Stewart AI

System Architecture and Implementation Overview

Confidential - Stewart Miller Companies
BuddyPro Handles This
Needs Supplementary Work
Requires Custom Build

Stewart OS

The Intelligence Layer

↑ Knowledge In
↓ Answers Out
↔ Live Data
🔒 Access Control

The Short Version

BuddyPro was a smart starting point and it works for basic team chat via Telegram today. But the system you described, with role-based access across Ark, LiveWire, and Stewart Miller Company, live Mindbody data, daily automated SOP updates, and eventually a public coaching product and coach cloning platform, goes beyond what BuddyPro was designed for.

This page maps out your full vision, shows where BuddyPro fits and where custom work is needed, and lays out a phased plan to build Stewart OS over the next 90 days and beyond.

Next step: Review this together on a call, align on Phase 1 scope, and get building.

1
Business Entities
🏋

Ark Gym

Dubai. Launch August/September 2026. Member management via Mindbody. SOPs for operations, pricing, membership rules, staff policies. Knowledge isolated to gym-authorized staff.

🎥

LiveWire Productions

Digital content and production. Customers: gym equipment manufacturers and gyms globally. AI lip sync, set building, logo integration, video production. Six years of content, three years as LiveWire.

🏢

Stewart Miller Company

Umbrella entity. Cross-company policies, financial data, strategic plans, C-suite intelligence. Only accessible to senior management and above.

2
Knowledge Pipeline - How Information Enters the System
OneDrive
SOPs Created
→
Google Drive
Synced Copy
→
EA Validates
Stewart Approves
→
Stewart OS
Processed & Indexed
→
Team Access
Role-Filtered
Needs Work
📄

SOP Ingestion

New SOPs, company policies (visa, leave, pricing, membership rules, new staff). EA uploads daily after Stewart validates. BuddyPro uses Google Drive for ingestion: EA uploads files to a shared Drive folder, then runs /update in Telegram. No API for programmatic ingestion. Custom build can auto-detect new files and process them without manual steps.

Custom Build
📊

Mindbody BI Data

Member counts, retention rates, class attendance, revenue metrics. Requires a data integration to pull live data into the AI. BuddyPro's API is chat-only (no external data connectors). A custom data pipeline is needed to bridge Mindbody into the knowledge layer.

BuddyPro OK
📚

Static Knowledge Upload

PDFs, documents, training materials, recorded content, YouTube/Vimeo URLs. BuddyPro handles this well via Google Drive folder + /update command. Supports PDF, docx, txt, audio, video, images, Google Docs, and web URLs.

3
Access Control - Who Sees What
Custom Build

BuddyPro Cannot Do This

BuddyPro has a 3-tier role system (Owner, Team, End User) but this controls admin commands, not knowledge access. All users see the same knowledge base. There is no per-user knowledge filtering. To simulate tiered access, you would need multiple separate BuddyPro instances ($197/month each, plus per-message AI costs) with no unified management view. Even then, conditional visibility within an entity (management sees more than team) is not possible.

Person Role Ark Gym LiveWire Stewart Miller Co. Financial Data All SOPs
Stewart
CEO / Owner		 C-Suite ✓ ✓ ✓ ✓ ✓
Thushani
Executive Assistant		 Senior Mgmt ✓ ✓ ✓ ✓ ✓
Kim
Project Manager		 Senior Mgmt ✓ ✓ ✓ Ltd ✓
Dragon
Gym Operations		 Management ✓ Pub — — —
Chris
LiveWire Production		 Management Pub ✓ — — —
Gym Staff
Team Members		 Team Ltd Pub — — —
Public / Clients
Future Phase		 Public Pub Pub — — —
✓ Full Access Ltd Limited / Role-Specific Pub Public Info Only — No Access
4
Interface Layer - How People Access Stewart AI
BuddyPro OK
✈

Telegram Bot

Current interface. Team messages Stewart AI via Telegram. BuddyPro supports this today. Works for basic Q&A but lacks role-based filtering per user.

Custom Build
🌐

Web Dashboard

Admin view for Stewart and senior management. User management, knowledge base health, usage analytics, access control configuration. BuddyPro's analytics are accessed via Telegram /stats command (not a web dashboard). No visual admin interface for managing users or access levels.

Partially Possible
📱

Custom App (Matthew)

Stewart's son Matthew is building a custom app. BuddyPro does have an OpenAI-compatible chat API (api.buddypro.ai). Matthew's app could call it for chat. However: the API is stateful (all calls save to memory), has no multi-user support (no per-user identity), and the owner can read all test profile conversations. A custom API layer gives full control over user identity and privacy.

BuddyPro Possible
🧠

Public AI Coach

Future: paid access to Stewart's brain for clients and the public. This IS what BuddyPro was designed for. Could remain on BuddyPro for this specific use case while internal system is custom.

5
BuddyPro Capability Assessment

Requirement vs. BuddyPro Capability

Static Knowledge Upload

Upload PDFs, videos, documents to create an AI knowledge base. BuddyPro handles this well.

Telegram Chat Interface

Team can message the AI via Telegram. Currently working.

Public Coaching Product (Future)

Clients pay to access Stewart's brain. This is BuddyPro's core use case. Good fit for Phase 3.

Daily SOP Updates

EA uploads files to a shared Google Drive folder, then runs /update in Telegram. No API for programmatic ingestion, no file-watch capability, no automation. Works at small scale, becomes a daily manual task as document volume grows.

Role-Based Access Control

BuddyPro shows all knowledge to all users. No way to restrict Dragon to Ark only or Chris to LiveWire only. Would require separate instances ($197/mo each) with no unified view.

Multi-Entity Knowledge Separation

One knowledge base per BuddyPro instance. Cannot show management-level data to managers while showing public-level data to team within the same system.

Mindbody / External Data Integration

BuddyPro's API is chat-only. No data connector endpoints exist. Knowledge is added exclusively via Google Drive + /update command. Cannot pull live data from Mindbody or any external system.

Stewart Miller Branding

BuddyPro offers white-label at the Telegram bot level: you set your own bot name, avatar, and description. End users don't see "BuddyPro" in conversation. However, the delivery channel is still Telegram (not a Stewart-branded app). A planned native mobile app (targeted Q1 2026) has not yet shipped.

Custom App API

BuddyPro has an OpenAI-compatible chat API that Matthew's app could call. However, it is stateful (all calls save to memory), has no per-user identity field, no multi-user support, and the instance owner can read all test profile data. Works for basic chat, insufficient for a multi-user app with privacy isolation.

Coach Cloning / AI Avatars

BuddyPro does offer voice cloning (clone your voice for AI audio responses) and text-based AI experts. However, Stewart's vision of filming coaches once and creating video avatars in an app requires video generation (HeyGen-style), not text/audio chat. Different product category for the full vision.

Data Ownership and Portability

Source content stays in your Google Drive (you own those files). However, BuddyPro's processed knowledge base, user memory profiles, conversation histories, and subscription data live on their servers with no documented export. If BuddyPro shuts down, you keep raw files but lose all AI processing, memory, and user data.

6
The Recommendation

BuddyPro was the right starting point. It got your team communicating with AI through Telegram, and that's real progress. The question now is what comes next.

What you've described goes beyond what BuddyPro was built for. It was designed for coaches monetizing knowledge to clients. You need an internal business OS with role-based access across three companies, live Mindbody data, and automated SOP updates. For today's basic team chat, BuddyPro works. For the full Stewart AI vision, we need to build custom alongside it.

What we recommend: Build Stewart OS powered by Claude AI, with a proper database for role-based access control, automated knowledge ingestion, and a Telegram bot your team already knows how to use. Your team sees no difference in how they interact (still Telegram). But behind the scenes, the system knows who is asking and what they are allowed to see.

BuddyPro stays. It continues working for basic team chat while we build. Once Stewart OS is live, your team transitions to the custom bot. When you're ready to offer paid access to your brain for clients and the public, BuddyPro may still be the right fit for that specific use case, since that is exactly what it was designed for. Your call at that point.

You own everything. The code, the data, the knowledge base, the user relationships. No vendor lock-in. If Matthew wants to take over and maintain it, he can. If you want us to run it, we will. The system is yours.

7
What Changes For Your Team
Person Today After Phase 1
Stewart Uses BuddyPro, Claude, and Manus separately. No unified view across businesses. One AI that knows everything about all three companies. Ask a question, get an answer with full context. Dashboard showing system usage and team adoption.
Thushani
EA		 Manually uploads SOPs to BuddyPro via Google Drive + runs /update command. Every document, every day. Drops files into a watched folder. System auto-processes, chunks, and indexes. Thushani verifies, not uploads. Time saved: ~1-2 hours daily.
Dragon
Ark Gym		 Messages BuddyPro on Telegram. Sees all company knowledge including LiveWire and Stewart Miller Co data. Same Telegram experience. But now only sees Ark-related knowledge: gym SOPs, membership rules, staff policies, pricing. Clean, focused, relevant.
Chris
LiveWire		 Uses traditional 3D layouts and offline methods. Resistant to AI tools that feel complicated. Messages a Telegram bot he already knows how to use. Asks about production specs, client briefs, or set requirements. Gets LiveWire-specific answers instantly. Low friction, high value.
Gym Staff No AI access, or shared BuddyPro with no boundaries on what they can see. Team-level access via Telegram. Can check leave policies, membership rules, daily procedures. Cannot see management data, financials, or cross-company information.
Matthew & Daniel Building app and studying. Not using AI to full potential. Trained on AI tools. Matthew's app connects to Stewart OS via API. Daniel gets a foundation in AI that gives him an edge at university and beyond.
8
Implementation Phases
Phase 1 - The Foundation

Stewart OS: Internal Operations

  • Custom AI brain with knowledge ingestion pipeline
  • Role-based access control (all team tiers)
  • Multi-entity knowledge separation (Ark, LiveWire, SMC)
  • Telegram bot with per-user filtering
  • SOP upload and processing workflow
  • Team training (waves: EA + PM, then managers, then staff)
Months 1-3 (90-day window, before gym launch)
Phase 2 - Expansion

Integrations and Intelligence

  • Mindbody API integration (live gym BI data)
  • Web dashboard for admin and analytics
  • API layer for Matthew's app
  • Chris / LiveWire AI production workflow
  • Advanced SOP automation (auto-detect new files)
Months 4-6
Phase 3 - Monetization

Public AI Coach and Beyond

  • Public-facing "Stewart's Brain" coaching product: clients pay for access to your expertise through AI
  • Coach cloning infrastructure: film a coach once, create their AI avatar (video + voice), deploy in the app
  • Integration with Matthew's app: the API layer built in Phase 2 powers the front-end experience
  • Subscription and payment management for end clients
  • Scale across your network: thousands of coaches and influencers, each with their own AI clone, accessible through one platform
Months 6-12

The Bigger Picture

You said it yourself: "I have access to thousands of coaches around the world and influencers. I want to clone them and put them in my own app." Phase 3 is where the internal OS becomes a platform. LiveWire already films fitness content globally. The AI infrastructure we build in Phase 1 and 2 becomes the engine that powers an entirely new revenue stream: AI-cloned coaches, delivered through Matthew's app, at scale. This is a separate conversation with its own scope and structure, but everything we build in Phase 1 and 2 lays the foundation for it.

Next Step

Review this together on a call. Align on Phase 1 scope and timeline, and get building. The 90-day window is open.

Prepared by Muhammad Asmal, Asmal Digital

April 2026 - For internal review only