Talking Scrum and Agile for Hardware at Aquion Energy

Author’s Note! This article has been imported from my previous website. I wanted to preserve all of the old content as many people have found some value in it. There may be some broken links and or formating issues. If something isn’t right, please let me know and I’ll do my best to make an update.

Last weekend, I made a rather spur of the moment decision to fly to Chicago and ride a motorcycle back through Pittsburgh to my home in DC.

While stopping in Pittsburgh, I receive a tour of the incredible Aquion Energy who make energy storage solutions, which are, really awesome batteries. I had forgotten how much I loved the smells, sights, sounds, and activities of a large industrial factory.

To the Point

The portion of the visit that was most exciting for me, was having a conversation with their Scrum Master, Mike, and learning about the application of Agile scrum methodologies in the hardware world. I wish I had the exact quote, but Mike said something along the lines of:

There has been so much innovation in software, in terms of workflow optimization, I just don’t think it has been tried much in the hardware world, but I believe it has great value.

I couldn’t agree with this more. Any startup is awash with lots of good ideas, lots of competing interests, and lots of uncertainty; so it would seem that agile processes could be applied regardless of the deliverable. I was curious about if there were differences in the hardware world that had to be taken into account when using agile scrum processes, and the following seemed like the main ones:

Limited Iterations

Software can be refactored an infinite number times, or as many times as time allows, whereas with hardware, there are significant materials and processing costs required to make a change. Often sprint deliverables could take the form of a design for a part, or getting a part prototyped. There would have to be a balance between the “most simple implementation,” the costs and lead times for manufacturing.

Less Show, More Tell

In discussing a sprint retrospective, the focus was much more on the telling than on the showing of completed work. This caused me to pump my fist in the air at the obvious presence of objective standards in hardware. “I build this, and it works.” The implementations were less of a concern, because everything was in plain view and the interface was obvious: a connector. Just because software is built in an air conditioned office on a computer does not mean it should not be built like any other functioning mechanical part. See Shop Class as Soul Craft for an excellent dissertation on the subject.

Somewhat Less Dependencies

This is a nuanced topic. We discussed that, often, sprint work was a collection of various tasks that did not require extensive planning with regards to interdependencies. A project on a large scale might have a bunch of things that need to get done, in just two weeks’ time, but not everyone has a relationship with another. In an “Agile Lemonade Stand” stories might be:

• Build Stand
• Print Banner
• Buy Lemons
• Design Recipe

Much of this could be done “on your own”. Mike explained that this lack of dependencies allowed thier planning sessions to be held to 2 hours of time. This surprised me, given my preference for planning as long as needed to have a well defined set of sprint work.

I’d Like to End…

With Aquion’s company values, which I think are very well said, and could be a lesson to us all:

Say What We Do. Do What We Say.

We deliver on our commitments. We are consistent, reliable and foster a culture of transparency. Integrity is at the core of everything we do.

Innovate or Die.

The survival of this company depends on our ability to improve constantly. We are never satisfied with solutions that under-perform or cost too much. We do not accept limits based on “the way it has always been done.”

We Believe It’s Possible.

We are optimistic and determined. We are willing to try hard things if the payoff is high enough. We do not make excuses.

Good Ideas Win.

We set aside rank and ego, instead relying on facts, logic and data to evaluate ideas.

As Simple As Possible.

We don’t use a cannon to kill a mosquito. We do not overpay for precision. We are as efficient as possible with time, money, and effort.

Frequent Course Correction.

We plan before we start. When new information indicates a new path, we take it. We understand the unexpected happens, and sometimes destinations change.

We Make Each Other Better.

We put the team first, and we recognize that individual achievement matters to the extent that the company as a whole is improved.

We Give a Damn.

We care about the way we spend time.

Have Fun Along The Way!