Insights on Context Engineering, AI-assisted development, and owning outcomes
In 2022, I wrote that DevOps had become waste. Now, in 2025, AI local optimization is the new waste—thousands of teams rebuilding the same RAG systems, prompts, and context pipelines in isolation.
I had a problem. A Lambda function that started as a quick prototype had grown to 1,348 lines. It handled AI character chat, vector memory, moderation, credits, and creator payouts. It had zero tests. It was untouchable.
The debate over AI and software engineering keeps circling the wrong question. It’s not whether AI can write production-ready code. It’s whether your organization’s systems are understandable enough for AI to reason about them in the first place.
When AWS published their post Deploy Amazon Bedrock Knowledge Bases Using Terraform for RAG-Based Generative AI Applications, it offered a beautifully structured architecture: document ingestion, embeddings, vector search, and automated retrieval through Bedrock Knowledge Bases.
On October 20 2025, AWS’s US-EAST-1 region stumbled—and half the internet lost its mind. Major learning platforms, gaming networks, airlines, and fintech services all went dark.