The fastest way to learn harness engineering? Build Claude Code from scratch.Why harness engineering? LangChain kept the same model and changed only the harness. Their coding agent went from 53% to 67% on Terminal-Bench, a top coding-agent benchmark. From outside the top 30 to the top 5. Same model. Better harness.Over the past few months, I've taken apart Claude Code, OpenCode, and Pi to see...
I spent weeks reading about how Cognee, Graphiti, and Neo4j's `agent-memory` build their agent memory architectures. They converged on the same heavy knowledge-graph design: an ontology, LLM extraction pipelines, deduplication, the works.I really wanted to use them for my personal use case, but that looks like such a heavy setup that adds a lot of friction and silos. Plus, it feels like I just...
Models are commoditizing fast. Harnesses already have. A "free" open-source harness feels like freedom, but the deeper I built in, the more I'd lose. "Free" open-source harnesses don't make you free.Staying coupled to the harness is the most expensive dependency you're not pricing. The fix is smaller than the problem: a context layer you own, so any model plugs in within ~5 minutes.Here are the...
I spent the past year building a unified memory layer for my AI agents using knowledge graphs and ontologies on top of MongoDB. I followed every trend first. I reached for the shiny frameworks and tried to design the perfect upfront ontology. I made basically every mistake possible.Naive memory fails at scale. File search bloats the context window once memory gets big. Claude Code handles it...
While building a financial assistant for an SF start-up, we learned that AI frameworks add complexity without value. When I started building a personal assistant with GraphRAG, I carried that lesson but still tried LangChain's MongoDBGraphStore. It gave me a working knowledge graph in 10 minutes.Then I looked at the data. I had 17 node types and 34 relationship types from just 5 documents,...
Freshly baked, out of the oven, touching on all the concepts you need to start building production-ready AI agents.
It's a 9-lesson course covering the end-to-end fundamentals of building AI agents. This is not a promotional post, as everything is free, no hidden paywalls anywhere, I promise. I want to share my work and help others if they are interested.
How I like to say it: "It's made by busy people, for busy people." As each lesson takes ~8 minutes to read. Thus, in ~1 and a half hours, you should have a strong intuition of how the wheels behind AI Agents work.
This is not a hype based course. It's not based on any framework or tool. On the contrary, we focused only on key concepts and designs to help you develop a strong intuition about what it takes to architect a robust AI solution powered by agents or workflows.
My job with this course is to teach you "how to fish". Thus, I built most of our examples from scratch.
So, after you wrap up the lessons, you can open up the docs of any AI framework and your favorite AI coding tool and start building something that works. Why? Because you will know how to ask the right questions and connect the right dots.
Ultimately, that's the most valuable skill, not tools or specific models.
Access the free course here: https://www.decodingai.com/p/ai-agents-foundations-course
Happy reading! So excited to hear your opinion.