Building a Multi-Agent AI Pipeline That Ships: LangGraph, RAG, and Evals That Matter

I spent 18 days building an AI product that converts research papers into audience-tailored PowerPoint presentations. Not a toy — a real deployed thing at doc2slides on Railway that anyone can use.

The interesting parts weren't the "make it work" moments. They were the tradeoffs I had to make honestly, and the times I resisted the temptation to add a "clever" fix that would have made things worse.

This post is about those decisions.

What I built

Doc2Slides takes a PDF and produces a .pptx file tailored to four audiences:

Building a Multi-Agent AI Pipeline That Ships: LangGraph, RAG, and Evals That Matter

Related reading

My RAG evaluation pipeline returned nan — here's what that taught me about…

I Built a 3-Agent AI Research Crew in 250 Lines of Python (LangGraph + Free…

LangGraph Production, RAG Memory Challenges, and AI Agent Patterns

Building an AI Research Agent with LangGraph, Claude, and AWS

I Built a 'Production-Ready' AI Agent Framework. It Was a Lie. So I Fixed It.

I Trusted 5 AI Agents With My Dev Pipeline. They Shipped a Product I Never…