Context Engineering: 5 Familiar Strategies from Real Product Teams
I've been getting a lot of questions about why I'm diving so deep into Claude Code. So I want to take a step back and provide some context.
Last March, when I started building my first AI product—the Product Talk Interview Coach—I felt like I had to figure it all out on my own. I had never built an AI product before. And I didn't have a team that I could lean on.
And while I had a blast digging in, experimenting, and learning what I needed to learn to ship my first AI product, I started to wonder, "How are product teams going to learn this stuff?"
As an industry, we are being asked to leverage a new technology that is foreign to us. We are all experimenting and learning what's just now possible. It's moving so fast, it's exhausting just following the news, let alone trying to learn and develop new skills.
At Product Talk, my goal has always been to help teams make better product decisions. That's been my tagline since the day I launched this blog back in November of 2011. That was forever ago and yet it's still what drives me today.
After releasing the Interview Coach, I started to ask, "How am I going to rapidly develop my skill set?" and "How can I help others do the same?" I came up with a three-part answer:
- I'm going to collect and share stories about how other teams are learning and building AI products. That's why I launched Just Now Possible.
- I'm going to push the boundaries on how I can use AI in my day-to-day life and I'm going to write about it.
- I'm going to keep building AI products and I'm going to write about that, too.
The Claude Code series was born out of number two. But it has had an interesting side effect. It's also helping me build better AI products.
The more I push the boundaries of what's possible with Claude Code, the more I understand how to build more robust AI products. And that's reinforced my belief that product teams need to get hands-on with this stuff in their day-to-day lives. It's how we are going to develop the skillsets we need to build tomorrow's products.
My context rot article where we learned how to manage the context window in Claude Code is a great example of this. Today, I want to show how learning about context window management in our day-to-day lives directly maps to managing the context window in the AI products we might build.
My hope is to make it crystal clear how experience in one area develops expertise in the other area. Let's dive in.
Start with this overview video and then dive into the rest of the article.
A Quick Refresher on Context Window Management
In the context rot article, we learned:
- what the context window is and what goes into it
- how to offload conversational context to the file system
- about the /compact and /clear tools
- to repeat critical information as the context window fills up to overcome tokens "lost in the middle" or at the beginning of the input
- how to use agents to get access to more context windows
It turns out these exact same skills are being used by developers to manage the context window in production products. I'll show you how.
If you haven't read the context rot article, start there: Context Rot: Why AI Gets Worse the Longer You Talk (And How to Fix It).
What is Context Engineering?
Context engineering is the work that we do to manage the context window in the AI products and services that we build. It's how we give the large language model the context it needs to do the job well. It's also how we manage and mitigate context rot in our product and services, so that we can get the highest performance from the underlying model.
Today, we are going to look at five different strategies that product teams are currently using in their context engineering efforts. You are going to see that each of these strategies ties back to a strategy you might already be using in your day-to-day AI usage (especially if you followed the advice in the context rot article).
We'll look at how product teams are:
- designing compact system prompts by breaking big tasks into smaller tasks
- building external memory/state structures to keep the context window clean
- curating what goes into each turn
- repeating critical information as context grows
- using sub-agents to grow the context window
Product Talk is a reader-supported publication. The rest of this article is for Supporting Members and CDH Members. If you haven't already, subscribe to get access.
