Intro -> Next Level

Six months ago, my team had an idea. “Let’s build an on-device agent that is actually useful. You know, one that can do stuff on the machine for the user, so they can get back to their work quickly.” Agentic tools were barely getting started, but we figured they would help us do things a little faster. One week later, we already had a proof-of-concept.

Was it perfect? Heck no. It looked and felt like it was held together with duct tape. But it ran and proved the point we were trying to make, that there was room for agents that have access to the device. Back then agentic tools were also nascent, but a week for something that should have been six weeks was the kind of velocity that turned heads. It was impressive for how fast it got done, and I could see that software development was about to level up.

This has happened before

This is not the first time software engineering has leveled up. One could argue that the “first” level was writing the machine’s instructions by hand. Punch cards. Assembly. (Remember coding NES games in 6502 assembly?) You weren’t expressing an idea so much as driving the hardware, one instruction at a time, holding the ideas of the game in your head while you did it.

Then the compiler arrived. FORTRAN proved the idea in 1957; by the time C spread with Unix through the 1970s, a generation had stopped hand-writing assembly. Software engineering had leveled up. The compiler did the assembly, and we focused on logic. Variables, branches, data. We’ve lived at that level, compiled and interpreted, for most of the time I’ve been building software.

I think agentic coding is, in many ways, the “next next” level. One where the agent can understand the concept and the intent and express it in code for you. When that happens, you can instead think more about the idea, the capability you’re actually trying to bring to life. For me, software development gains an extra degree of creativity when this happens (not that it wasn’t before, but more so).

Software engineering is moving from the how to the what. The new job is to bring the ideas so that they can be brought to life.

Ideas got cheap to try

This shift has unexpectedly made me more creative. When I can take an idea and see it on screen in minutes, I can spend time seeing many different ideas quickly, which usually produces a better result. I can work through what feels right. I can experiment with paths that are probably sub-optimal, but which have learning lessons in them, because they become cheap to try. My list of things to look into ‘some day’ goes from a few to many ideas in a short time. So many possibilities!

Becoming truly useful

For me, smartphones became truly useful when you could sync your calendar over the internet and always have it up-to-date. When that happened, the calendar in my pocket became a necessity. Similarly, once I saw what agentic coding could do six months ago, I’ve been watching for the moment it became truly useful to me, on my own work, every day.

That moment is here

Agentic tools are still immature, and still mostly pointed at large companies (agentic harnesses, anyone?). But the tide is shifting toward people like you and me. I think that we’re not far off from a world where a creator will be able to hand off a lot of their daily email, the scheduling, the office busywork, to an agent. A world where an open-source maintainer will be able to let an agent triage PRs and resolve conflicts, so they can focus on other things. A world where a hobbyist can watch an idea come alive in minutes instead of having it wither on a list. I feel like I’m watching it happen in my life, right now. It’s both exciting and scary, all at the same time.

Why I’m writing this down

So I’m starting this blog to write down my experiences. What it’s like to build during this crazy time of fast paced change, how things are changing, and what I’m learning from it. There will be experiments that worked and the others that didn’t. There will be patterns that emerge as I use the tools. There will be lessons I only learned by getting them wrong first. It won’t always be about agents, or even about code, but for a good while it will be, because that’s what I’m curious about right now.

Mostly, I want to catalog what it actually feels like to learn and grow as the industry around me re-invents itself.