Good morning, AI enthusiasts!
If you’ve missed it, the recording of our live workshop at AI Engineer World’s fair is now live! You can watch it here.
Inspired by my friend, Leonie, I decided to turn this workshop into an article version for anyone who couldn’t attend...
... or anyone who wants even more detail than is available in the recording :)
We talked about context management and shared the results and the whole setup of our experiments.
The goal of this workshop is to understand compaction methods and use them effectively.
And we had some interesting discoveries from these experiments, like how important cache management is in 2026…
If this sounds interesting, you can watch the full workshop here, or read the entire blog post with even more details here.
https://www.louisbouchard.ai/context-engineering-2026/
p.s. Everything here is open source: the tutor’s full codebase, the live demo with all the experiment results, and the slides. You can poke at every number I mention.
p.s.2. Please consider supporting the AI Engineer YouTube video (here) of the workshop to help make it one of their most successful workshops!