*Hey, Luca here! Welcome to a new edition of the *
I also publish an original essay every Wednesday. Here is the one from last week in case you missed it:
This week’s newsletter is brought to you by our friends at Palo Alto Networks!
Most VPC security stops at the perimeter, so traffic moving laterally between VPCs can be left uninspected.
With this solution template, you get a pre-configured Palo Alto Networks VM-Series environment with an AWS Gateway Load Balancer across four VPCs, so you can try:
Three traffic flows, one inspection point— route outbound, east-west, and inbound traffic through VM-Series via Transit Gateway.Live threat simulation— a real-world exploit hits your demo app, and you switch from alert to active blocking.App-ID in action— identify SSH on a non-standard port and enforce rules by application, not topology.
Explore the full architecture, step-by-step walkthroughs, and a live threat simulation, all for free!👇
Many teams feel conflicted about putting real AI governance in place, because it looks like a brake at a moment where everybody expects you to accelerate.
I have a contrarian take: I believe good governance can be an accelerant.
In 2006, Peter Summerlin ran a simple study about kids in playgrounds. Teachers took kids to a playground with no fence, then to a comparable one with a defined border. Without the fence, the children stayed huddled around their teacher, afraid of leaving her sight. With the fence, they felt free to explore within the boundaries. So in playgrounds with fences, kids used more space.
People work the same way. Once they know where the fences are, they feel empowered to do more within them. But that’s only true if governance is good.
We already see this in coding. We talk about guardrails for AI coding all the time, and having strict guardrails is exactly what allows me to be more liberal with the tasks I give to my agents, and with what they can ship.
Data also seems to point the same way. A late-2025 Google Cloud / CSA study looked at agentic AI adoption by governance maturity:
Full governance→ 46% adoptionPartial governance→ 25% adoptionStill in development→ 12% adoption
Correlation is not causation, but it makes it hard to look at governance as just a tax.
I wrote a full guide about how to get started with AI governance, including what you should govern and how rules graduate from common sense to software 👇
In July I talked with Geoffrey Litt, design engineer at Notion, about malleable software, and he shared one of his favorite product design parables.
Imagine a bicycle whose gears are labeled not with numbers, but with modes like “gravel gear” and “uphill gear”. It sounds user-friendly, but it’s actually terrible. What do you do when you’re going uphill on gravel?
When you hide the underlying model behind labels, you take away the mental model people need to develop to handle new situations. And humans are smart! They can learn numbered gears, and then combine that knowledge creatively.
What malleable software means is having a smaller set of primitive components that can be reassembled to make anything, and doing a really good job introducing and teaching those components to everyone using the software, just like bicycle gears.
Notion is a good example of this. Every paragraph, heading, and image is a self-contained block you can drag, nest, and sync across pages. It’s a small learning cost upfront that keeps paying back over time, and now it pays back with agents too: they reuse the same primitives, so Notion agent instructions are just Notion pages.
You can find the full conversation with Geoffrey here 👇
Finally, here are the best articles I have read this week:
Steve spent almost twenty years at Amazon, and he argues that its famous writing culture didn’t survive AI.
Bezos used to say you can’t write a six-page memo without clear thinking, and that is simply not true anymore, so a doc is no longer proof that someone has thought about the problem. Food for thought.
Karri argues that good products carry something of the people who make them, and that many products today feel messy because adding new capabilities is much easier than rethinking the existing ones. This is a great take, that I also needed to hear for Tolaria.
Felix works on Claude, and wrote a practical guide to using AI for more than doing the same work faster. He splits ambition into altitude, depth, and range. For example he went from asking Claude to fix single crashes to asking it to keep the apps crash-free, which first meant giving it crash reports and machines to reproduce bugs on. Lots of good prompts to steal, too!
And that’s it for today! If you are finding this newsletter valuable, subscribe to the full version!
1700+ engineers and managers have joined already, and they receive our flagship weekly long-form articles about how to ship faster and work better together! Learn more about the benefits of the paid plan here.
I wish you a great week.
Sincerely 👋
Luca
