Look, Ma! AI Can Program!

My friend, William Neil, recently wrote an app. Rather, he convinced AI to write an app for him. And he recorded himself doing it!

If you’re technical, you might enjoy watching it. Or, if you find recordings of machines generating machine-y looking things soothing like ASMR.

William chose one of my collaboration workouts as the subject of his app. I host a monthly series of workouts called Staying Strategic as part of my Collaboration Gym. The first two workouts is something called Question Dumping — literally dumping whatever questions or top-of-mind for you at the moment, then doing a little organizing and answering. Participants do their work in Google Docs, and I prompt and coach them along the way.

William did the program earlier this year, and he asked me if I had ever thought of creating an app version of my workouts. As a matter of fact, I’ve often thought about this. So, he built one!

We had an hour-long conversation where I walked him through how I thought it should work, then he spent at least another hour refining the requirements using ChatGPT as a kind of secretary while he went on a walk (as he describes in the video). Building / testing / debugging an iteration of the app took about an hour total.

I haven’t done any serious coding in decades. I also haven’t played with coding using AI, although I’ve had some interesting conversations with friends, and I’ve been following musings from Jon Udell, Les Orchard, and Harper Reed. (I also enjoy Mike Hoye’s general commentary and critiques.) So it was fun to have William walk me through the process, and I’m so glad he recorded this and shared it with the wider world.

It’s a simple, non-production quality app. I think an experienced engineer could also build it in about an hour, with other potential benefits, such as higher code quality. It also would have cost at least an order of magnitude more. Maybe the benefits outweigh the costs in the long run. I wonder about things like maintainability and how easy it is for LLMs to refactor a codebase with minimal human intervention. And, I’m also conscious of the Bitter Lesson.

Now about that app…

For many years now, even before GPT-3, my friend, James Cham, has talked about the potential of AI replacing overpriced strategy consultants. If you look at the mechanics of what most traditional strategy consultants do, this is a no-brainer. But the dirty little secret of Big Consulting is that they’re rarely hired for said mechanics.

So I don’t think that AI will replace Big Consulting (although it may drive the cost down). But I do think that many groups legitimately want to align their people around good strategy. This is why I created Staying Strategic, which is an evolution of something I’ve been tinkering with for my whole career. And I think that AI could not only help scale workouts like Staying Strategic, but it could enable new and interesting possibilities. The fact that AI could help create the tools that would enable AI to help us be more strategic is just meta icing on the cake.

My Self-Care Dashboard

When Kristin Cobble and I were starting Groupaya, we spent a lot of time discussing the kind of culture we wanted as an organization. In particular, we both felt strongly about the importance of integrating personal development into our daily work lives.

In order to meet this goal, Kristin designed a collective process for us based on Daniel Ofman’s Core Quality Framework. The premise of the framework is that our biggest pitfalls are our greatest strengths (our “core qualities”) taken to an extreme. We all reflected about ourselves and about each other using the framework as a guide. It was enlightening to compare the differences in perception.

For example, I identified my drive to learn as my core quality. Too much of that led to dabbling and lack of focus — my pitfall. Kristin and Rebecca Petzel, on the other hand, both chose to focus on my high standards as my core quality. My corresponding pitfall was my tendency to drive myself and my team mercilessly when my standards weren’t being met. They wanted me to be more accepting when people made mistakes and more patient with people’s learning curves.

As we explored this further, we agreed that I actually wasn’t bad at these things. I had evolved these skills through lots of practice over the years. The problem was that these were not natural qualities for me, and when I was stressed or tired (which was often during my stint at Groupaya), Grumpy Eugene would come out of his cave.

Each of us had to commit to a practice to help counteract our pitfalls. Because I was generally good at being patient when I was taking care of myself, I committed to self-care. And the way I would do that was to commit to playing basketball once a week.

I had asked my friend, Lisa Heft, to work with me as a coach the previous year. One of the things I realized from that work was that when I’m playing basketball regularly, I’m generally happy and centered. Needless to say, I was not playing regularly at the time, much less exercising at all. I figured that committing to basketball once-a-week was more than reasonable, easily trackable, and would pay off big.

Despite all that, I got off to a bad start in 2012. We were swamped with the usual challenges of running a business and dealing with client work, and as usual, I neglected my self-care practices. What was different this time was that I felt bad about my neglect, because I had made a commitment to my team, and I wasn’t living up to it.

In order to turn this around, I decided to track my progress in a simple Google Spreadsheet, and to share this with my colleagues, so that they could check up on my progress anytime. I had a row for each week of 2012, and a column for the number of times I had played basketball that week.

The simple act of tracking in the open had a transformative effect on my practice. It forced me to think about the practice regularly, and it allowed me to see in very concrete ways how I was doing.

Over the next several months, I evolved my spreadsheet to incorporate new practices and learning. For example, I wouldn’t always play basketball, but I would sometimes go on runs or long walks, and while that wasn’t as good as basketball, it was definitely good for me (and my colleagues) overall. So I started tracking that too.

I eventually added two more practices to my spreadsheet: turning off work email in the evenings and on weekends, and taking play days in the middle of the week. Every time I did one of my practices, I gave myself a point. Using a line graph, I charted the total number of points per week as well as the four-week running average.

I also added a notes section for context. There were weeks that were restorative despite not doing any of my practices, and I wanted to be sure I noted that. There were weeks when I was traveling or sick.

The chart essentially became my personal dashboard, and my practices became almost a game — keep the line above 1 (my commitment to my team). It was very challenging for me to maintain that on my own, so I started incorporating other tricks such as signing up for a fitness bootcamp.

Moreover, the chart helped my interactions with my team tremendously. Whenever I would get frustrated at somebody, before I unloaded those frustrations, I would first check my dashboard to see if I had been taking care of myself. I often found in those situations that I hadn’t, and it was a signal to me that I should go for a run before I said anything to anybody.

I have found the dashboard so valuable, I have continued the practice. Here’s what this year’s spreadsheet looks like:

Self-Care Spreadsheet

Notice the different colors indicating whether or not I did a practice that week. Here’s what the corresponding line chart looks like:

Self-Care Dashboard

As you can see, the four-week running average is a better indicator of my state of self-care at any point in time than my number for that week or of the overall average. You can also see that I’ve been doing very well with my practices over the past few months. If I were to compare this chart to last year’s numbers, you would see that I’m taking much better care of myself this year than last.

I’ve made the Google Spreadsheet template available for anyone to copy and adapt as he or she sees fit. I’ve also put together a screencast that quickly walks through how to use and customize the dashboard. Post your questions or thoughts below, and if you decide to use or adapt it, please let me know, as I’d love to hear how it’s working for you!