What IT Is

There is a lot of commentary about how AI initiatives are “failing”. Some measure it as ROI, which is a fair yardstick. Others point at the lack of adoption, which every technology goes through. The blame for these “failures” is often placed on leadership, which is fair given the meaning of the term. Speaking of terms, derivatives of “fail” have been in quotes so far for a reason: if you think of these things as a fail, then you are either sitting on the sidelines or throwing in the towel on the opportunities that AI offers. The only way to fail with AI is to give up on discovering how it will help your business. That will likely be followed by another type of fail.

Like everything else, failure is also a continuum. A prompt that returns an irrelevant result can technically be considered a fail, again challenged by the assumption that one can truly fail if they take the result as a lesson and do something else. At the other end of the spectrum is an agent that Deletes Company’s Entire Database, which is as close to a true fail one can get. There is no getting away from the fact that some people, teams, even companies, are just not very good at what they do, and capitalistic Darwinism will deal with them regardless of whether they are adopting AI or not (though AI will speed up the process).

Those true fails are a very small percentage of the world. The rest is a result of a type of hubris that (probably not coincidently) has seen a lot of attention in the business- and pop-psychology mediums lately, the Dunning-Kruger effect. Well, actually, just similar. The Dunning-Kruger effect is mostly about those that think they are doing better than they really are. The precursor to the failures that occur from attempting to follow early adopters doesn’t really have a term. However, think of this analogy: a person shows up to open mike night at a comedy club and sees a few folks pull off really good sets. They sign up to give it a try and find out the hard way that there is a lot more to getting an audience to laugh than just telling jokes.

So, lots of companies piled on to the AI bandwagon after having seen others succeeding with what looks from the outside as little or no effort. From the inside, these front runners have been playing with AI for years before ChatGPT woke the world up to the value of LLMs and Generative AI. They already had goals in mind of what they would do with the next evolution of the technology and they applied the latest and greatest with the same rigor they had been working with the latest but-maybe-not-the-greatest capabilities previously. The Lesson: Have a goal, make a plan, and be flexible moving from current state to target.

Back to the leadership blame. Again, some leadership is just not that great. The rest become great by engaging the company as a whole to define goals, make plans, and support the flexibility needed in achieving those goals when following a roadmap that traverses new territory. With AI, that leadership could start with a survey about “What tasks do you perform that are tedious?”

It’s especially important for leadership to ask this of the company as a whole because they are generally insulated from the types of mundane work that takes away from the ability to be productive. Some common areas are time and expense reporting. Most time reporting systems have a way to simplify this for recurring entries, but for those with varying tasks it would boost productivity and morale to have an agent that parses emails, IMs, and calendars to draft the weekly time submission and remind the person to review and submit. Or expense reports drafted by uploading receipts and the driving meeting invite or email. The ROI of such agents will vary greatly between enterprises, from a few dollars per person to a few million per year.

By polling the entire company for input on where AI can free people up from repetitive, simple, and necessary tasks that reduce the time, energy, and interest they could spend on work that is more fulfilling and more profitable, an enterprise can rapidly create a backlog of ROI-driven AI initiatives. The initial ROI may be small and sometimes difficult to measure. There are two key differences these initiatives would have over the 95% that “fail”:

1. ROI-Driven Goal: The initiative would have an ROI-driven goal from the start, avoiding the trap of, “We’re doing this because everyone is doing it.”
2. Built-in Adoption: Adoption is built in, because the goal was defined by the very people who will benefit directly and immediately from the results.

Once business success is demonstrated, more ideas will flow. At which point, it’s a good thing you defined some governance first. You did, right? Well, that’s another article.

As an addendum to this post, I asked Google Gemini for some better questions to solicit ideas for AI initiatives. Here is what it responded with: