System Design
Architecture you can walk through in an interview
Replace diagram placeholders with exported visuals or interactive embeds when ready. The structure below is intentional for EM/architect conversations.
Authentication Flow
JWT-based login, claim validation, and RBAC enforcement across services.
Nodes
- 1User submits credentials
- 2Auth API verifies identity and issues JWT with role claims
- 3Client sends Bearer token on subsequent requests
- 4Services validate signature/expiry and enforce permissions
AI Pipeline
End-to-end path from user query to grounded streamed response.
Nodes
- 1Receive authenticated query
- 2Embed query and retrieve top-k chunks
- 3Assemble prompt with policies + context + memory
- 4Stream tokens to client
Material Processing
Upload to searchable knowledge via extraction and embeddings.
Nodes
- 1Validate and store raw material
- 2Enqueue processing job
- 3Extract normalized text + metadata
- 4Chunk, embed, and upsert vectors
Microservices Boundaries
Separation between core domain systems and AI/worker services.
Nodes
- 1Core domain owns transactions and institutional workflows
- 2AI services own retrieval/generation contracts
- 3Workers handle async extraction and embedding
Deployment Architecture
Containerized services with environment-based configuration.
Nodes
- 1Build images per service
- 2Inject secrets/config via environment
- 3Route traffic through reverse proxy
- 4Observe logs and health endpoints
Database Architecture
Relational state, cache, and vector store responsibilities.
Nodes
- 1Transactional entities in relational DB
- 2Ephemeral session/cache in Redis
- 3Semantic payloads and vectors in Qdrant
Request Flow
Typical authenticated API request lifecycle.
Nodes
- 1Authenticate and authorize
- 2Validate payload
- 3Execute business logic
- 4Persist/read and return response
API Flow
REST contract patterns between Vue clients and backend services.
Nodes
- 1UI calls versioned REST endpoints
- 2Domain APIs handle institutional workflows
- 3AI APIs handle chat/generation/retrieval
Question Generation Pipeline
From materials to validated assessment candidates.
Nodes
- 1Retrieve concept context from materials
- 2Generate candidate questions
- 3Validate structure and detect duplicates
- 4Faculty reviews in planner before publish
Student Journey
Learner path through dashboard, materials, and AI assistance.
Nodes
- 1Authenticate as student
- 2View courses and materials
- 3Ask grounded questions via AI tutor
- 4Complete assessments and track progress
Admin Journey
Operator path for configuration, monitoring, and control.
Nodes
- 1Authenticate with privileged role
- 2Manage users and permissions
- 3Monitor processing and AI usage
- 4Review operational reports