AI Receptionist Labs
Learn to build production-ready AI applications through hands-on labs.
Lab 1: Environment Setup & Project Introduction
Create accounts for the services we need, install coding tools on your computer, and get the AI receptionist app running on your machine.
Lab 2: AI Lifecycle & MLOps Integration
Build a Flask MLOps service to track AI performance, integrate Prometheus for metrics monitoring, and implement comprehensive metrics collection for your AI receptionist.
Lab 3: Testing AI Systems
Learn to test your Flask MLOps service with pytest, validate metrics tracking, and ensure your AI monitoring system works reliably.
Lab 4: Deployment Pipelines (CI/CD)
Build automated CI/CD pipelines with GitHub Actions to test, build, and deploy your AI application to production environments.
Lab 5: Containerization with Docker
Learn Docker basics and containerize your Flask MLOps service for consistent deployment across different environments.
Lab 6: Orchestration & Scaling with Kubernetes
Install Kubernetes locally (minikube), deploy your containerized Flask service, and learn how to scale it up and down with simple commands.
Lab 7: Cloud Deployment with AWS
Deploy your complete AI application stack to production: Next.js to Vercel and Flask MLOps service to AWS EC2 with Docker.
Lab 8: Serverless Deployment with AWS Lambda
Convert your Flask MLOps service to serverless architecture using AWS Lambda and API Gateway for cost-effective, auto-scaling deployment.
Lab 9: Monitoring & Logging for Production AI Systems
Learn production monitoring concepts, explore AWS CloudWatch for deployed Lambda functions, and enhance your Prometheus dashboard with detailed health checks and metrics.
Lab 10: Security & Compliance for AI Systems
Implement security fundamentals for your AI application including API key authentication, rate limiting, secure environment variables, and GDPR compliance basics.