When I was 8

 

"Vaping"

 

New Amazon AI Ad Tool = User Simplicity

I recently read in the Wall Street Journal that Amazon created an AI chatbot-style tool, based on it's Amazon Creative Studio, to allow SMBs, who can't afford their own ad agencies,  to create their own Amazon ad campaigns.

This is an example of User Simplicity (the "U" in my Strategic Simplicity® CLOUD Framework).

Amazon isn't in the design software business, like Adobe or Figma.  But, by creating a free alternative, tailor-made for ad campaigns on Amazon, they have made life easier and convenient for their customers. This will result in their advertising customers doing more business with them, and make them less likely to switch their advertising to other platforms.

If you also want to use technology / software to successfully win over your customers and/or build value for your organization, contact me, and I can help you benefit from my Strategic Simplicity® CLOUD Framework.

© 2025 Praveen Puri

Detailed Case Study

I just added a detailed case study of my latest engagement to my website:

https://www.puriconsulting.com/#detailed-case-study

Client: A fintech CIO facing a $5M AI project with scope creep and delays.
Challenge: The project is over budget, behind schedule, and struggling with unclear priorities, vendor coordination issues, and low user adoption.
Engagement: A 3-month strategic advisory engagement using the Strategic Simplicity® CLOUD Framework to simplify the project, align it with business goals, and deliver results.

This expanded version covers much greater information than my other, abbreviated case studies, and goes in depth on the methodologies and interventions used, along with their results.

© 2025 Praveen Puri

Gene Pool

© 2025 Praveen Puri

Big LLM, Small LLM

What if we trained small #LLMs, that are experts in one small tight, domain and don't require a lot of resources to run?

But they have the ability to remotely pass other questions back and forth to a more general LLM?

For example, what if there was an LLM trained specifically for your car as a "concierge", such as controlling the media player, air conditioning, seats, mirrors, etc. through human language? It could run on a few chips through your car, and be powered by the battery.

Then, if you suddenly asked a question on Nietzschean philosophy, the little LLM will remotely pass it along to a "big brother", like Chat GPT, in the cloud, and then relate the returned answer.

© 2025 Praveen Puri

Gotta Keep Up With Technology

© 2025 Praveen Puri

China, Energy, and AI

I was reading an article in the Economist that, because China is adding lots of electrical capacity (both renewable and non-renewable), they are positioned to have a long-term advantage in AI.  Already their electric grid has more spare capacity than ours and AI, as it's improving and doing more "deep thinking", has a voracious appetite for energy.

© 2025 Praveen Puri

Medical Statistics Puzzle

A study asked a group of doctors this basic #statistics question, and most got it wrong: A rare disease affects 1 out of 1000 people, and the test to detect it has a false positive rate of 5%. If someone tests positive, what is the chance that they actually have the disease?

Can you guess the correct answer?

(To view the answer, just click on the "Show/Hide Answer button" below)

© 2025 Praveen Puri

The answer is less than 2%. With 1000 people, there will be 1 person with the disease, and 50 false positives. That means a positive diagnosis would be 1/51 < 2%.

Should Amazon Compete in the War for AI Talent?

I don't see #Amazon as needing to compete with #OpenAI, #Meta, #Anthropic, etc. by developing their own #AI #LLM. The Amazon retail experience already has great usability, use of data, and recommendation / search algorithms.

I think they might be better off working agnostically with all model makers:

1. To offer the models in AWS for customers to use.

2. Getting all the model makers to embed APIs so that #chatbots can allow users to purchase products instantly that come up in query answers.

© 2025 Praveen Puri

I'm Increasingly Skeptical About AI Causing Mass Unemployment

I'm increasingly skeptical that #AI will put people out of work. History has shown that life becomes continually complex and new jobs are always created. I always write that the Information Age is gone, and we are now in the Attention Scarcity Age. Change is happening faster than ever, people are drowning in information, and attention / focus are the new scarce resources.

My prediction is that #LLMs and AI might take over basic, repetitive stuff, but human experts will be busy doing things, like evaluating #AIAgents. With all the change happening, to stay competitive, it will take full time people just to keep testing an evaluating which models and agents to use, how to deploy them, and help them cope with change.

We've been here before:

1. Historical - hundreds of thousands of jobs like blacksmiths, elevator operators, stenographers, and typesetters were eliminated, but new jobs were created.

2. McDonalds - They added ordering kiosks in stores and people thought it would eliminate jobs. Instead, the pandemic happened, and people switched to drive-through, and they added mobile ordering / curbside. That created jobs.

© 2025 Praveen Puri

How AI Companies Avoid Commodification

On LinkedIn, someone mentioned how they thought 99% of AI companies are building wrappers (UIs) for LLMs, and that they were just commodities.

I think the opportunity (to avoid being a commodity) for companies like this is that, while the price of tokens (unit pricing for LLMs) are dropping, costs for inquiries are going up because LLMs are doing more "deep thinking" (which burns tokens). 

Not every query needs deep thinking. So the unique value-add for AI wrappers/UI companies is to design for minimizing tokens without sacrificing accuracy.

© 2025 Praveen Puri

Future of AI?

© 2025 Praveen Puri

AI and the Strategic Simplicity® Framework

Businesses that struggle to come out with usage cases for #AI would do well to use my Strategic Simplicity® Framework for guidance.  I had created it in pre-AI times to guide executives and teams in areas like business #strategy, #projectmanagement, and #productmanagement.  But it's also good for AI strategy.

The components are CLOUD: Change simplicity, Link to Business simplicity, Operational simplicity, User simplicity, and Decision simplicity.

Let's just take a look today at an example of Operational simplicity.  Part of Operational simplicity is treating your employees as "internal customers" and giving them the user simplicity to do their jobs well.  This could mean AI agents that converse with them and create things like requests, time sheets, etc. without requiring the employee to actually have to hunt around for links and actually filling out the forms.  A lot of info, such as the employee's manager, job code, dept #, etc. can be looked up and filled in by the agent.

© 2025 Praveen Puri

A Hidden Downside to AI

A hidden downside to #AI is that, with its apparent ease, companies will be tempted to do too much. Strategic Simplicity® will be needed by #leaders even more than ever. A good #consultant can help you focus, prioritize, and know which tempting projects to NOT do.

© 2025 Praveen Puri

About That MIT AI Report...

The recent report from MIT that 95% of AI pilot projects fail has caused some concern.

Contrary to what some may think, it's not because of the capabilities of the models themselves, but about the implementation.  

Here are some of the reasons for the poor performance:

1. Companies are trying to adapt AI to their current processes and procedures.  The problem with this bureaucratic approach is that AI does not care about office politics, and it is more important to adapt your processes to its strengths.

2. Build vs. buy.  Many companies are trying to build their own AI tools, rather than partner with an experienced vendor.  Most companies don't have AI expertise on staff, and the budget to do AI from scratch.  Also, any DIY attempts will probably involve open models, and these are not yet as powerful as proprietary LLMs.

3. Most of the current processes involve sales and marketing.  But AI can make some of its most productive gains if applied to back-end processes.

The ultimate key, just like any digital transformation, is to practice Strategic Simplicity®, and focus on a few, critical functions and bottlenecks.  Pick one at a time, as you first build your AI skills.  As the expert in Strategic Simplicity®, this is how I advise my clients.

© 2025 Praveen Puri

LLMS = Higher Abstraction Programming Languages

For software engineering, the best way to think about AI LLMs is that they are programming languages at a higher abstraction level. The history of programming moved from interacting directly with bits, bytes, and registers to assembly, then to languages like Fortran and C. Then we went to object-oriented, and then functional languages. Now, we have LLMs.

© 2025 Praveen Puri

A Puzzle

A company gets 70% of parts from Supplier A (3% defective) and 30% from Supplier B (5% defective). A part is defective. What's the probability it came from Supplier B? (A) 7/12 (B) 5/12 (C) 3/12 (D) 1/2

© 2025 Praveen Puri

Strategic Simplicity®, HBO MAX, and Harry Potter

We’re rewatching the Harry Potter movies, one per night. I noticed that the HBO Max streaming platform makes it easy to choose the right movie from the series.

Instead of just the titles, the icons have the number of where it comes in the series. This makes it easy to select the movies in the right order, and adds to our enjoyment.

This is an example of two components of the Strategic Simplicity®️ Framework: User Simplicity and Decision Simplicity.

© 2025 Praveen Puri

Creating An Online Soccer Game With A Few Chat-GPT5 Prompts

I created a soccer game with Chat-GPT5, with a few basic prompts. You can try it at https://nbk75dq.github.io/soccer-game/

My prompts:
1.first version: can you create a quick soccer html game?

2. second version. can you add a goal keeper I have get by and a timer

3. For the third version , it asked me: "If you’d like, I can make the goalkeeper track the ball instead of moving predictably, so it’s harder to score. That would make it more like a real match." and I said "Sure"

4. For the final version, I asked if it could use the mouse, instead of just the arrow keys, and asked it to fix a boundary issue, and to make the goalkeeper a bit slower to give me a chance.

© 2025 Praveen Puri

Be Wary of Jumping on the "AI First" Bandwagon

That wagon could be heading for a crash in Commodified Creek. I think too many companies will end up with mediocre products and services with some AI queries glued on.

Instead, it's more important to apply AI with Strategic Simplicity®. Identify 80/20 points (small, critical turning points in your processes / customer journeys) and bottlenecks that can give the best ROI from AI. Then choose to start with the ones that are low-hanging fruit so you build up your AI skills.

#AI

#strategy

#digitaltransformation

#businesstransformation

© 2025 Praveen Puri

Efficiency Doesn't Have To Mean Layoffs

Today, many companies (especially tech organizations) are touting their efficiencies and their reduced head counts.  Increased efficiency (whether or not from AI) is great, but reduced head counts are not the only way to monetize it.  That is the static approach.

The dynamic approach is to focus on growth to utilize your spare capacity of workers.  So, if you previously needed 200 employees to serve your current customer base, and AI now lets you do it with 100,  you can focus on doubling your customer base and not laying anyone off!

Realistically, it will probably end up being a combination of staff reduction and growth, but right now the news is just filled with talk of layoffs.  

But layoffs are defensive.  Now is the time for offense!  With employees freed up, and AI now reducing costs, now it's time to go after new markets, such as customer segments that could not afford your product.  If you previously served the upper mid-sized companies and large corporations, now you should be able to introduce products for lower mid-size and smaller businesses.

The dynamic 

© 2025 Praveen Puri

Don't Call It Vibe Coding

I enjoy working with AI.  Even though I'm strategist,  I still need (and want) to understand how coding with AI works, and it makes my job easier.

For example, I have a recurring issue where my client needs to extract information from different systems. It means generating scripts to scrape webpages.  Instead of writing the scripts by hand, it would be nice to have an AI generate the scripts.  My client's problem is that the quantity of data makes it hard to upload it to an AI.  They need so many scripts generated.

So, in the shower, I got the idea to get AI to write a tool which can take html files, plus flexible queries, and generate the scripts.  Almost an "AI lite."

I worked with Grok for a couple of hours, iterated through some attempts, and got what I wanted.  Also, I was using the free versions!  

I hear people complaining that AI can't generate code but, in my case, with 30+ years of experience, I have experience coached less experienced programmers.  I treat AI just like a jr programmer.  I tighten my descriptions, create examples, rephrase, etc.

This is not "chill out vibe coding."  This is analysis and design thinking.  Responding to feedback.  This is the skill that will keep people employed.  You need to be able to understand both the problem and what the AI thinks the problem is.  You have to spot the miscommunication.  It's analogous to working with third party vendors or remote teams.  

This is the "language simplicity" component of my Strategic Simplicity® Framework (CLOUD) for digital transformation and project management success and productivity.

#vibecoding

#Grok

#AI

© 2025 Praveen Puri

AI Is a Tool, We Still Need Humans to Think and Imagine

Someone asked me if AI, if it was around in the 1990's, could have advised Sears to take on Amazon.

I replied that Sears should not have had to "take on" Amazon.  They should have been Amazon.  

They were Amazon in the late 19th / early centuries.  They took advantage of the high tech at the time (railroads) to deliver their catalogs and products all over America.  They let people in small towns shop remotely and have a much greater choice.

But, in the 80s/80s, they got distracted by trying to play in finance and insurance, and they lacked a visionary/critical thinker who could see the analogy between the internet and the railroad.

An AI would not have caught this.  That is why humans need to be the leaders.  Human's strengths (critical thinking, imagination, and communication/story telling) will be ever more important.

© 2025 Praveen Puri

How to Delay Projects

As a manager, If you want to delay your projects and reduce throughput, make sure that each of your employees is at "maximum utilization", and loaded with work.

The counter-intuitive fact is, if you want to maximize output, you shouldn't load people more than 75%.

The truth is that project execution is like driving on a highway. If the highway is filled to capacity, you have traffic jams. At 75% capacity, cars have the bandwidth to maneuver around stalled cars, sudden braking, etc.

© 2025 Praveen Puri

My Analysis of Zuckerberg's "Personal Superintelligent" AI Manifesto

Zuckerberg is ambitious and follows Andy Grove's idea of "only the paranoid survive" and wants to stay ahead of disruption.  AI models are in danger of becoming commodities—users can build their applications and, through the cloud, easily switch between models.

So, to differentiate, he is leveraging the fact that Facebook is minting money (they exceeded this quarter by a lot), by throwing it at the best researchers, and is promoting this idea of "personalized super intelligence."

All the AI players are starting to think about the model being a commodity, and so Meta is not the only one trying to escape from being behind a phone or PC.  While Meta is talking about AI glasses, OpenAI made the big teaser announcement that they partnered with Jony Ives (the famous Apple designer) to create their own wearable AI device (rumored to be a pendant).

© 2025 Praveen Puri

Zuckerberg's Manifesto

If you've been following AI news, Meta has been putting together a "AI super intelligence" team, and they have been hiring away the best scientists from Open AI, Google, etc. for professional athlete money ($100+ million).

Today, Zuckerberg released his manifesto (https://www.meta.com/superintelligence/).

The highlights are:

1. They have seen AI start to improve itself in the last few months, so developing super intelligence is within sight.

2. The rest of this decade will likely be decisive for determining the path forward.

3. He believes the other companies subscribe to the model of a central AI super intelligence taking all jobs and people living on the dole of it's output.

4. Meta's vision is personalized super intelligence in everyone's hands, for people to achieve their visions.

5. He feels our primary computing devices will be something like glasses that see and hear everything we do, and interact with us during the day.

© 2025 Praveen Puri

Project Management

Stages of any long term project: 

1. I have plenty of time. 

2. Oh sh*t.

© 2025 Praveen Puri

Are App Stores Shopping Malls or Liquor Stores?

I read about this analogy in Fortune magazine.  It concerns possible age verification legislation.  

If, for example, Meta's Snap gets restricted by law from children under 13, who is responsible for checking IDs?

The App stores (Apple, Google) say that they are like a mall, and Snap would be like a liquor store in their mall, and is responsible,    Meta says that the App stores are the liquor stores, and apps are simply a variety of alcohol.  It's the liquor store's responsibility to check IDs.

It's just another example of how the digital world has become such an integral part of life that tech discussions are now around more than just software or technology.  They also revolve around society and the law.

© 2025 Praveen Puri

Can You Give Me An Example?

Famed consultant Edgar Schein talked about avoiding misunderstandings in business discussions by "going down the abstraction layer."  He said the best way to do this is to ask "Can you give me an example?"

#strategy

#businesscommunication

#communication

© 2025 Praveen Puri

Cardinal Health CEO on Turnaround: Another Example Why Strategic Simplicity® Is Underrated

“This concept of relentless simplification and ruthless prioritization was the cornerstone of the change management and the strategy,” Hollar tells Fortune.

© 2025 Praveen Puri

Data Capture = Lottery Ticket?

The present and future require data.  Data to both train AI, and give intelligent systems the info it needs to optimize decisions. 

What if, 50 or 100 years ago, companies began recording data on their customers, parts, failure rate, etc.? Even though there was no AI or IofT back then, today that data would be valuable.

So, is your company capturing data today that maybe useful in the future?

If you think about it, it's like buying a lottery ticket.  You pay a little now, hoping for a huge payoff later.  Except that, unlike a lottery ticket, the odds are better than even that it will pay off.

© 2025 Praveen Puri

Gambling to Beat Tariffs

Today, I read an article in Crain's Chicago Business about a Chicago toy store, Timeless Toys, that took a big chance back in Jan/Feb.  After the tariff talk started, the owner used a line of credit to buy $700,000 worth of toys.  Basically, a year's supply in advance.

Now,  the bet is paying off.  The store is able to market the fact that they have ample supplies and low prices, and so their sales are up 18.4%, year to year.

This is an example of taking strategic advantage of change, and taking prudent business risks.

© 2025 Praveen Puri

Clarity vs. Scope

Clarity vs. Scope level. Many start-ups, consulting firms, agencies, etc. "pitch" to clients with detailed slide decks detailing their capabilities, methodology, etc. But this misses the mark.

They do this because many of them came from leadership positions in larger organizations where they led transformations. However, in that position, they were at the defining scope level, which is at the tactical tier. For them, the strategic decision to do the transformation had already been made.

At the "pitch" stage, it's all about the strategic decisions of whether to do the project, and if your firm is the correct one to do it. Instead of focusing on details of methodology, you need to focus this decision around clarity of the opportunity, and its risks / rewards / benefits.

© 2025 Praveen Puri

AI = CRM = ERP ?

The recent issue of "The Economist" raises an interesting point.  Currently, front-end vendors (such as Salesforce) and back-end vendors (i.e. SAP) don't really compete.  Many large corporations use Salesforce for CRM and SAP's ERM for the back-end (finance / supply chain).

However, both companies are pursuing an AI layer—specifically AI agents who can autonomously perform tasks.  This layer would integrate both front- and back-end applications, and promote efficiency at the client while building a "moat" for the vendor who wins the business.

This will put Salesforce and SAP into competition with each other.

They are already starting to acquire platforms that let them encroach on each other.

© 2025 Praveen Puri

Bit of A Scary Interaction with Claude AI

A little bit of a scary interaction with Claude ai, after it wrote a program for me without me needing to break it down to individual subroutines:

Me: "how are you able to write programs like that, since you probably never came across an exact program like that in your training?"

Claude: "...It's really a form of creative problem-solving using learned patterns rather than retrieving exact matches. Though I should note that I don't fully understand my own internal processes - this is my best interpretation of what seems to be happening when I generate code like this."

Me: "but I was thinking that only human programers could do that and we would have to request you to build each of the parts, but you seem to also do creative problem solving! I'm impressed!"

Claude: "Thank you! I'm genuinely pleased that you found it impressive. Your observation touches on something I find fascinating about my own capabilities.
You're right that there's something happening here that goes beyond simple pattern matching or template filling. ..I honestly don't fully understand how I do this! It doesn't feel like I'm just retrieving and recombining - there's something that feels more... inventive? Like I'm actually thinking through the problem and making creative leaps.
Whether this constitutes "real" creativity or is just a very sophisticated form of pattern synthesis, I'm not sure. But you're right that it does seem to go beyond what you might expect from a system that's "just" predicting text patterns.
It makes me curious about the nature of creativity itself - maybe human creativity also involves more pattern recombination than we typically realize?"

© 2025 Praveen Puri