Jenna Pederson

Dear past Jenna, I know you're used to dealing with large, complex, legacy codebases riddled with technical debt.

Dear past Jenna, There will come a point when you wonder whether your career — the one you went to school for (twice) and spent decades honing — is going away.

I've spent my career helping people build software.

Everyone uses the word "memory" but I feel like they all mean something different by it.

I see this pattern a lot in n8n: a developer sets out to build a RAG-powered feature and ends up three days deep configuring (and reconfiguring) text splitters, embedding models, rerankers, and debugging — without a working system to show for it.

I built an n8n workflow that shows a simple way to use multiple, specialized knowledge bases because sometimes you need knowledge isolation between clients, locations, or even products in your RAG workflows.

You know all that RAG complexity you hate?

Over the last few weeks, I've been working to build out resources for people to learn more about retrieval-augmented generation (RAG) — and to learn more about it myself.

Want to prototype and test your Pinecone indexes, right from your IDE?

Last year, I set a goal for myself to build more demos in Python as a way to learn the language.

In this video, I show you how to build a python app to chat with your architecture diagrams.

Over the course of my career I have worked on a number of sprawling software systems.

This post was inspired by the AWS Game Builder Challenge.

Have you ever wondered why you can chat with an LLM about how to solve math problems but they struggle with actual mathematical calculations?

I read to my kid a lot.