Experimenting With AI as a Creative Assistant: How I Created My Recent Videos

Over the last few weeks, I have been playing with AI as a creative assistant. Since my multimedia creative skills are - let's say sub par, I have used AI as a partner, or assistant in. The goal is to enhance content to promote knowledge sharing in manufacturing. Not AI as a replacement for expertise, but AI as a way to translate expertise into formats people actually absorb.

As part of this, I created two videos and I wanted to share the behind-the-scenes story of how I made them, what tools I used, and what I learned along the way.

Digital-First & Composable: The Future of Pharma Manufacturing Design

 

Grandpa Learns AI.

Why I’m Doing This

A few months ago, I was interviewed by a research team connected to the World Economic Forum. They’re studying the future of work and education in the digital age—specifically how people learn and adapt in environments that are changing faster than ever.

That interview got me thinking: Manufacturing is changing. Digital tools are changing. But our learning models haven’t caught up.

And if I’m being honest, my own communication style tends to be direct, dense, and sometimes… too straight to the point. Great for experts, not always great for everyone else.

So I wanted to see what happens when I let AI help me explain the concepts I care about—but in a completely different voice. So I leveraged the generative AI tools (specifically I used NotebookLM from Google for no other reason than availability - its free for now) and I’ll admit: I expected the usual AI fluff but the results was… surprisingly good.

With some well thought out prompting and iteration NotebookLM didn’t just rewrite my explanations—it transformed them into something more approachable, more story-driven, and dare I say it, more human. It brought out a teaching style that’s very different from my natural tone.

Transforming the Content

The first video was really just a "let me just feed some content and see what I get...". I recently wrote a whitepaper titled "Digital-First and Composable— A NewParadigm for ConceptualFacility Design in Pharmaceutical Manufacturing" about why its critical to take a digital first approach to the design of pharmacuetical manufacturing facilities. (Its not published publicly yet, but let me know if you are interested in a copy)

I wanted to test whether NotebookLM could help explain this somewhat deeper and more technical topic in a different way to non technical people. Basically as if you are explaining this to your grandmother. This is a known exercise that is commonly used to create a simplified and easier to understand content of technical topics. It was something I typically asked my students to do when defining their research topic, e.g. the The Feynman Technique. 

Here AI surprised me again. It took my content and created a narrative that felt clear, structured, less consultanty and was like a guided tour of the future of manufacturing It delivered the same intellectual payload—but in a format that's easier to digest for people who aren’t neck-deep in these topics every day.

For the second video I fed it the transcript from my WEF conversation about how people learn, and the AI picked up on a few of the stories that I used to exemplify how to explain new digital concepts to the industry. It took the my grandpa story  and created a story about a grandpa discovering AI for the first time. It turned a complex topic into something relatable and a little emotional. 

I shared both the whitepaper and the video I created with customers and colleagues and the feedback was that the video is by far more valuable than the whitepaper. The surprising part was that people actually learned from it. They weren’t just “getting the point.”, they were experiencing it - maybe even feeling the point. 

Why Use Personas?

One thing that became clear through this experiment is that who explains something matters just as much as what is being explained.

In manufacturing, we’re all guilty of communicating like… well, manufacturing people. Precise. Direct. Dense. Focused on efficiency. It’s great for experts, but not always for learners who don’t live and breathe MES architectures or Pharma 4.0.

This is where personas come in. Sometimes the most effective way to teach a technical idea is to have it explained by someone who is not you.

• A grandpa.
• A mentor.
• A line worker.
• A curious newcomer.
• A future digital assistant.

AI helped generate voices and storytelling styles that I simply wouldn’t have used myself. And that difference matters. It’s disarming. It opens people up. It creates emotional connection. It makes the content stick.

But—and this is important—it didn’t invent anything on its own. It worked because I gave it:

• the right context
• the right source material
• the right stories
• and a clear intention
• grounded in my decades of experience

AI can’t fabricate expertise but it can translate expertise into a form that reaches people where they are. The personas made the learning accessible and my context made it accurate. It’s a powerful combination.

What I Learned

In the end, this experiment taught me that AI can significantly expand my creative range—but only when it’s grounded in the right context. AI didn’t magically produce valuable content; it was effective because it worked with my whitepaper, my WEF interview, my research, and my own stories from years in manufacturing. When AI has that depth to draw from, it becomes an amplifier rather than a generator of fluff. 

I also realized how essential storytelling is for real learning. The emotional layer—whether it was explaining a digital-first facility as if to a grandmother or turning my grandpa anecdote into a touching narrative—made the concepts stick in a way traditional technical writing rarely does. And using personas was far more powerful than expected: having someone unlike me tell the story didn’t dilute the expertise; it made it more approachable and meaningful. What this ultimately reinforced is that AI isn’t the expert—it’s the assistant. It can translate, reframe, and humanize ideas, but only when guided by intention and supported by real experience. And that, I think, is exactly how AI will create value: by helping us communicate better, teach more effectively, and unlock new ways to share the knowledge we’ve spent years building.

What is a Manufacturing System - Part I

This is a post that is long overdue. A central discussion topic on this blog is Manufacturing Systems and I have not yet really explained what I mean by a Manufacturing System. I have talked about manufacturing system that are agile and Holonic, so it is about time that I posted a more practical or at least clear description of what I mean.

Most definitions of Manufacturing System are focused on describing a solution, or more precisely the functionality and architecture of a Manufacturing System solution. For example the MESA model presents number of functional categories from a business perspective, where as the ISA-95 (S-95) model provides a solution architecture based on functional decomposition. All these are of course relevant and useful yet it seems that the problem only interesting to academia – try to Google it. It is assumed that we in industry all know what it is – a dangerous proposition to have.

We all agree that the key to a successful deployment of a Manufacturing System is the understanding of the problem that it is designed to solve. This obviously not a novel approach – it is what everybody attempts to do with the system’s requirement or URS. Yet my experience shows that even in the requirement phase many resort to using the existing models, thus reverting to describe the problem with the solution itself. Quite confusing isn’t it?

So here is my take on what a Manufacturing System is, or in other words the Shop Floor Management Problem. I like to describe it as the problem of integrating 3 important flows in a manufacturing organization. The 2 vertical flows provide Product and Logistical information while the horizontal flow is the physical flow of material, equipment and people.

The Shop Floor Management problem is therefore: How to make use of the information provided by the Product and Logistical flow to efficiently and effectively manage the physical flow of Resources and Materials (also known as the production process). Simple isn’t it - that is what a Manufacturing System is designed to do. Try to imagine a seasoned and effective production supervisor or plant manager – the Shop Floor Management problem is very close to his real life job duties.

It is obviously not that simple and there is of course much more detail that is yet to be discussed. I plan to provide some of this in upcoming posts (hence this post is named Part I). Also this is not meant to take away from the importance and complexity of product development, process engineering, operations, and planning. It is a model that is focused on explaining the particulars of managing a shop floor (yes this is my disclaimer).

More detail to come in future posts…

Using metrics and what it tells us about Manufacturing Intelligence

In continuation to some of the other posts in the topic of metrics and KPIs, this time I would like to discuss the use of metrics. So, not so much what the metrics are or which metrics are most important, but how do we use them. If we look at how analysis is performed we may be able to gain some insight into how the data should be collected and structured. This may be for example to support lean or process improvement initiatives. The idea regardless of methodology requires that the team or person gain an understanding of the process and its behaviour based on the data at hand.

I think the best way to frame this up is to tell the story of a persona in a simple scenario. Let’s consider Patrick Process Engineer who is trying to understand yield fluctuations specifically and maybe the yield’s behaviour in general. He is perplexed about why he cannot accurately predict yield given that most of the processes are “in control” (yes, another one of these myths about processes). What he really is striving for is an understanding the process and the best way to investigate it – in other words analyze the process.

Obviously Patrick will be looking at the Yield metric(s) and once he sees some fluctuation he will embark on an analysis. Typically he will perform what I call a high-level analysis, which is kind of a “look-around” in the data and maybe other related metrics to determine patterns. But wait, why patterns. Well whether we like it or not when we analyze processes we naturally look for patterns since that is what complex processes really exhibit. I guess I need to write a bit more about the complex adaptive behavior of manufacturing systems, but let me leave that for a future post. For now let’s just say that the patterns really tell us about the dependencies between the different metrics and parameters in the system.

OK, once Patrick has performed is “high-level” analysis he may then start digging a bit deeper in to some of the areas that may lead him to the root-cause of the fluctuation. He may perform some more detailed analysis, maybe choose to monitor some specific metrics, define some additional more detail or focused metrics. If he really is trying some advanced analysis he may try and observe dependencies between metrics for a period of time. That means monitor maybe a few metrics and how they change in relation to each other.

What is described here is really a simple scenario of human behavior exhibited when we perform troubleshooting. Although this as simple behavior for us, when we think about the data and data structures that we need to support what Patrick is trying to do, we may quickly realize that the complexity abounds. Modern business intelligence concepts such as multidimensional analysis, OLAP, and practices for data aggregation provide the tools. However it takes a lot of work and process knowledge to transform the base process data to such information structures.

This I believe is the main challenge in modern manufacturing systems. Compounding this problem is that effective analysis needs to use information from all the host of system that may reside in a manufacturing business, i.e. ERP, MES, Automation, Historians, LIMS and others. Most manufacturing intelligence tools that are in the market today simply do not address this simple scenario. If we do our inbound marketing work correctly and draw up the scenarios above, with Patrick our main persona, the problem definition is straightforward; however the engineering task required to solve it is not.

What makes a home sell?

This i a bit off topic, but still and interesting question...

What makes a house sell? I have been pondering this question, obviously since I am trying to sell my home. How do you get into the minds of the people that may be potential buyers? There are of course the standard things that the real estate agent tells you to do such as the de-cluttering, remove personal objects, make it clean and tidy, price, the signs, etc. But when you walk into a home what is it that makes one like or dislike this home?

I wish I could get into the minds of these buyers, but as a seller you get no exposure to the real people that visit your home when it is cleaner than it has ever been. They leave no trace, no scent, and no feedback. Maybe I should consider some hidden cameras? Maybe ask them to fill out a questionnaire before they leave – right!

My only method of understanding my potential buyers is by asking others within my network; what is it that made them buy the house they currently own? So this is it, my plea to all - please let me know who my buyer persona is?

Inbound and Outbound Marketing according to Pragmatic Marketing

This may be redundant information but I wanted to make sure that it is persisted somewhere for reference. It is really a summarized version of some of the teachings from Pragmatic Marketing.

Inbound Marketing

Understanding of the markets that are targeted by the company's/products' "distinctive competencies". The idea is to gain unequivocal understanding of the market, the people working in this market, and specifically the problems that they have. The goal is to provide product features that directly solve the problems in the market. In order to do that the product management activities are focused on defining and prioritizing these problems and conveying them to the product development as market requirements. The driving concept is that a product (and its features) need to do a job for the customer. For example: Online bill pay. the job is to pay bills, if you did not have this capabilities you would have to do it manually which is time consuming and tedious. Therefore it is a Market Oriented feature it solves a distinct problem for the customer.

Outbound Marketing

These activities involve the positioning and messaging of the product. It involves traditional marketing as well as what is now widely adopted "the new rules of marketing" using the internet as the main conduit. Using "viral marketing", new media, blogs and eBooks are some of the methods. The goal of all of these activities is to generate demand and leads that can be turned into license revenue by the sales team. One of the methods to expose the products to the market is using a concept called  "Marketecture". The idea is to describe the product (and its features) to the market not by its technical functionality, but by the problems that it solves for the users. In other words it is a market oriented description of the product that is developed as a result of the "Inbound" activities.