The engineering best practices you can drop straight into Claude
The exact markdown files we use for writing, coding, and building agents at Towards AI
We’ve spent years building LLM systems at Towards AI. The main goal has always been the same: share what we build and, more importantly, what we learn building it, so you can grow as an AI engineer without hitting every wall we did.
Part of that is our courses. But the bigger part is making your actual building process easier, every day. So we took the markdown files we use internally (the ones you can feed directly into Claude, so it builds with the context that usually takes years to develop) and made them public.
Access everything here: https://github.com/louisfb01/ai-engineering-cheatsheets
It includes decision-ready references for the most common AI engineering problems: all the engineering best practices from our courses distilled into dense markdown files you can use mid-build or feed directly into Claude, so it works from decisions already tested on real systems.
Open a cheatsheet, find your situation in the table, and follow the recommendation.
What’s Inside
These come directly from the Towards AI Academy courses, the same frameworks we teach in depth, distilled into references you can use today. No course required. No paywall.
You can access everything here: https://github.com/louisfb01/ai-engineering-cheatsheets
If you want to go deeper, full lessons, code, and hands-on projects, that’s what the Towards AI Academy is for.
The timing on this is great — I've been maintaining my own set of markdown instruction files for Claude Code over the past few months and the difference it makes is night and day. Without context files, you're basically asking the model to guess your architecture decisions every single time. I built an AI system that orchestrates across multiple models (Claude, GPT, Haiku) and the biggest unlock wasn't better prompts — it was giving each agent a persistent markdown file with decision history, coding conventions, and past failures to avoid. Curious whether you've experimented with chaining these cheatsheets across multi-agent setups, or if they're primarily single-session references?
These cheatsheets are exactly what engineers need to move faster with AI.