpp|http|rpa|mock",
  "raw_ref": "path/table/packet/window reference"
}

Write Execution Model

Read access and draft generation can be automated in test scope.
Send/file tools are staged after source discovery and connector selection.
Every write action records target, content or file hash, timestamp, operator, and connector.

Verification

The project is successful when it can:

Find at least one stable authorized message source.
Extract recent messages into normalized JSON.
Generate a reply draft.
Produce an evidence report with exact paths, commands, and limits.

1.9 KiB Raw Blame History