Platform Architecture
Data Flow & Infrastructure Diagram
Client Layer
Clients
All clients connect to a shared authentication service
Web
iOS
Android
Mac
Surface
API
MCP
Authentication Layer
Login Application
Centralized auth service — all clients redirect here
SSO (SAML / OIDC)Username / PasswordEmail OTPOther Providers
Returns Access Tokens + RBAC Permissions (Role-Based Access Control)
Authenticated API Calls (Bearer Token + RBAC)
API Gateway
api.iblai.app
Routes requests to underlying platform services
Learn
ibl-edx-pro
- → Content creation
- → Course management
- → LMS capabilities
- → Learner tracking
Data Manager
ibl-dm-pro
- → Agentic functions
- → Agent orchestration
- → Data processing
- → API services
ASGI Connection (Agent Routing)
Internal Tooling
Observability & Media
LLM Analytics
- • Prompt tracing
- • Cost tracking
- • Model evaluation
- • Usage dashboards
Audio / Video
- • Phone calls
- • Voice AI
- • Real-time audio
- • WebRTC
Back-End Infrastructure
Load Balancer
Distributes requests across App Scalable pool
App Scalable Servers
64 GB+ RAM each (min. recommended) · Horizontally scalable · N instances
App Scalable 1
LearnData MgrLLM AnalyticsAudio/Video
App Scalable 2
LearnData MgrLLM AnalyticsAudio/Video
App Scalable N
LearnData MgrLLM AnalyticsAudio/Video
ASGI Connection (Agent ↔ Sandbox routing)
Agent Sandboxes
8 GB+ RAM each (min. recommended) · 1 sandbox per agent · Unlimited sandboxes · Connected via Data Manager
Agent A
8 GB+
Agent B
8 GB+
Agent C
8 GB+
…
8 GB+
Agent N
8 GB+
Scales to any number of concurrent agent sandboxes on demand
App Single Server — Persistence Layer
64 GB+ RAM (min. recommended) · Single instance · Read replicas supported
PostgreSQL
Used by Data Manager
- App data
- User records
- Permissions
- Read replicas
pgVector — Embeddings
MySQL
Used by Learn
- Course data
- LMS records
- Read replicas
MongoDB
Used by Learn
- Documents
- Logs
- Unstructured data
- Read replicas
Redis
- Sessions
- Cache
- Pub/Sub
- Rate limiting
Object Storage
- File storage
- Media assets
- User uploads
- Backups
Shared Filesystem
- Configurations
- Static files
Data Flow
Complete Data Flow Sequence
- 1User opens any ibl.ai client (Web, iOS, Android, Mac, Surface, API, MCP)
- 2Client redirects to centralized Login Application — user authenticates via SSO, password, or email OTP
- 3Login Application returns Access Tokens + RBAC Permissions — user redirected back to client
- 4Client makes authenticated API calls to api.iblai.app (Bearer token + RBAC)
- 5api.iblai.app routes to Learn (ibl-edx-pro) or Data Manager (ibl-dm-pro)
- 6Load Balancer distributes across App Scalable servers (64 GB+ RAM each)
- 7Data Manager opens ASGI connection → routes to appropriate Agent Sandbox (8 GB+ RAM, 1 per agent)
- 8Agent Sandbox reads/writes: PostgreSQL (pgVector), MySQL, MongoDB, Redis, Object Storage, Shared Filesystem
- 9Internal tooling: LLM Analytics (prompt tracing, costs) + Audio/Video (calls, voice AI)
- 10Agent Sandbox → Data Manager → api.iblai.app → User
Scaling
Scaling Model
| Component | Scaling | Details |
|---|---|---|
| Clients | Static | CDN / app stores / API / MCP |
| Login Application | Shared | Centralized auth for all clients |
| api.iblai.app | Gateway | Routes to Learn + Data Manager |
| App Scalable Servers | Horizontal ↔ | N instances, 64 GB+ RAM each (min. recommended) |
| Agent Sandboxes | Horizontal ↔ | Unlimited instances, 8 GB+ RAM (min. recommended), 1 per agent |
| App Single Server | Vertical ↕ | 1 instance, 64 GB+ RAM (min. recommended), read replicas |
| Load Balancer | Single | Distributes across App Scalable pool |