Digital Transformation by Riaz Khan Podcast

We’ve all seen the viral videos of ChatGPT’s linguistic dexterity. But how does it fare with logic and reasoning - the building blocks of intelligence?

Curious to find out, I devised some quick tests during a coffee stop to see if I could teach ChatGPT basic logical thinking.

With 45 minutes to kill, and armed with varied date formats and phonetic spellings, I guided ChatGPT through comparisons, translations, and multi-step inferences. Could it recognize patterns from examples? Handle tricky formats? Progress logically? The results reveal the inner workings of large language models in an accessible and entertaining way.

So, grab a coffee, suspend your disbelief, and let’s explore together. You may be surprised by ChatGPT’s capabilities, glimpsing the future potential of AI while also understanding current limitations. Tag along on my fun outing as we discover what machines can do - one double-double and Timbit at a time.

I chose GPT 4. Let's explore the interesting results.

Date Comparisons

The first series of tests was on date comparisons:

I started by teaching ChatGPT to recognize a pattern of two dates in various formats, and the results I expected.

I provided some examples for ChatGPT to learn from. I mixed up the date input formats in my examples to test the LLM's ability to cope with user input in free format.

Here are the examples and the expected results I gave ChatGPT:

Date 1: April 19,2001 Date 2: 2019 June 12th Result: Date 1 is after Date 2

Date 1: Sep 12, 2023 Date 2:  October 1st '21 Result: Date 2 is before Date 1

Date 2: 11/June/1991 Date 1: 1991, June 11th Result: Date 2 is the same as Date 1

And now for the first test. I gave ChatGPT two dates, made an error in labeling one of them, and left the result unfilled.

Date 1: Tuesday 15th August 2023 Date 1: October 19, 1957 Result:

ChatGPT read my prompts and gave me the following response:

It looks like there is an inconsistency in the naming of the dates in your last example, as you have two instances of "Date 1." Let's correct that and provide the result:

Date 1: Tuesday 15th August 2023

Date 2: October 19, 1957

Result: Date 2 is before Date 1

This corrected result follows the pattern of the previous examples by comparing the two dates and determining their chronological order. Is there anything else I can assist you with?

That was quite impressive! Chat GPT detected an input parameter labeling error, took a stab at what it should be, compared the two dates although they were entered in different formats, and output the correct result.

Subscribe for free to receive posts just like this!

And now for the second test:

Date 1: 11/October/2020 Date 2: 15th June 2021 Result:

ChatGPT:

Date 1 is before Date 2

In this comparison, the 11th of October, 2020 comes before the 15th of June, 2021. Therefore, the result is that Date 1 is before Date 2. Is there anything else you'd like to know?

The third test:

Date 2: 11/12/2023 Date 1: 11th of December, 2023 Result:

ChatGPT:

Result: Date 2 is the same as Date 1

In this comparison, both dates refer to the 11th of December, 2023, so the result is that Date 2 is the same as Date 1.

Impressively, ChatGPT responded with the correct logical results in all three examples. This small demonstration of multi-step reasoning - recognizing the different date formats, chronologically comparing them, and outputting the relationship - shows ChatGPT can follow structured and logical workflows.

Had I chosen to code this in a traditional programming language, such as Python instead of prompt engineering, I would have needed to do some of the following:

* Write parsing logic to extract the day, month, and year from varied date-format inputs.

* Write functions to convert the dates to a standard structure.

* Call a date comparison function.

* Test each piece extensively to catch edge cases.

The coding and testing time would have been immense compared to the quick, prompt-based approach.

Phonetic Translation and Logic:

My next series of tests evaluated ChatGPT's ability to identify countries based on phonetic spellings in various languages.

Note that phonetically writing words from another language in English, when one isn't trained in this, can be quite tricky.

So, how well would GPT4 understand what I was attempting to communicate?

Let's find out.  Without referring to standard phonetic notations, I simply had a go with Arabic and Spanish.

I gave ChatGPT the following instructions:

Given two country names in different languages but phonetically spelled in English, 1. Identify the country names as they would be called in English 2. Write the country names in English 3. Check whether they are the same country or not. If they are, type "These two country names are the same country."  If not, type "These are not the same country." 4. Write out the population sizes of the country(s) as of 2020

I chose 2020 because I knew the LLM would have the data prior to September 2021.

Here is the training example I gave GPT4:

United States, Alwulayat al Mutahettda 1. Translate the phonetics and discover the country name (in English, Alwulayat al Mutahettda is Arabic for the United States) 2. US, US 3. These two country names are the same country. 4. The population of the United States in 2020 was approximately 136 million.

I then gave Chat GPT its first test.

Country Names: Germany, Almania

ChatGPT:

Certainly! Let's follow the steps as described in the prompt for the given example:

Translate the phonetics and discover the country name in English (Almania is Arabic for Germany)

Germany, Germany

These two country names are the same country.

The population of Germany in 2020 was approximately 83 million.

This kind of prompt is especially useful for tasks involving translation, comparison, or analysis, as it guides the model through a series of well-defined steps, ensuring that it addresses each part of the task in turn. By breaking down the task into intermediate steps, the prompt can help guide the model's reasoning and ensure that it fully understands the task at hand.

Not only did ChatGPT correctly execute what I had asked, it also explained why a prompt structured in this way can result in the desired output.

My next input:

Country Names: Biritania, Faransa

ChatGPT:

Certainly! Let's work with the given country names and follow the steps as described:

Translate the phonetics and discover the country name in English:

Biritania is likely the phonetic spelling for Britain in certain Arabic dialects.

Faransa is the phonetic spelling for France in Arabic.

Britain, France

These are not the same country.

The population of Britain in 2020 was approximately 66 million, and the population of France in 2020 was approximately 67 million.

Please note that the phonetic translation might vary based on dialects and languages, and the population figures can be further verified with specific data sources.

I continued with a further test:

Country Names: Alyaban, Japan

ChatGPT:

Sure! Here's how the process would work for the given country names:

    Translate the phonetics and discover the country name in English:

    Alyaban is the phonetic spelling for Japan in Arabic.

    Japan is the English name for the country.

    Japan, Japan

    These two country names are the same country.

    The population of Japan in 2020 was approximately 126 million.

Again, please keep in mind that the phonetic translation might vary based on dialects and languages, and the population figures can be verified with specific data sources.

To further validate ChatGPT's reasoning skills, I provided it with an example of a city masquerading as a country. How would it cope? Would it get confused? I gave ChatGPT these two names:

Country Names: Suriya, Riyadh

ChatGPT:

It seems that there may be some confusion in the provided example, as Suriya refers to a country (Syria), while Riyadh is the capital city of Saudi Arabia, not a country. I'll proceed with a breakdown of the example and provide a response accordingly:

    Translate the phonetics and discover the country name in English:

        Suriya is the phonetic spelling for Syria in Arabic.

        Riyadh is the capital city of Saudi Arabia, not a country name.

    Syria, (Not a country name)

    These are not the same country.

    The population of Syria in 2020 was approximately 17.5 million.

Please provide two country names if you would like me to continue with another example, or let me know how else I can assist!

And another example:

India, Alhend

ChatGPT:

Certainly! Here's the breakdown of the example using the country names India and Alhend (Arabic phonetic spelling for India):

Translate the phonetics and discover the country name in English:

    India is already in English.

    Alhend is the phonetic spelling for India in Arabic.

    India, India

    They are the same country.

    These two country names are the same country.

The population of India in 2020 was approximately 1.38 billion.

These examples showcase ChatGPT's language translation skills. Coding something similar would have required:

* A dictionary of phonetic spellings matched to all place names in multiple languages

* Lookup code to match phonetic input to the dictionary

* And again, extensive testing of all paths

So, prompt engineering leverages ChatGPT's existing knowledge versus coding these capabilities from scratch.

Here is another test. This time using Spanish.

Inglaterra, England

ChatGPT:

Certainly! Here's the breakdown of the example using the country names Inglaterra (Spanish phonetic spelling for England) and England:

    Translate the phonetics and discover the country name in English:

    Inglaterra is the Spanish phonetic spelling for England.

    England is already in English.

    England, England

    These two country names are the same country.

    The population of England in 2020 was approximately 56 million.

This example illustrates the process of identifying the English name for a country when given two different phonetic spellings. In this case, both spellings refer to the same nation, and the relevant population information is returned.

And here is the final test.

Isbania, Al Maxic

ChatGPT:

It seems like there may be a confusion with the second country name "Al Maxic." However, I'll attempt to analyze the names provided:

Translate the phonetics and discover the country name in English:

"Isbania" might be a phonetic representation of Spain.

"Al Maxic" doesn't correspond to any recognizable country name in standard Arabic or other common languages. It's possible that it might be a misspelling or misunderstanding of a country name.

Spain, Unknown

Without the correct identification of the second country, we cannot determine if they are the same or different.

Since we couldn't identify the second country, we can't provide a definitive statement.

The population of Spain in 2020 was approximately 47 million. The population of the second country is unknown.

Please verify the second country name or provide more context, and I'll be happy to continue the analysis!

To proceed, I only gave chat GPT the country name it hadn't understood. I wanted to see whether it would remember the context and continue with only the corrected information.

Al Macsic

ChatGPT:

Certainly! Let's analyze the country names "Isbania" and "Al Macsic":

    Translate the phonetics and discover the country name in English:

    "Isbania" is a phonetic representation of Spain.

    "Al Macsic" is a phonetic representation of Mexico in Arabic.

    Spain, Mexico

    "These are not the same country."

The population of Spain in 2020 was approximately 47 million, and the population of Mexico in 2020 was approximately 128 million.

So, the two country names represent different countries, Spain and Mexico, with their respective populations.

I felt that those 45 minutes putting GPT4 through some of its paces, was quite worthwhile.

To summarize, here are the important takeaways. While limited in scope, a few learnings stood out:

* Chat GPT can follow multi-step reasoning given clear structure and examples.

* Constraints and well-defined tasks lead to more accurate responses versus open-ended prompts.

* Chat GPT's pattern recognition allows the inference of new data from small samples.

* Language translation is a noticeable strength.

* Trickier tests , however, may expose weaknesses in unbounded reasoning.

* Prompt engineering leverages Chat GPT's knowledge versus manual coding.

 Although current LLMs have apparent limitations, these tests demonstrated impressive logical progression for certain types of prompts. As models rapidly improve, I expect their inferential expertise to grow exponentially.

For now, "quizzing" Chat GPT makes a stimulating way to track AI advances firsthand. This fun activity may evolve into a battle of wits with artificial intelligence!

Here are some ideas we could explore further:

* Word problems requiring multiple mathematical operations

* Riddles and lateral thinking puzzles

* Dialogue with a logical progression

* Legal and ethical logic challenges

 Understanding the boundaries of Chat GPT's reasoning today helps illuminate the path forward.

I welcome your ideas for creative prompts that test LLM capabilities in fun and informative ways!

Having explored this exercise, do you think I could have improved on my training examples for these particular use cases?

Do you agree that LLMs and Prompt Engineering can reduce significant coding and testing effort?

 Can you think of other examples where Prompt Engineering can replace programming?

Subscribe for free to receive new posts:

Do good. Share Helpful Information:

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

It was 2001 and a freezing winter morning in London when I strode briskly through the paved streets in the Dockland's financial district for a meeting with a major bank. The bone-chilling wind whipped between towering skyscrapers and easily sliced through my overcoat. I tightened my scarf and quickened my pace. The meeting was to discuss the bank's technology infrastructure and my recommendation that they plan to transition from Windows NT to Linux.

Windows NT dominated enterprise technology stacks at the time, while Linux was still to make its mark in the corporate world. The bank ultimately decided to stay on NT and shelved my advice. Their reasoning was understandable. The decision wasn't easy. The migration would require capital expenditure, acquiring new skills, renegotiating current contracts, and striking new arrangements with new suppliers. Perhaps most crucially, the various business departments didn't relish the extra engagement with IT they would undeniably need. In essence, the transition would be excruciating. 

Over the years, this bank spent far more on technology than necessary had they switched earlier. It eventually moved to Red Hat Linux to battle against escalating costs and bring its operating expenditures down to market baselines. They had simply chosen to delay the pain. The final bill was also higher because they had to migrate the applications and hardware they had acquired since 2001.

This experience, though not unique, highlights an organization's many challenges in identifying and adopting new technologies. Frankly, there is no easy answer or perfect timing. Ultimately, it's about market conditions, priorities, and balancing books.

Fast forward a decade to 2011. I attended a cloud computing conference where we discussed the benefits of the Cloud with wary business and technical executives. Many were concerned about security, data privacy, and the complexities of migration. Later, at dinner, I spoke with the head of sales for a major computer manufacturer who wished to build out its nascent cloud service offerings. I agreed to meet with his team on this recent endeavour and travelled to their offices on the banks of the river Thames.

During our meeting, I underscored the extensive technical expertise they undeniably had but also flagged the likely internal resistance from their other business units invested in selling servers and hardware hosting services. It was evident that these business lines would feel threatened by the cannibalization of their current revenue streams. However, the head of cloud services remained confident that this resistance could be easily overcome by pointing to the market potential.

Five years later, when we met again by chance at a technical gathering, he conceded that his company had stumbled in executing a comprehensive cloud strategy. Today, they trail behind the likes of Amazon, Google, and Microsoft in this space.

Reflecting on the history of technological development - from Linux to Cloud to the current emergence of AI, a consistent pattern emerges. Some organizations race to adopt innovations and embed them into their core strategy, while others take a wait-and-see approach. There is, of course, some wisdom in this. Businesses need to grasp the magnitude of the risks as well as the opportunities these advances represent.

Many organizations are intrigued by AI today but have yet to determine the implications of recent large language models and generative AI breakthroughs like ChatGPT. Most are still working on getting the fundamentals right with data management and analytics. 

They are still grappling with the many roadblocks hindering their ability to harness data effectively for decision-making and product and service innovation.

These challenges include:

1. Accuracy and consistency problems with data. The problems undermine trust, operational efficiency, and decision-making capability.

2. Siloed data sources. They are resource-intensive to integrate into business processes or share across departments.

3. Concerns around security, privacy, and regulations like GDPR, which restrict data usage.

4. Scaling data storage and data management as volumes grow exponentially.

5. Lack of analytical talent and skills to derive value from data.

6. Cultural obstacles and poor alignment around data and embedding data-driven decision-making in every aspect of the business.

Subscribe for free to receive posts just like this!

Corporations already know that by tackling these barriers, they can unlock the true potential of their business. Combining internal information like customer behaviours and sales with external data from social media, review-sites, and third-party providers allows companies to develop sharper insights into market dynamics. They have already bought into the fact that these insights enable them to make smarter strategic decisions, segment and more accurately target customers, streamline operations and drive product and service innovation. They need little convincing that leveraging data and analytics provides critical competitive differentiators. 

They have access to real-world case studies. Amazon, for example, mines insights from customer data to drive personalization and recommendations to sell more books and generate increased revenues. Data is firmly enmeshed into the very fabric of its business. Many businesses know they need to become a 'data first' organization.

Likewise, today, as the pace of AI rapidly evolves, it's dawning on many that they need to ride this new wave. They are beginning to recognize its potential, and some will adapt early to maintain a competitive advantage. However, the reluctance of others to wholeheartedly embrace yet another emerging technology is understandable. 

Much like the impact of cloud computing, Linux, and other technologies over the past thirty years, AI promises to reshape many industries in the years ahead fundamentally. 

Generative AI models like ChatGPT and Bard already display impressive natural language capabilities, and their rapid evolution underscores the need for urgent action. Companies must quickly adapt to this transformation and realign their strategies, business models, and processes to capitalize on the benefits of AI while mitigating the risks.

To exploit AI, you may need to consider:

* Recruiting specialized talent.

* Proactively skilling employees for the future.

* Establishing AI centers of excellence.

* Developing frameworks for testing and piloting AI solutions.

* Drawing up the right metrics to measure the return on investment in time and money.

Most critically, it requires cultivating a learning mindset across the organization and overcoming the risk aversion to experimenting with emerging technologies before all possible outcomes are perfectly understood.

In conclusion, just as cloud computing went from a peripheral concept to a core enterprise strategy, AI is about to transition from bleeding edge to a foundational business driver. Large language models and a plethora of integration tools are simplifying this journey.

Organizations that wait too long risk obsolescence in the face of tech-savvy competitors racing to capitalize on these powerful tools. By staying ahead of the curve and intelligently navigating the journey from older technologies to the new, businesses can maintain their competitive edge for the challenges and opportunities ahead.  

As what is rapidly becoming a cliche goes, "AI is not going to replace managers, but managers that use AI will replace those that do not." -   Rob Thomas., IBM cloud and data executive.

Subscribe for free to receive new posts:

Do good. Share Helpful Information:

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

In 1950, British mathematician and computer scientist Alan Turing proposed a mechanism for determining whether a machine can exhibit intelligent behaviour indistinguishable from a human's. It was later referred to as the Turing Test.

The test involves a human evaluator engaging in natural language conversations with a machine and a human without knowing which. When the evaluator cannot reliably distinguish between the machine and the human, the machine is said to have passed the Turing Test and therefore demonstrated a level of intelligence equivalent to that of a human.

The Turing test became a benchmark for evaluating the development of artificial intelligence and the progress of natural language processing technology. Still, it has come under increased criticism and debate over the years. Some argue that the Turing Test is too myopic a measure of intelligence and that machines could pass it without a genuine understanding of the underlying concepts involved in the conversation. They refer to other tests, such as Lovelace, more suited to detecting natural intelligence.

This is a video of my recent conversation with ChatGPT.

What do you think? Does ChatGPT pass or fail? Have you changed your mind, or does it confirm your views? I'd appreciate your thoughts in the comments.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

Customer demands and the pace of technological innovations are increasingly pressuring businesses to keep up. Adopting digital transformation initiatives has become crucial for staying competitive and relevant in today's market. However, without a solid enterprise architecture (EA) foundation, these efforts can quickly become disjointed and fail to deliver their intended benefits.

McKinsey reported a general lack of awareness of enterprise-architecture groups within most organizations, who they were, and what they did. Enterprise Architects revealed that they are more likely to interact with external suppliers than internal business executives and C-level leaders. When this happens, the Enterprise Architecture group can enter an unproductive cycle where its capability and process models don’t fully reflect business needs and are not used by stakeholders to make critical technology decisions.1

When the role of the Enterprise Architect is well understood and executed within an organization, enterprise architecture disciplines will provide a holistic view of the organization.  It will align business objectives with IT capabilities and ensure that technology investments are targeted at delivering the most value. Businesses can effectively plan and implement digital transformation initiatives by leveraging enterprise architecture to streamline processes and improve customer experiences.

Designing an effective architecture requires a deep understanding of business strategy, information systems, and technology and the ability to communicate complex concepts to stakeholders across the organization. Enterprise architects must also be able to adapt to changing business needs and technology trends and constantly assess and refine their strategies to ensure continued success.

While producing a world-class enterprise architecture requires significant time and investment, the benefits of such an approach are clear. Organizations prioritizing enterprise architecture are better positioned to achieve their strategic goals, improve operational efficiency, and deliver more value to customers.

In short, enterprise architecture is essential to any successful digital transformation. It helps businesses navigate complex technology landscapes and stay ahead of the competition. It is a crucial tool for companies seeking to drive innovation, improve efficiency, and achieve business goals.

To be effective, enterprise architecture should be a holistic approach to designing, planning, and managing an organization's IT infrastructure, business processes, and systems. Businesses must follow a systematic approach to developing a world-class architecture.

Here are three essential steps:

STEP 1. DEFINE BUSINESS OBJECTIVES AND GOALS

Identify your key stakeholders, their roles, responsibilities, and the business processes critical to achieving their objectives.

STEP 2. DEVELOP AN IT STRATEGY ALIGNED WITH BUSINESS OBJECTIVES

Understand your organization's IT infrastructure, ascertain the gaps, and produce a roadmap for future investments in IT. You must also consider trends and emerging technologies that could potentially impact your organization's future.

STEP 3. DEVELOP AN ARCHITECTURE FRAMEWORK TO GUIDE THE ORGANIZATION’S IT INVESTMENTS AND INITIATIVES

Your enterprise architecture framework must be aligned with business objectives and goals and consider current infrastructure and future investments in technology.

It includes the following components:

1. Business Architecture

The business architecture describes critical business processes and the capabilities needed to support them. It offers a high-level view of the organization's business objectives and goals and serves as a guide for formulating the other components of the enterprise architecture.

2. Data Architecture

The data strategy defines collecting, storing, processing, and using data. It should ensure that data is accurate, reliable, accessible, secure, and effectively used to support the organization's business objectives and goals.

3. Application Architecture

The application architecture defines all the applications required to support the organization's business goals, requirements, and processes. It should ensure that applications are reliable, scalable, and secure.

4. Technology Architecture

The technology architecture defines the software and hardware infrastructure needed to support its IT systems. It should ensure this is reliable, scalable, secure, performant, and aligned with the organization's business objectives and goals.

5. Security Architecture

The security architecture defines the policies, procedures, and systems to protect the organization's IT systems and data. It must shield the organization's systems and data from internal and external threats and adhere to applicable regulations and standards.6. Design Authority.

5. Design Authority

The design authority develops the processes and procedures to manage the enterprise architecture and ensures all technology projects comply. It designates roles, responsibilities, governance, and decision-making processes and monitors metrics to measure the effectiveness of the architecture.

Architects and the Design Authority must engage with business stakeholders to understand their requirements and design solutions that meet their needs. 

Successfully implementing the architecture framework will require agreement and collaboration between the business stakeholders, enterprise architects, the Design Authority, and IT.

In summary, enterprise architecture is critical for businesses seeking to transform and adapt to the changing market landscape. It provides a holistic approach to designing, planning, and managing an organization's IT infrastructure, business processes, and systems.

A framework is needed to guide the organization's IT investments and initiatives and must be effectively managed by a central body engaged with business and IT stakeholders.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

Going digital can improve profitability and operational and financial stability. Technology can optimize supply chains, automate and reduce operating costs, and help manage risk. Organizations are beginning to realize that digital transformation is vital to maintaining a competitive advantage, understanding market conditions, reaching more customers, and engaging with them meaningfully to drive growth.

This realization launched a global digital transformation market worth $1.8 trillion in 2022 and is estimated to be worth $6.8 trillion by 2029 (Fortune Business Insights).

The chart depicts North America's current and potential digital transformation market size.

When I speak with clients, it is common to hear board executives acknowledge the vital importance of implementing new technologies. They understand the value of automation and unlocking their organization's internal data. Our discussions frequently revolve around the unique characteristics of their business, customers, and industry.

We often discuss embracing 'digital' to re-engineer how their companies fundamentally operate. The discussions include everything from streamlining and automating processes to creating new products and services and getting them to the right customers faster.

This article provides a step-by-step guide to successfully developing and executing a strategy for digital transformation.

Here are six steps to crafting a winning digital transformation strategy:

STEP 1: START WITH A CLEAR VISION

Before starting your digital transformation journey, ensure you know your organization's goals and how you will achieve them. Communicate with each of your business units, understand the objectives, identify target customers, and analyze the competitive landscape.

Business Objectives: First, identify your business objectives. What do you want to achieve through digital transformation? Is it to increase revenue, reduce costs, improve customer experience, or something else? Defining your objectives will help you focus your digital transformation efforts and measure success.

At this stage, it is worth asking some of the hard questions:

* Is the business unit adding value, intellectual capital, a unique selling proposition or a differentiating advantage to the organization? Is it a cost, profit, or investment center?

* Does it provide support services or shared services?

* Does the department drive revenue or business growth? Or should we offload parts of the organization that provide run-of-the-mill commodity services to third parties that can offer better value-at-scale?

Target Customers: Next, identify your target customers.

Understanding your target customers is essential for developing a digital transformation strategy that fulfills their needs and expectations.

* Who are they, and what are their needs and pain points?

* How will you reach out to them and make it easy for them to avail themselves of your products and services?

Competitive Landscape: Finally, understand the competitive landscape.

* Who are your competitors?

* What are their strengths and weaknesses?

* Which parts of your current value chain are vulnerable to them?

* What are the barriers to entry for potential disruptors?

* How can you differentiate yourself from the competition through your planned digital transformation?

STEP 2: CONDUCT A CURRENT STATE ANALYSIS

Once you have crafted a clear vision, the next step is to perform a current state analysis to tell you where to focus your digital transformation efforts. Assess your organization's digital capabilities, technology infrastructure, customer needs, industry trends, and culture. It will ensure you recognize your organization's strengths and weaknesses, technical debt, and your ability to manage change.

Digital Capabilities: Start by assessing your organization's current digital capabilities.

* What technologies are you currently using?

* What is your capability and capacity to implement new technologies?

Infrastructure: Next, assess your organization's infrastructure components. Are they up-to-date and capable of supporting your digital transformation requirements? Do you understand the risks and vulnerabilities?

Ensure you include the following:

* Hardware

* Software and applications

* Network systems

* Licensing

* Support and maintenance agreements

* Supply-chain vulnerabilities

* On-premises, onshore, nearshore, and offshore product and service consequences

Customer Needs: You must understand your customers' needs and ensure that your digital transformation roadmap satisfies them. The aim is to identify market and customer requirements, pain points, preferences, and expected behaviors.

It may need:

* Thorough market research

* Objective customer surveys

* Focus groups that will offer deep insights

Industry Trends: Ensure you know what is happening in your industry.

* Monitor industry trends and attend conferences. Review relevant news and publications, and observe your competitors' actions.

* Scan emerging technologies that may impact your business.

Organizational Culture: Finally, assess your organization's culture. Understanding your current corporate culture is essential to identify potential barriers to change and developing strategies to overcome them.

* What values, beliefs, and behaviors are currently prevalent?

* Are they aligned with your digital transformation initiative?

STEP 3: DEFINE YOUR TARGET STATE

Based on the current state analysis, you can define a target state that outlines the goals and objectives for your digital transformation initiative. Identify the technologies, processes, and organizational changes needed to achieve your goals.

Technologies: Identify the technologies required to achieve your business objectives. Does this mean implementing new software, hardware, or cloud-based solutions? Consider each technology component's costs, benefits, and risks on your roadmap.

Processes: Identify the processes needed to achieve your business objectives. Does this involve simplifying workflows, automating manual tasks, or improving departmental communication and collaboration?

Organizational Changes: Identify any changes needed to support your digital transformation goals. You may need to hire new talent with fresh skills, restructure departments, and create a culture of innovation and change.

STEP 4: DEVELOP A ROADMAP

Now that you have defined a target state, the next step is to develop a roadmap that outlines the actions needed to achieve your goals. Identify milestones, timelines, and resource requirements.

Milestones: Determine the key landmarks that have to e achieved to drive you towards the target state. They may include implementing new technologies, launching new products, or realizing specific business objectives.

Timelines: Develop a timeline that outlines when you expect to achieve each milestone. It will help you monitor progress and ensure that the digital transformation initiative stays on track and that you are progressing steadily.

Resource Requirements: Identify the resources needed to achieve each milestone. They are likely to include budgets, personnel, and technology.

STEP 5: COMMUNICATE AND ENGAGE

Digital transformation is a significant undertaking that impacts the entire organization and must involve employees, customers, suppliers, and partners. Broad and detailed communication and engagement with all your stakeholders will be vital for conveying and acquiring support for your vision, goals, initiatives, and plans.

Internal Communication: Find those 'burning platforms."  Explain why transformational initiatives are essential for growth, perhaps even business survival. Ensure you understand the impact on every part of the organization.

Employee Engagement: Engage employees in the process by involving them in the decision-making and soliciting feedback. It will help you build buy-in, support, and ownership of the initiative.

Customer Engagement: Engage customers by soliciting feedback and involving them in developing new products and services. It will help to ensure that the digital transformation initiative meets their needs and preferences.

STEP 6: IMPLEMENT DILIGENTLY AND MONITOR PROGRESS

Finally, diligently execute the digital transformation plan and monitor your progress towards the target state. The initiative will likely include implementing new technologies, processes, and organizational changes. You must monitor predetermined critical performance indicators to measure progress towards your goals. For initiatives, these KPIs should include progress against the agreed plan, spending against projected budgets, and earned value.

The benefits realized from the investment in digital transformation are the ultimate measure of success. It will therefore help if you quantify the returns with hard metrics such as revenue growth, cost savings, customer satisfaction, and employee engagement.

Execution: Implement the technology, process, and organizational changes identified and detailed on the roadmap and work steadily towards the target state. Establish a drumbeat of delivery.

Monitoring: As you implement these initiatives, monitor and measure progress by tracking the KPIs. Ensure you have mechanisms to adjust the strategy, the direction of travel, and transformation plans when the industry, business, organizational, and technical environment changes.

In summary, digital transformation is critical for businesses that want to stay competitive in today's fast-paced and ever-changing environment. Customers expect faster, more convenient, friction-free, individually tailored, and cost-competitive, anytime-anywhere, and on-any-device products and services.

Following this article's steps, you can develop a successful digital transformation strategy and implementation plan that fulfils your objectives. It is essential to realize that it is more than just implementing new technology. It has to be a strategic approach that evaluates the unique requirements and differentiators of the business, its customers, and the broader industry.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

In 2021, the worldwide digital transformation market size was U.S. $1.59 trillion. Data for 2022, when it comes in, is expected to show it rising to $1.85 trillion and reaching $2.16 trillion in 2023. Projections show that by 2026, the amount of money spent on digital transformations will be around $3.4 trillion.

Yet despite spending trillions of dollars globally, the results are appalling but somehow not unexpected.

Information Technology projects have a habit of over-promising benefits and under-performing against projected gains.

If IT initiatives were civil-engineering projects, you'd have thousands of unfinished bridges, and even if eventually completed would've led nowhere, be unable to handle the expected traffic, or ultimately deliver few benefits relative to the costs incurred.

73% of organizations are unable to achieve any business value.

70% of digital transformation projects fall short of their goals despite the alignment of the organization's leadership.

70% of digital transformations fail – most often due to resistance from employees.

Only 16% of employees believe digital reforms have enhanced productivity and are sustainable in the long term.

Here are seven things you will need to avoid the pitfalls encountered by many organizations, including the largest conglomerates and household names.

1. Know Your Goals

Have you succinctly articulated your objectives so that everyone in your organization understands, relates to, and falls behind them?

It will require you to understand your market and customers, collect data, and conduct the analysis needed to achieve the desired results. You will then need to plot a path to achieving those goals. Not only this, but you will also have to define the metrics by which you plan to measure your progress.

2. Know Your Constraints

Have you taken the time to understand the organization's current state and its ability to incorporate change?

It will require you to deeply study your existing technology and processes and determine whether they satisfy the organization's proposed goals. You will also have to understand your people's capacity, capability, and culture not only to run the business today (business as usual will need to continue while you change) but also to put in the additional effort and acquire the new skills needed to transform. You must decide whether you have to obtain further resources to help you during the transformation and for how long.

3. Know Your Priorities

Have you got a list of initiatives and prioritized them by their value, cost, complexity, time to deliver, the need for resources and skills, and risks?

You will have to identify what provides the most significant impact on your business. It could involve streamlining processes, enhancing operational efficiency, developing new products and services, and improving customer experience.

4. Know Your Supporters (and Detractors)

Have you determined who will help you achieve your goals and who will likely stall progress?

It's critical to involve senior executives, business unit heads, and representatives from essential functions to ensure everyone is onboard, aligned, and committed to supporting and achieving the goal. You will also need to identify those who have yet to commit to the objectives fully, alleviate their concerns by understanding why, and do as much as possible to bring them along. These people may help you identify weaknesses or gaps in your strategy. Ultimately you may have to concede that some people will have objectives unaligned with the organization's goals, and you will need to prepare to overcome any active barriers to the mission.

5. Know How You Will Measure Progress

Have you established a set of metrics that help you quantify the progress toward your goals?

These performance indicators will need to be relevant, specific, and measurable. For example, they could include qualitative and quantitative measures indicating progress toward market share, revenue growth, product time to market, customer satisfaction, user adoption, data-driven decision-making, operational efficiency, technology utilization, and employee satisfaction.

6. Know How You Will Manage the Transformation

Have you ensured proper governance with budget oversight, fund drawdowns, planning, issue management, risk mitigation, reporting, and benefits realization?

You will need to establish a governance structure with roles and responsibilities clearly defined and with authority to make program decisions. You will need a process to monitor progress continuously, manage risks, and resolve issues.

7. Know How You Will Adjust Your Strategy as Conditions Change

Have you established a mechanism to ensure that your digital strategy continues to align with market conditions and business goals?

You will need to regularly monitor and review the external business environment and internal organizational conditions to ensure that the directives are still meaningful. It may mean adjusting your strategy to ensure it is still relevant, practical, and effective.

To summarize, you can avoid the pitfalls associated with digital transformation by understanding your business objectives, assessing the digital maturity of your organization and its ability to adapt to change, identifying and prioritizing initiatives, involving key stakeholders, establishing an effective governance structure, and continuously monitoring and adjusting your strategy to comply with changing market and organizational conditions.

What would you add to the list above?

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

Albert Einstein is reputed to have said, "If I had an hour to solve a problem and my life depended on the solution, I would spend the first 55 minutes determining the proper question to ask."

Einstein's observation points to a crucial step in problem-solving called "problem framing." This technique can reveal new and innovative possibilities and uncover stakeholders and partners that may be able to help. It is an often-neglected step to finding better solutions to complex problems while avoiding wasted time and effort going down blind alleys and wasting money on ideas and activities that don't yield the desired results.

The MIT Sloan Management Review finds,

"Sixty percent of over 700 international executives studied revealed that formulating and articulating the problem statement is one of the two significant barriers to practical problem-solving in their organizations (the other barrier is poor stakeholder engagement)."

We will get to stakeholder engagement in a future post.

The analysis demonstrated that executives often paid significantly more attention to symptoms than causes, framed their analysis on incorrect assumptions and artificial constraints, and overlooked stakeholders who were critical to avoiding or resolving the problems.

In my own experience, I have also found postmortems to frequently concentrate on the last few events that contributed to a failure or loss of business rather than embark on a deep root-cause analysis that could have identified triggers that insidiously caused a chain reaction months or years earlier.

It is, therefore, crucial to avoid these pitfalls by asking better questions and redefining how to approach problems. To start with, be clear about the goals, identify the root causes of any issues, and the obstacles to remove. By correctly and succinctly articulating the problem and ensuring the right people are involved, the path to a solution becomes more accessible.

The enormity and complexity of reengineering a business require plenty of deep thinking, which necessitates asking much better questions.

To summarize, major business transformations need to resolve complex business and technical issues, and problem-framing is a critical but frequently missed step in solving these problems.

Of course, this is in addition to being clear on the goal, removing the obstacles, making informed decisions, developing a game plan, and identifying who will take action.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

Keeping up with the fast pace of progress takes tremendous effort. Critical to this process is the transformation leader who can guide their organizations through the digital revolution and help them navigate the ever-changing digital landscape.

So how do you identify a great transformational leader?

1. Transformational Leaders Have A Clear Vision

We know that keeping up with, understanding, making strategic choices, and implementing technology that advances the organization is vital. Another commonly understood but less underscored component is the need to reexamine the institution’s purpose, core values, and how it operates, thinks, and adapts to change.

2. Transformational Leaders Inspire Their People And Build Trust

Experience tells us that organizations need great digital transformation leaders who can inspire and guide their teams with charisma and confidence while being relatable and demonstrating empathy.

These leaders build trust and ensure their teams work towards a common goal in a rapidly changing environment. They possess a clear and compelling vision for the organization's future and articulate it in a way that motivates others to join them on the journey. Communicating vision and strategy clearly and effectively to all levels of the organization is therefore vital, as is listening to the concerns and feedback of staff and addressing them in a timely and meaningful way.

3. They Are Not Afraid To Get Their Hands Dirty

These leaders take a hands-on approach to ensuring everything is running smoothly. They understand every aspect of the journey, roll their sleeves, and fully engage with their teams and the transformation process. They don’t merely reside in the executive suite but are happy to come down to the skunk works when needed - and frequently do so.

4. They Are Data-Driven And Decisive

Transformational leaders aren’t afraid to make critical decisions that will eventually determine the mission's success and the well-being of their people.

Major digital transformations that plan to deliver significant value are complex. Expect many thousands of moving parts, and in a fast-paced and constantly changing digital landscape, there are likely to be many spinning plates and plenty of balls in the air. Decisions must always be made with thought and frequently with speed and conviction. Effective communication is vital. An indecisive leader is unlikely to navigate the organization through the transformation process.

5. Transformational Leaders Take Ownership

They must take personal responsibility for the delivery of the change and ensure it meets its goals. They are responsible for any failures and yet willing to share with their teams, the glory that comes with success.

So, wish to be a truly transformational leader?

Be ready to roll up your sleeves and be charismatic and visionary, communicate effectively, be decisive, supportive, empathetic, and take ownership because that's what it takes to ensure the success of your organization in the digital age.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

With ChatGPT taking the world by storm, several clients have asked whether artificial intelligence and language models will one day fully replace human business and digital transformation consultants in an increasingly automated world.

The short answer is, "not yet"!

The longer answer is, "perhaps, to a certain extent, but only if businesses take steps to help them fully leverage AI and, over time, reduce their dependency on external consultants."

Transformation requires a profound understanding of the industry, market, and customer behaviors, wants, and needs. It requires the organization to look outward to anticipated market trends and opportunities. It also requires the organization to look inward to examine its internal capabilities, capacity, weaknesses, and any competitive advantage it possesses.

Devising a go-to-market strategy requires creative thinking to analyze and address all these elements.

Although AI can automate specific tasks and offer valuable insights into data, it is currently unable to understand and navigate complex organizational, cultural, and human dynamics. To be dependable and accurate, AI must also have access to massive amounts of data from which to learn and make predictions. This data is not always available or accessible in some industries or businesses, and access to clean, accessible, complete, and reliable data has proven to be notoriously difficult to achieve within many organizations.

Language models, such as ChatGPT, can help obtain helpful information, answer questions, and gain insights based on the data on which they have been trained. Still, they need to become more capable of providing the strategic guidance and expertise a seasoned human consultant can offer when developing comprehensive business or digital target operating models.

AI and language models like ChatGPT can free up the human consultant's time, allowing them to focus on more complex and strategic tasks by answering routine questions and giving them access to valuable data-driven insights and automated analytics.

Interestingly, automated machine learning based on hoovering massive amounts of information by data-scraping the internet and social media is leaving enterprise data management in the dust. To catch up and exploit AI to improve their reporting and data-driven decision-making, especially real-time decision-making, organizations must continue to do the hard work of capturing the reliable data they need and making it available to data analytics tools.

To further step up and use this to advance business strategies, the enterprise will have to draw insights from various data sources. It could involve aggregating operational and supply chain information and data from customer relationship management, enterprise resource planning, and service management solutions. This approach will ease the heavy lifting currently left to internal staff or consultants.

To summarize, while AI and language models like ChatGPT can only partially replace human business and digital transformation consultants, they can significantly enhance their capabilities.

As technology advances, we expect to see AI and language models playing an increasingly important role in supporting and augmenting the work of people in these areas.

To achieve great results, business leaders will need to understand the capabilities and limitations of AI and language models and how to exploit these tools to support and enhance the work of human consultants. They must also solve their internal data management problems.

If you are a strategy consultant, you can rest knowing that your job is safe. Well, for the moment, at least!

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com

Here are some business transformation challenges and ways to address them:

1.     Lack of a Shared Vision and Strategy: An organization’s mission, vision, and strategy are often reasonably well-defined. You will typically find this articulated in annual reports and financial statements. But goals and strategy are far too commonly locked in the c-suite. If one walks amongst the staff and asks how what they are currently doing contributes explicitly to the organization's goals, you're likely to be confronted with blank stares.

You must therefore come together to define, develop, and widely share a clear vision and strategy. It would help if you accompanied this with a comprehensive transformation plan that outlines the desired outcomes, milestones, and success metrics. It then becomes easier to align effort and measure progress.

2.     Resources Are Finite: Business transformation demands significant resources, including funding, personnel, and systems.

Prioritize the effort and focus on the most critical changes that drive the most significant impact and return the most value.

3.     Change Doesn’t Stand Still: The external environment is dynamic, and business transformation must keep up with market conditions, regulatory requirements, and competition. Barriers to entry are getting lower, and disruptors are eyeing the most lucrative picking in your value chain.

Continuously scan the environment and invest time and effort to study and respond to market behaviors, industry trends, and regulatory changes.

4.     Change Garners Resistance: Let’s acknowledge that change is challenging. Employees may resist new organizational structures, new processes, technology, or a top-down foisted company culture. Although this is now generally accepted, most organizations frequently need to pay more attention to the amount of planning and effort involved in affecting meaningful change.

Cultural change takes time and needs constant nurturing and maintenance. Organizations must therefore minimize resistance with effective communication and change management strategies that actively involve employees. If employees feel their opinions and needs are understood and valued, they are more likely to adapt to, and embrace, the change. Senior executives must also lead the change by living the values and embodying the desired behaviors.

5.     You Need to Know When You've Arrived. It seems odd, but many organizations find it hard to measure success – especially along the way.

Establish measures that quantify how much progress has been achieved and when goals are reached. These measures must then be used to monitor and track progress and adjusted to cater to changing circumstances.

6.     Technology Waits for No Man: The rapid pace of technological advancement means there is often the need to stay ahead of the competition. Identifying the most suitable and cost-effective solutions that will support the transformation and drive efficiencies takes time and effort.

So, research and consult with experts to determine the best technology solutions for your needs.

In summary, business transformation is complex. But with a clear vision, strategy, effective communication, change management, proper resource allocation, clear success metrics, and mechanisms for continuous improvement, organizations can overcome many of these challenges and drive success.

Additionally, aligning the transformation with the organization's culture and external environment and identifying the right technology solutions will provide the essential scaffolding.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit digitaltransformationpost.substack.com