Good morning!

Yes, you are not hallucinating, we indeed got two newsletters this week!!

If you missed it, I gave away our best tips in yesterday’s iteration. Check it out here:

If you’ve been hearing “harness engineering” everywhere lately and your first thought is, “okay, so this is probably just prompt engineering with a nicer name”, that’s the first misconception to kill.

It’s not, and it’s not “just” a new term.

And the reason this matters is not just vocabulary. It tells you where AI is actually heading. By the end of this week’s video, you should be able to tell the difference between prompt engineering, context engineering, and harness engineering, and more importantly, why the industry suddenly started caring about this now.

What changed is pretty simple:

Agents got good enough to be useful, but not reliable enough to trust on their own.

That’s the entire story.

Agents got good enough to be both useful and dangerous. They now can do more than generating text, or token. Useful enough that people started letting them write serious code, make real tool calls, and operate across long tasks. Dangerous enough that if you wrapped them in nothing but a loop and a dream, they would confidently make the same stupid mistake again and again.

And we need to do something about that... this is “harness engineering”. Learn more in the video (or article format here):