Dynavera/README.md

Dynavera: An Agentic Approach to Role-Specific Trainers

Dynavera is a distributed agentic onboarding platform designed to solve the productivity gap in organizational training. The motivation was to create a system that delivers tailored, retrieval-grounded guidance for new roles, leveraging modern AI and orchestration techniques. This project was built to address the challenge of scalable, role-specific onboarding—where generic training fails to meet the needs of specialized positions. By combining curriculum generation, document-grounded retrieval, and live progress tracking, Dynavera enables organizations to onboard users efficiently and transparently. Through this project, I learned how to architect distributed systems, integrate retrieval-augmented generation, and design agent workflows for real-world impact.

Table of Contents

• Overview
• Core Features
• Architecture
• Quick Start
• Usage & Smoke Test
• Project Structure
• Demo Access
• Operational Commands
• Screenshots
• Documentation

Overview & Core Features

Dynavera addresses the onboarding productivity gap by combining:

• Role-aware curriculum generation
• Retrieval-augmented responses grounded in uploaded organizational documents
• Tool-aware orchestration over WebSockets
• Local-first inference support for privacy-sensitive deployments

The runtime is intentionally distributed: Django manages state and governance, while a dedicated inference service handles model-intensive workloads.

Key features:

• Distributed architecture separating application control plane and inference plane
• Multi-agent style orchestration for curriculum, knowledge, assessment, and monitoring behaviors
• RAG pipeline with semantic chunking, embeddings, and pgvector retrieval
• Live onboarding session updates via Django Channels WebSockets
• Persistent session/progress storage for auditability and recovery

Architecture

High-level architecture diagram:

Key backend runtime entry points:

• apps/onboarding/consumers.py for orchestration loop and WebSocket flow
• apps/onboarding/mcp.py for tool routing and backend tool execution
• apps/knowledge/tasks.py for ingestion/chunking/embedding workflow
• gpu_server.py for inference and embedding endpoints

Quick Start

Prerequisites:

• Docker Engine or Docker Desktop
• NVIDIA drivers and NVIDIA Container Toolkit (for GPU inference)

1. Clone repository

git clone https://git.cs.bham.ac.uk/projects-2025-26/vxn217
cd vxn217

2. Create environment file

PowerShell:

Copy-Item .env.template .env

CMD:

copy .env.template .env

macOS/Linux:

cp .env.template .env

3. Start development stack

docker compose -f compose/dev/docker-compose.yml --env-file .env up -d --build

4. Open application

• http://localhost:8000

Usage/Smoke Test

Follow this end-to-end workflow to use the project and to run the smoke test:

1. Create or select an organization and role
2. Upload role-specific training files
3. Wait for ingestion and embedding to complete (monitor the ingestion UI or logs)
4. Invite a user to the configured role
5. Log in as that user and start onboarding
6. Complete at least one guided interaction and one assessment action

Expected behaviour:

• Workflow completes without manual page refresh
• UI state transitions update live
• No dropped WebSocket session during onboarding

Project Structure

• apps/accounts user, organization, and role membership logic
• apps/knowledge training file ingestion and vector document persistence
• apps/onboarding sessions, orchestration runtime, and tool integration
• config Django settings, routing, ASGI/WSGI wiring
• compose development and production container configuration
• site frontend application
• docs architecture and deployment documentation

Demo Access

Hosted URL:

• https://fyp.viswamedha.com

Evaluation credentials:

Role	Email	Password
Admin	admin@example.com	admin
Manager	haleisaac@example.com	password
User	j.thompson@example.com	password

Manager registration code: MANAGER2026

Operational Commands

Stop services:

docker compose -f compose/dev/docker-compose.yml --env-file .env down

Tail logs:

docker compose -f compose/dev/docker-compose.yml --env-file .env logs -f

Run migrations:

docker exec -it fyp-django-dev python manage.py migrate

Reset seeded passwords:

docker exec -it fyp-django-dev python manage.py reset_passwords

Screenshots

Home:

Organization:

Onboarding generation state:

Onboarding content flow:

Documentation

• Distributed Runtime Flow
• Application Structure
• Deployment Topologies