WHITEPAPER v4.0

AI Butler: Software That Thinks

Not just another chatbot. A lightweight personal software platform powered by AI — controlling your PC, phone, and smart glasses from one hub.

February 2026 · ABIS Information System · v4.0

FREE
Base Product
¥1/mo
Subscription
6
AI Services
3
Devices

Table of Contents

  1. Executive Summary
  2. The Problem
  3. Product Vision — Software, Not Chatbot
  4. Architecture — 6-Layer Platform
  5. Multi-Agent System
  6. Device Hub — PC as Brain
  7. DashScope AI Platform
  8. Business Model
  9. Competitive Analysis
  10. Roadmap
  11. Technology Stack

1. Executive Summary

"This is not an LLM. It's software that utilizes the LLM."

AI Butler is a personal software platform for Windows desktops that uses artificial intelligence as its engine — not its product. While competitors build chatbots, AI Butler builds a software ecosystem where AI is one of many tools that help you get things done.

The platform is free at its core — local AI (Ollama), voice control (Edge TTS + Whisper), smart browser, and task management cost zero. For users who want cloud-grade AI (Alibaba Qwen), the platform offers pay-per-use access at 2x cost with 30% consumer rewards through referrals.

What makes AI Butler unique is its multi-device architecture: the PC is the brain, while phones (WeChat Mini Program) and smart glasses (Alibaba S1 via MCP) serve as input/output endpoints. One AI, one account, all your devices.

Key Differentiators:
  • Free local AI — Ollama runs on your hardware, no server cost
  • Software, not chatbot — AI takes actions via function calling, not just answers
  • Multi-device hub — PC + Phone + Smart Glasses, one unified AI
  • ¥1/month subscription — 1/145th the price of ChatGPT Plus
  • 30% consumer rewards — Users earn from referrals and ad revenue

2. The Problem

Today's AI assistants force users to choose: powerful but expensive (ChatGPT Plus at $20/mo), or free but limited (basic tools without intelligence). Furthermore, every AI assistant is essentially a chatbot — it answers questions but cannot take real actions on your behalf.

The Chatbot Trap

Current AI products are language models wrapped in chat interfaces. You ask, they answer. But real productivity requires action: creating calendar events, comparing prices, generating images, controlling devices. A chatbot that can't execute is just a fancy search engine.

The Device Silo

Your phone has Siri, your PC has Cortana, your browser has ChatGPT. None of them talk to each other. Your AI context is fragmented across devices. There is no unified personal AI that follows you from desktop to phone to glasses.

The Pricing Wall

ChatGPT Plus costs $20/month (~¥145). Claude Pro costs $20/month. Kimi Pro costs ¥59/month. For the average Chinese user, spending ¥100+ per month on AI is not justified for occasional use. The industry needs a ¥1 tier.

3. Product Vision — Software, Not Chatbot

"The foundation is free, but the extensibility is incredible."

AI Butler is a desktop application that happens to use AI, not an AI that happens to have a desktop interface. The distinction matters:

Chatbot ApproachSoftware Approach (AI Butler)
User asks, AI answersUser states intent, system executes
Text in, text outText/voice/image in, actions out
Single device (web/app)Multi-device hub (PC + Phone + Glasses)
Cloud-dependentLocal-first, cloud-enhanced
$20/month minimumFree base, ¥1/month cloud

The AI engine (DashScope Qwen) is like the engine in a car — essential but invisible. What the user sees is a personal productivity platform with a character-driven UI, voice interaction, smart browsing, task management, media creation, and device control.

4. Architecture — 6-Layer Platform

+------------------------------------------------------------------+ | Layer 5: DEVICE HUB | | PC (Brain) --- Phone (WeChat Mini) --- S1 Glasses (MCP) | | WebSocket --- Butler Device Protocol --- Device Registry | +-------------------------------+----------------------------------+ | Layer 4: SKILL MARKETPLACE | | Built-in: Price Compare, Auto-Login, Blog Writer, Scraper | | + Marketplace (Developer 70% / Platform 30%) | +-------------------------------+----------------------------------+ | Layer 3: AGENT LAYER | | Router Agent --> Secretary | Analyst | Creator | Controller | | Function Calling = AI takes actions, not just answers | +-------------------------------+----------------------------------+ | Layer 2: AI ENGINE | | Local: Ollama (FREE) | Cloud: DashScope Qwen (Booster) | | Streaming (SSE) | Deep Thinking | Tool Use | +-------------------------------+----------------------------------+ | Layer 1: CORE ENGINE | | PyQt5 Widget | Auth (WeChat) | Payment (Alipay/WeChatPay) | | Settings | Vault | Edge TTS | Whisper STT | Auto-Update | +-------------------------------+----------------------------------+ | Layer 0: OS INTEGRATION | | System Tray | Global Hotkeys | Filesystem | Clipboard | DPI | +------------------------------------------------------------------+

Each layer is independent and extensible. Layer 0-1 provide the foundation. Layer 2 powers intelligence. Layer 3 enables action. Layer 4 adds capabilities. Layer 5 connects devices.

5. Multi-Agent System

The multi-agent architecture transforms AI Butler from a chatbot into software. Instead of just generating text, the AI can call functions — creating todos, generating images, comparing prices, opening URLs, and controlling devices.

Router Agent

A single Router Agent receives all user input and dispatches to the appropriate tools via DashScope's function calling API. In v4.0, one agent handles everything. As tools grow beyond 20, specialized agents (Secretary, Analyst, Creator, Controller) are activated.

Tool Categories

AgentToolsExamples
Secretarycreate_todo, set_reminder, search_calendar, send_notification"Add grocery shopping to my todo list"
Analystweb_search, analyze_image, summarize_document, price_compare"Compare AirPods prices on Taobao"
Creatorgenerate_image, generate_video, text_to_speech, clone_voice"Create a poster for my shop"
Controlleropen_url, run_skill, control_device, capture_screen"Open Taobao and search for headphones"

Growth Strategy

v4.0 1 Router Agent + ~15 tools. AI selects the right tool automatically.
v4.1 Specialized agents activated when tools exceed 20. Intent classification first, then delegation.
v4.2 Multi-agent collaboration. Secretary checks calendar, Analyst researches, Controller sets reminders — all in one conversation.

6. Device Hub — PC as Brain

"Control your glasses, phone, and computer — all through one butler."

Butler Device Protocol (BDP)

All device communication uses a unified JSON protocol:

{
  "bdp_version": "1.0",
  "device_type": "pc | phone | glasses | web",
  "msg_type": "intent | response | notification | sync",
  "payload": { ... },
  "auth": { "token": "jwt" }
}

Channel Architecture

ChannelProtocolTarget
LOCALPyQt5 SignalsPC (native widget)
WEBSOCKETWSSPhone / Web client
MCPBLE + Wi-Fi DirectS1 Smart Glasses
HTTPHTTPS RESTGeneric IoT / 3rd party

Phone: WeChat Mini Program

Instead of a native app, AI Butler connects to phones via a WeChat Mini Program — zero installation for 1.3 billion WeChat users. Chat sync, todo sync, file transfer, voice commands, and referral sharing are all built in.

Glasses: Alibaba S1 (MCP)

The PC is the brain. S1 glasses are sensors and display endpoints. Camera frames flow to DashScope Vision AI via the PC. Microphone audio goes through local STT. Responses return as TTS audio and display overlays. Same DashScope API key, zero additional cost.

7. DashScope AI Platform

DashScope (百炼) by Alibaba provides 6 AI services under a single API key:

ServiceModelCost (Platform)User Price (2x)
AI Chat (Deep Thinking)Qwen3-Max¥2.5~10/1M tok¥5~20/1M tok
AI Chat (Economy)Qwen-Turbo¥0.3~1.2/1M tok¥0.6~2.4/1M tok
Image GenerationWan2.6-T2I¥0.2/image¥0.4/image
Video Generation (720p)Wan2.6-T2V¥0.6/sec¥1.2/sec
Text-to-SpeechQwen3-TTS¥0.8/10K chars¥1.6/10K chars
Vision AnalysisQwen-VL-Plus¥2~5/1M tok¥4~10/1M tok
Why DashScope?
  • Single API key for ALL services — text, image, video, voice, vision
  • Same platform as Alibaba S1 glasses — native ecosystem integration
  • Qwen3-Max: 65K context, deep thinking mode, competitive with GPT-4
  • China-native infrastructure — low latency for primary market

8. Business Model

Three Revenue Streams (Completely Separate)

StreamTypePriceMargin
SubscriptionFixed monthly/yearly¥1/key/mo or ¥10/key/yr~100%
BoosterPay-per-use AI2x DashScope cost~20%
ProductsOne-time purchase¥5~2060~100%

Free Tier (Forever Free)

Local AI (Ollama), Edge TTS, Whisper STT, basic character, todos, browser, 3 languages — all permanently free. The free tier is a fully functional local AI assistant that runs on the user's hardware at zero cost to the platform.

30% Consumer Rewards

Every booster payment returns 30% to the ecosystem: 20% to the direct referrer, 10% to the second-level referrer. Earnings auto-reload into booster balance, creating a "free AI" experience for active referrers.

Growth Flywheel

Free local AI (hook) → Quality gap (try booster) → Top-up ¥10 → Referral rewards (share) → Auto-reload balance ("free AI" feeling) → Multi-device stickiness (can't leave) → More referrals → Viral growth

9. Competitive Analysis

PlatformFree TierPaid TierOur Advantage
ChatGPT PlusLimited GPT-4o-mini$20/mo (~¥145)1/145 price, desktop-first
Tongyi QianwenDaily limits~¥19/moUnlimited local AI + multi-device
DeepSeekFree chat¥0.14/1M tokComplete software (UI+voice+skills)
Doubao (ByteDance)Daily limitsSubscriptionDesktop + phone + glasses
Kimi (Moonshot)Free long-context¥59/moFunction calling + local AI fallback
Unique Position:

AI Butler is the only desktop-first AI platform that combines local AI, cloud AI, multi-agent function calling, and a 3-device ecosystem (PC + Phone + Glasses) — at 1/145th the price of alternatives.

10. Roadmap

Phase A: Week 1-2

Core Experience

SSE streaming responses, balance top-up UI, 3-tier model selection, dark mode. Users feel "real AI".

Phase B: Week 3-4

Function Calling = Software Transformation

DashScope tools parameter, tool registry, skill-to-tool conversion, client-side tool execution. AI takes actions.

Phase C: Week 5-6

Media UI + Payment Completion

Image/video generation UI, WeChat Pay integration, subscription status dashboard, referral link generation.

Phase D: Week 7-9

Device Hub Server

WebSocket endpoint, device registry, BDP message router, context sync engine, push notifications.

Phase E: Week 10-13

WeChat Mini Program

Phone connected. Chat sync, todo sync, file transfer, referral sharing — all via WeChat.

Phase F: Week 14-20

Smart Glasses + Marketplace

S1 MCP adapter, vision/audio pipeline, skill marketplace UI, developer SDK, ad integration.

11. Technology Stack

ComponentTechnology
Desktop ClientPython 3.11 + PyQt5
Server BackendFastAPI + PostgreSQL + Uvicorn
AI Engine (Cloud)DashScope (Alibaba) — Qwen, Wan, TTS, VL
AI Engine (Local)Ollama (llama3, qwen2, mistral)
VoiceEdge TTS (free) + DashScope TTS (premium) + Whisper STT
AuthenticationWeChat OAuth 2.0 + JWT
PaymentAlipay RSA2 + WeChat Pay V3
Phone ClientWeChat Mini Program (WXML/WXSS/JS)
Device ProtocolBDP v1.0 (WebSocket + MCP)
InstallerPyInstaller + InnoSetup