Managed AI Routing and Serverless Endpoint

🛠 Lab from the AI Platform Engineering Bootcamp. Used in Week 2. Bootcamp landing page: https://academy.tekanaid.com/bootcamps/ai-platform-engineering-bootcamp Parent course(s):

• Week 2: LLM Integration and API Patterns (slug: llm-integration-102)

🟡 Beta bootcamp lab. Hands-on instructions, check scripts, and solve scripts are in place. Lab is part of the running Platform Assistant capstone arc that grows across all 8 weeks of the bootcamp.

This hands-on lab teaches you to package managed AI access behind a reusable router and publish it through a serverless AWS endpoint.

You'll learn to:

• Call the TeKanAid AI gateway through an OpenAI-compatible client
• Route between a premium managed primary model and a lower-cost managed fallback model
• Package Python code for AWS Lambda using pinned dependencies
• Deploy a Lambda function with IAM and environment configuration
• Publish an HTTP API with API Gateway and validate fallback behavior end to end

This lab replaces the old Bedrock-specific workflow with a platform-safe pattern that still teaches managed-provider integration and serverless delivery.