MockNest Serverless is an open-source, AI-powered API mocking platform built in Kotlin, using Koog to implement the agent graph and integrate with Amazon Bedrock. I built it for the AWS 10,000 AIdeas competition, where it became one of the 20 winning projects.

This talk is about the engineering journey behind the winning project. MockNest was a backend-heavy developer tool competing with visually impressive, futuristic, and social-good applications, so I knew I was unlikely to be the crowd favourite. Instead, I decided to be techy — compete on engineering.

I will show how I planned the build around a fixed deadline, which architectural choices I made and which best practices I implemented. Furthermore, we will look at how a single AI call evolved into a Koog-based graph and how Kotlin on the JVM shaped the implementation on AWS serverless compute with Amazon Bedrock for inference.

There are plenty of war stories along the way, including cold start performance tuning, eval-driven development, and running out of credits, all of which changed the implementation and influenced engineering decisions.

Using demo videos, Kotlin and Koog code snippets, and architecture diagrams, I will show the audience how the original idea developed into the final product and competition win. To conclude, I will summarise which engineering decisions worked, which did not, and what I would do differently if I started again.