Saturday, September 30, 2023

What does the 1st Agile Principle (Satisfying Customer with Valuable Software) look like in Action?

Many want to go Agile or claim to be Agile. The question is, are you and will you really align with the Agile values and principles?  To better understand what this means, I dissected the Principles to better discover the intentions behind them and what behaviors they entail. In this article, I expand on the first Principle and attempt to model how to marshal supporting evidence that a culture change may be occurring.  

Our highest priority is to satisfy the customer through early and continuous delivery of valuable software is the first Agile principle.  Satisfying the customer means delivering valuable software in a timely manner (that is, in the market window) for a reasonable cost. Continually striving to meet elusive customer value is important. Ultimately, the key measure of value for customers is an increase in sales and the continued loyalty of existing customers. 

How do you know that you are moving in the right direction of building value? It starts with understanding your customers: who they are and what motivates them. Their profiles include such information as their challenges, their vision for your product, and their buying trends. 

Delivering value continues with an effective sprint review process where the customer gains an opportunity to review and provide feedback on working software. If customers can sense that their input is valued during the demos, their satisfaction can increase. This is particularly true if the customers see that their feedback from the last demo has been incorporated in the working software of the current version. 

In addition, it is beneficial to use the Business Owner/Product Owner (PO) as the delegated voice of the customer to solicit acceptance criteria on what the customer would expect when they see a particular requirement or feature in action. You may also conduct periodic customer surveys to gauge their level of satisfaction with the product or solution. 

What actions exhibit “satisfying customer with valuable software”? 

  • The PO works to understand customer value, constantly prioritizes and refines the backlog, and discusses customer needs with the team. 
  • The PO creates customer profiles to recognize motivations. 
  • The backlog is your single source of requirements (aka, value). 
  • The Customer vision reflects how you wish to engage your customers. 
  • Business Strategy focuses on delighting the customer. 
  • Customers are an integral part of Reviews to provide feedback and validate value. 
  • Acceptance criteria are been captured and met for each user story. 
  • Customer satisfaction surveys are periodically conducted. 
  • Customer revenue metrics are captured and reviewed.  

It is up to you to determine what supporting evidence will highlight that a culture change is occurring. It is worth experimenting with as it will help you better understand and embrace the Agile principles. The final question, if you really believe in this principle, do you believe in continuous customer engagement, adapting requirements, and validation as a means of building valuable software to satisfy the customer? 

----------------------------------------------------------------------------------------------

Learn more about what other Agile Principles look like in action:

Thursday, August 31, 2023

Importance of Agile Readiness for a Transformation

To be a successful farmer, one must first know the nature of the soil.  —Xenophon, Oeconomicus 

Have you ever been in a daily stand-up where everyone was reporting status to the one person they thought was the leader or where most didn’t know why they were doing a stand-up every day or ever? This highlights a lack of readying the mind for what a daily stand-up is and why we are doing it.  A lack of readiness can stall or halt an Agile transformation because people aren’t in the right frame of mind for transitioning to Agile.

Readiness starts the moment when the question, “Is Agile right for me?” is asked. Readiness activities can help you better determine if Agile is right for you. Agile readiness is akin to conditioning and fertilizing the soil before growing the seeds. It is good to take a realistic look at the conditions of the fields, equipment, and people. Conditioning the mind with an understanding of Agile principles improves the ability to adopt Agile in a way that leads to truly being Agile. Strengthening the soil helps improve the physical qualities of the soil, especially in its ability to provide nutrition for plants. They can make poor soil more usable and rebuild soil that has been damaged by improper management.

This is exactly what readiness activities can do. Examine the condition of the environment where Agile is being considered. Understand and educate people on the Agile values and principles and the business benefits that can be gained. Gauge the buy-in from leaders and the willingness and capability of teams. Determine if openness or command-and-control behaviors are being exhibited (explicitly or implicitly). Understanding this context provides valuable insight into ways to adapt and move forward.  What we learn, can help shape the agile implementation according to the condition and context of an organization.

You do not need to complete all readiness activities to begin implementing, but I have learned that if you begin implementing Agile, you quickly realize that you will need to address these areas, so it is better to be proactive. With this in mind, an iterative approach may be used. Here are high-level readiness activities that you may consider. As always, feel free to adapt this list of activities if it benefits you.

  • Establish a common understanding of Agile.
  • Construct and share the drivers for an Agile organizational change.
  • Provide Agile mindset education based on Agile values and principles. Then determine subsequent educational needs.
  • Add “Customers and Employees Matter” to the company vision and share this with employees.
  • Gauge levels of executive and stakeholder buy-in.
  • Establish an overall strategy and backlog for the agile transformation.
  • Determine team willingness and capability.
  • Identify allies, champions, and subject matter experts (SMEs) and resources.
  • Identify and establish agile roles and organization.
  • Establish agile frameworks and practices that may be used. (This should not be a prescriptive model but a flexible framework, because each team is different.)
  • Establish done criteria, user story framework, and sizing techniques.
  • Craft measures of success and general metrics.

A benefit of readiness activities is that you can adapt the transformation approach based on what you learn. Another advantage is that if you find that there are challenges in an area, you can address and improve the situation. For example, you may find that there is not a clear driver for moving to Agile. This can initiate discussions on the business benefits of Agile, motivational factors behind the move, and what it takes to be Agile.

Consider Agile readiness activities as the first increment in your transformation. The outcome of Agile readiness and what you’ve learned can help you better plan the next iteration. Finally, I recommend that once you embark on these activities, you initiate periodic check-ins to gauge progress, mitigate roadblocks (such as risks and issues), and adapt along the way.

Wednesday, July 26, 2023

Are there Benefits for adding ChatGPT as a team member?

There is evidence that ChatGPT can be beneficial in helping you do your work. Involving ChatGPT today is already occurring in repetitious, creative, and diagnostic type work. Some say it’s inevitable and you should learn to work with many forms of AI. Current uses have shown that it can improve work efficiency, assist with tedious tasks, help you with creative tasks, and facilitate learning. We are also learning that because ChatGPT is based on a large language model, it can act as your assistant; providing personalized responses based on your inputs, helping you work smarter, and boosting your productivity.

As it can help an individual in their work, how about helping a team?  In this article, I explore how helpful ChatGPT can be for a team. In other words, I suggest making ChatGPT a member of your team. ChatGPT is an artificial intelligence chatbot capable of mimicking human-like conversations so why not be a member of your team? As mentioned, ChatGPT has been recognized to boost productivity so let’s consider the context of a software engineering team who are producing new features and correcting bug fixes to the code base.  To consider this, here are the potential positives, negatives, and limitations of incorporating ChatGPT as an engineering team member. Here are some considerations:

First, let’s start with some Positives:

  • Multi-tasking: ChatGPT can handle many questions, inquiries, and tasks simultaneously allowing certain work to be handled more efficiently and scaled to a higher volume of work.  
  • Quick feedback: ChatGPT provides quick feedback to questions and inquisitions allowing for more input for potential better options and decision-making.
  • Availability: ChatGPT is technically available 24/7 and can work while team members rest allowing for busy work to get completed and tasks to be ready for team review when they are back online.
  • Scalability: As an AI, ChatGPT can handle a high volume of inquiries without experiencing fatigue or requiring breaks.
  • Database of information: ChatGPT has access to a vast amount of information and can provide accurate and up-to-date answers to team members' queries.
  • Human Languages: ChatGPT can speak in multiple languages and can accommodate global teams across multiple boundaries and locations.  
  • Programming Language: ChaptGPT has the potential for programming capability across various language platforms.  

Next, let’s move to the Negatives:

  • Time from Team Members: Working ChatGPT will take time from some team members. A buddy for ChatGPT will need to be designated to help provide context for ChatGPT, line up tasks, reduce ambiguity of the requests, verify and validate the work done by ChatGPT, and more.
  • Lack of emotional intelligence: ChatGPT lacks emotional understanding and empathy, which may limit its ability to provide refined and empathetic output to team members.
  • Limited contextual understanding: ChatGPT will struggle to understand the context in which you are working including the complexity of the work, potentially leading to misunderstandings or incorrect responses.
  • Bias and completeness fn training data: the database from which ChatGPT pulls has already shown some bias based on patterns and data provided which means it may generate reasonable responses but may be incorrect or biased if not carefully reviewed.
  • Lack of creativity: Because ChatGPT pulls from existing data and patterns, this limits its ability to generate genuinely innovative or creative ideas.

Finally, several considerations should be factored in. The first is ethical considerations as ChatGPT may inadvertently generate or reinforce biased or discriminatory responses due to its training data (which includes such biases). Careful monitoring and bias mitigation strategies will be necessary. The second consideration is legal and compliance challenges.  Incorporating ChapGPT into a product team may raise legal and compliance concerns, particularly in regulated industries that require human input, oversight, and/or accountability.

It's essential to consider these factors and strike a balance when integrating ChatGPT or any AI model into a product team. Human supervision, ethical guidelines, and continuous evaluation can help mitigate the limitations and ensure optimal utilization of AI technologies like ChatGPT. Now it is time for you to wrestle with this question: Are there Benefits of adding ChatGPT as a team member? Hopefully the overview, positives, negatives, and considerations can help you with your answer. 

----------

If you are interested in learning more about ChatGPT in relation Agile, Teamwork, or experimentation, consider reading these additional articles:



Friday, June 30, 2023

How to Experiment with ChatGPT

As ChatGPT continues to make waves, is it time to learn more about it? One way to approach this is begin experimenting with ChatGPT within your context.  Learn where ChatGPT can help and where it can benefit you. In other words, what do you want to get out of ChatGPT? This allows you to test your hypothesis and the surrounding assumptions to provide knowledge and insight into whether (in this case) ChatGPT can help you or not. Here is an example.

Start with the question: Can ChatGPT help my team improve? Validate this question. Conduct preliminary research to gauge if this is relevant for your team. Start by finding out if team members are interested in using ChatGPT. This can also help you identify assumptions and if there are any other variables in play that can impact the direction of the experiment. It can also help you narrow down an area that you think ChatGPT can help.  After discussion with the team, team members believe that ChatGPT can help in retrospectives

Craft a hypothesis in a clear sentence on what you expect to find: Include ChatGPT in the retrospective can lead to better root cause analysis.  Some team members had an assumption that ChatGPT could provide root cause analysis capabilities. A hypothesis can help you validate whether ChatGPT can provide better root cause information. You can also use the “if… then” form: if we use ChatGPT during our retrospective, it will provide better root-cause analysis results, leading to more effective actions for improvement.    

Craft the experiment. Now that you have a sturdy hypothesis, it is time to craft your experiment. Describe the steps through your experiment. To do this, consider how long the experiment will run and who will be involved.  In this case, you decide to include ChatGPT in the next three retrospectives in order to get a more meaningful set of results and to have time to determine if the actions are leading to more effective results. Determine who will use ChatGPT during the retrospective and how the questions and statements will be written. Also consider the metric you will use to validate your result and what success criteria you will use to determine if the hypothesis was true (or not).  At this point, it is time to run the experiment. 

Run the experiment. An experiment should be considered as recognized effort and categorized as real work to track in your backlog.  Enact the steps listed in your experiment. Capture observations along the way and results upon the conclusion of the experiment. Get together with those who are involved in the experiment and determine what you’ve learned. Ask the question, did what we learn validate the hypothesis (or not)?  Then determine what decisions you will make as a result of this experiment. In this case, should you to continue using ChatGPT for retrospectives (or not)? Determine if there are any next steps. 

In conclusion, if you are thinking about ChatGPT, the key is to experiment. ChatGPT is a tool like other tools that may benefit you. Brainstorm where ChatGPT can help you in your context. Use the experiment to see if it does. Consider multiple experiments so that you build working knowledge of ChatGPT in your environment and working context.

---------

If you are interested in learning more about ChatGPT in relation Agile, Teamwork, or experimentation, consider reading the following articles:



Tuesday, May 30, 2023

A Discussion with ChatGPT about Agile

I had a good discussion with ChatGPT about two weeks ago. I started by asking “What is Agile?” The response was that “Agile is a methodology” with a bit more details. While technically incorrect, given the amount of information and vectors it pulled from, it wasn't completely wrong. What I mean by this is that many people, including some “Agile experts”, refer to Agile as a methodology which is incorrect. Depending on where ChatGPT is pulling this information from, this isn’t a surprise.   

  • My response: “Agile is a set of values and principles. Some Agile information is not aligned with Agile values and principles and instead rely heavily on Agile processes and methodologies or people's misinterpretation on what is agile”.  
  • ChaptGPT's response: You are correct. Agile is indeed a set of values and principles outlined in the Agile Manifesto, and it emphasizes flexibility, collaboration, iterative development, and customer satisfaction. However, misinterpretation or a focus solely on Agile processes and methodologies can lead to a deviation from these values and principles.

I was happy to see that it was aware of the Agile Values and Principles as this is how Agile is defined by the Agile Manifesto which is the seminal information defining Agile. And as I mentioned in my previous article, The Dangers of ChatGPT to Agile, there is a lack of quality evaluators on the numerous Agile articles and presentations in cyberspace that indicate if the information provided is right or wrong, good or bad.


Two weeks later (today), I asked ChatGPT the same question, “What is Agile.” This time it included the Agile Values and Principles as part of its long-winded response that included:


"Agile is an iterative and incremental approach to project management and product development that emphasizes flexibility, collaboration, and continuous improvement. It was created as a response to traditional, plan-driven project management methodologies that often struggled to adapt to changing requirements and deliver value in a timely manner.

Here are some key aspects of Agile:

    1. Values and Principles: Agile is guided by the Agile Manifesto, which outlines four core values: individuals and interactions over processes and tools, working software over comprehensive documentation, customer collaboration over contract negotiation, and responding to change over following a plan. These values prioritize human-centric approaches and adaptability.
    2. Iterative Development, 3. Cross-functional Teams, 4. Continuous Improvement, 5. Customer Collaboration, 6. Flexibility and Adaptability" (Note: I removed the details of 2 thru 6 from ChatGPT as this wasn’t relevant to this article).  


While ChatGPT will continue to develop and response to my queries, I am happy to see that it is using my (and others’) input to fine-tune its language model and improve its responses.

-------------


If you are interested in learning more about ChatGPT in relation Agile, Teamwork, or experimentation, consider reading these additional articles:

Friday, April 14, 2023

Guardian Angel or Intuition? Remembering the Boston Marathon Bombing on its 10th Anniversary

It was Marathon Monday. The Boston Marathon bombs went off at 2:49 pm on April 15, 2013. The Boston community was shocked and shattered in what was a horrific and terrible day for those who lived there. As I recall that horrible day, I realize I was standing a few yards away from the bomb near the finish line that ruined many people’s lives. About 30 minutes before that bomb went off, something told me to leave, to go home. And to this day I wonder, was it my guardian angel or my intuition? I’ve been reluctant to share this story as it was quite traumatic at the time. But now 10 years later, I’m here to share that story.

The Story

It was a chilly Patriot’s Day morning on Monday, April 15, 2013 in Lexington, MA. I started the day enjoying a Revolutionary War reenactment where the British and the Minutemen confronted each other on the Battle Green, the first troops fell, and where the “Shot heard round the world” was memorialized. I decided to bring a small folding step stool that allowed me to stand behind and a little above the crowd for a better view of the battle. I then posted photos of the event that morning on Facebook so family and friends knew I was there. After a stop at home to change clothes, I drove into the city to watch the 117th running of the Boston Marathon.

I headed into Boston toward Newbury Street thinking I would have trouble finding parking in the city but low-and-behold, I found a spot near Fairfield Street. This was exciting as I was very close to Boylston Street where the final stretch of the 26.2-mile running race occurs. While the race began around 9:30 am for elite women and 10:00 am for elite men, I arrived just in time (around 11:30 am) to see the women finish and then the men soon thereafter.

I stationed myself about 20 feet in front of Marathon Sports at 671 Boylston Street and behind the packed crowd that was already there beside the finish line and the flags. In order to get a good view of the runners and knowing that it would be difficult to get anywhere near the front row, I again brought my short step-stool that elevated me about a foot above the crowd, just enough to give me a great view of the runners and the spectators. I was doing what thousands of others were doing, cheering on the 23,000 wonderful athletes who had trained hard to compete in this historic running event. The extra elevation also allowed me to hang back behind the main thrust of the crowd, about six rows from the front. Behind me, there was an open space between me and the front of Marathon Sports where people travelled up and down the sidewalks.   

As I cheered, I took numerous photos of the runners and my surroundings. I texted some of the photos to friends and family as it was quite an exciting time. I stayed for about two and a half hours until the finish-line clock showed close to four hours and counting. I became hungry as I hadn’t eaten lunch and it was getting close to mid-afternoon. I walked to the Firehouse Sub shop (that has since closed) planning to pick up a sandwich and go directly back to my position in front of Marathon Sports and behind the flags at the finish-line.

Then something bizarre happened. As I entered the sandwich shop, I suddenly had a strong sensation that pushed me back out of the shop and insisted that I go home. “Go home” my subconscious mind was telling me. I cannot explain this then or now, but I simply left and headed home. And within the hour, I realized how fortunate I was that I did.  

By the time I got to my house, I received texts from my sister and a couple of friends asking me if I was okay. I thought they were just responding to the reenactment photos I posted of muskets firing earlier that morning and were meant to be funny. I was confused about what they were texting me, until my sister messaged me to turn on the television. 

The first image that I saw were the flags getting blown out near the finish line of the marathon. I was temporarily in shock then horrified to see what happened to the crowd behind the flags, so many innocent people that I had cheered with were hurt. I later learned that 3 had died and over 260 were wounded. Then I grew angry! Who could have done this unspeakable violence?

Abruptly, I was rocked back into reality when I realized the fact that I was in that very same crowd where the greatest amount of harm had occurred. I would have certainly been a victim and most likely, I would have been dead, lost a limb, or sustained very serious injuries because I was located at the back of the crowd no more than 10 feet from where the bomb went off. According to the reports, the bomb was a pressure cooker filled with shrapnel including nails and ball bearings that would have shredded me as it did the numerous innocent victims that were there.  

When I look back at those events, I wonder what pushed me to go home? Instead of getting food and returning back to the same location with the crowd at the finish line, I was compelled to go home. Was there a guardian angel on my shoulder or was my intuition tuned into the cosmos telling me to leave the area? Whatever it was, I’m glad I listened, and I am alive and healthy today because of it

The Prologue 

Afterward, I sent my photos to the FBI as they had a request to submit crowd photos in the areas of the bombs. Later, I got together with the Wayland community where I worship including the many religious institutions (churches, temple, and mosque), the Wayland Police, and more groups, where we mourned together, prayed together, gave blood together, and fundraised money for the victims. I couldn’t be prouder to be a part of Boston, where the police, the healthcare providers, and the collective community worked together to repair the damage of that day. Ten years later, we continue to cheer on the runners who are racing the Boston Marathon, being prouder than ever to call Boston our home, stronger than ever, Boston Strong.  




Wednesday, March 29, 2023

The Meta of getting to Small in an Agile World

If you are Agile in the Product delivery and software development space, there is strong emphasis on thinking small.  This means decomposing work to small pieces to allow for iterative and incremental delivery and eventually the continuous flow of work. While this sounds straight-forward, in practice, it is hard because it disregards the challenging mindset shift that must occur to get people to think small. 
It is important for Agile teams, coaches, and leaders need to understand for those who have never decomposed their work to “small” size chunks, they have little idea what that means and it may take time. This article focuses on several reasons why “decomposing the work to small pieces” is challenging and the meta surrounding the concept of small.

Small is mindset shift  

Imagine that you have never considered what is small and someone says, “think small!”  This is meaningless without any context or experience in “getting to small”.  To achieve the concept of understanding small bite-sized pieces or work, there is mindset change that must occur.  Imagine if you were piloting a plane for the first time and your instructor says, you must go “fast” to take off.  What does fast enough mean if you’ve not done this before? If you only ride a bicycle, then fast may mean 25 mph (or 40 kph). However, in order to take-off, fast means 75 mph (or 120 kph) for a propeller plane and 170 mph (or 275 kph) for a jet.  There must be a strategic steps to shift the mindset to think differently that includes allowing the team time to learn and experience their way to small. 

Small is Relative 

What is “small” will be different depending on the type of work a team is doing. There is back-end, middleware, front-end work and more. Each team must gauge what is small based on their work. Also, what is small will differ from team to team and is relative to team size, talent, and experience. What is small must be specific to each team. Management must not compare sizes across teams as this will deteriorate the relative sizing for the specific teams.
  
Small is Complex 

Creative work like building new products and services (or features therein) are considered complex (per the Cynefin framework) as there are unknowns and “unknown unknowns”, ergo requiring a "probe–sense–respond" approach.  Many will translate small to days of work. But translating small to time of work disregards the complexity and unknowns of the work. In an Agile world, we consider not just effort, we look at complexity of the work (e.g., what is known and unknown), and any risks involved in the work (e.g., what skills, experience, tools, infrastructure a team has and more specifically what they don’t have.  What this means is that to identify small work, you must look at effort, complexity, and risk so it isn’t straight-forward.

Small is Imprecise 

In an Agile world, we don't pretend to think that we can have precision in our sizes. We want good sizes but we have to move away from the traditional mindset where we think we can provide accurate estimates. If it isn't correct, this is actually okay as we’ll soon learn more about the work.  When you size the work within an iteration (aka, sprint) and the iteration is done, you will quickly build a historical database of sizing and will learn more about the work.  The very next iteration, you will have learned whether you were over or under for a size and when similar type work comes along you have input for the future sizing of work.  In other words, “don’t sweat the sizing”. 

Summary

When transforming to Agile, there is a shift to to small pieces of work allowing for iterative and incremental delivery of the work. Small is challenging for teams that have not had to work decompose to small. Understanding the meta around getting to small can help coaches, teams, and leaders navigate the challenges knowing that it is a mindset shift, it is imprecise, it is relative to the work and each team, and is complex.  



Tuesday, February 28, 2023

Are there Dangers with ChatGPT for Agile?

How will ChatGPT impact Agile? This article discusses ChatGPT and its implications to Agile in the industry today. ChatGPT is taking the internet by storm and hard to ignore. Because of this, it cannot be ignored by those in the Agile field. What are the implications of ChatGPT on Agile? Here is a brief summary of what is ChatGPT and a review of what is Agile and its current journey.

What is ChatGPT?

ChatGPT is an artificial intelligence (AI) chatbot-type tool developed by OpenAI. It is adept at producing human text-based output on the input it is given. This model incorporates a large body of text data and can create responses to questions, write articles, and more. The challenges with ChatGPT are that it is only as good as the “large body of text data”, can be used maliciously and with bias, can spread misinformation, and is ethically complex in its application and future application. This applies to any field that people may use it for including Agile.   

What is Agile?

Once upon a time (in 2001) Agile was unveiled based on the Manifesto of Agile Software Development which is comprised of Agile Values and Principles. The objective of articulating the values and principles is to apply them in the form of an Agile transformation to derive better business results. However, the manifesto does not provide guidance on how to apply Agile. 

Soon, a number of processes and methods (e.g., XP, Scrum, Kanban, SAFe, etc.) were established to construct and apply agile ways of working. Agile has also spawn a number of certification programs in an attempt to educate people in Agile ways of working, in some cases aligned with a process or method. During this same time, Agile coaches were educated to help their own companies and Agile consultancies to help other companies apply Agile ways of working. The Agile movement has grown and expanded in a number of fields beyond software development.  After over 20 years, what are the results? The challenges are three-fold.  

  • First, the current state of Agile is underwhelming. The most recent State of Agile Report (16th Annual – 2023), tells us the following. Only 18 percent of organizations implemented Agile for all the teams. Around 50 percent of respondents report that less than half of their teams are using agile, and 84 percent acknowledge that their organizations are below a high level of competencies. There is clearly plenty of opportunity for growth.
  • Second, some of the Agile savvy (e.g., coaches, consultants, leaders, managers) seemed to lack an understanding of what is agile. In an Agile study where 109 agile professionals answered a survey on Scrum events and Agile principles, 59% could name 3 or more of the five Scrum events, while only 11% knew 3 or more of the twelve Agile principles. This is quite astounding. And they didn’t need the full statement of the principle but got credit for even the key words of the principle. The concluding hypothesis is that the reason there is such a lack of awareness of Agile principles is that there is much less focused on the mindset and culture and maybe too much focus on the mechanics.
  • Third, the implementation of an Agile transformation is complex per the definition provided by the Cynefin framework. Agile transformations are neither linear nor predictive. It depends on the readiness of the culture and willingness of its leaders in their ability to move forward. Complexity means that it is not clear on what the best next step is until you act, ergo you need to probe, sense, response your way forward. This is why experimentation helps reveal what is possible each step of the way. You must both meet the company and teams where they are and help them determine what is the next step to further the transformation.  

What this tells us is that there are great opportunities for improvement and that there is no easy way to apply Agile, no one-size fits all, and no clear roadmap. Why? Because every organization is different due to their current culture, size, fields, practices, and more. 

Implication of ChatGPT and Agile

Now that we have an overview of both topics, the question is what are the implications of ChatGPT to Agile (and vica-versa)?  I’ll start by saying “What you put in is what you get out”. ChatGPT is only as good as the “large body of text data” available to pull from. The good news is that today there are reams of text data on Agile. The bad news is that there is no rating system on the quality of most of the Agile related information. With the advent of blog’s, there is a large body of unverified knowledge that enters into the “large body” of available data. What are the implications of this? 

  • Arguable Quality of response - The quality of ChatGPT generated articles and answers should be read with a grain of salt. This isn’t a “knock” on ChatGPT, and instead it is due to the quality of the body of text data that ChatGPT draws from. And the reality is there is no one right way of applying Agile.  
  • Propensity for Misinformation - There is a danger of misinformation and abuse of those who use ChatGPT to bias their responses. Some may be accidental as the body of text being pulled in isn’t broadly approved or agreed upon. While I don’t expect that most will be intentionally abusive, do keep in mind, there is money to be made in selling agile so bias may be seen.  
  • Not doing your own Research - While you may want to occasionally use ChatGPT, it is better to learn from the body of Agile knowledge out there (e.g., books, articles, presentations, seminars, etc.) according to the areas that will benefit your current needs in your Agile transformation or need. In other words, do your own research so you can critically judge the quality of information that gets generated.
  • Taking Agile Jobs - Can ChatGPT take jobs away from Agile Coaches and Consultants? This is unlikely as a significant part of an Agile transformation include coaches and consultants who have been on a transformation journey that can help companies navigate the complexity of both the current needs and the anticipation of near-term needs. ChatGPT cannot “read the room” like an Agile Coach. Should a company think that ChatGPT will be “enough”, it highlights that they don’t understand the complexities of a transformation and what it takes to change culture.

Summation

Now that you have some background, let us again turn to the question, “how will ChatGPT impact Agile?” There will be those that use ChatGPT to provide answers for Agile theory and questions. If you want to write an Agile article, it will help provide input and insight, although you have to be aware that the value of the information is only as good as what it pulls from. Think of ChatGPT as another resource to help you think through your ideas on agile topics and how it may help you in your Agile transformation. However, just remember, it is just a tool like other tools.     

It is unlikely that ChatGPT will take over Agile roles and the art of the transformation. A big part of Agile transformation is discovering, observing, and experimenting on what will work and what will make progress. Remember, when defining Agile, it really implies a transformation. This is a combination of doing agile and more importantly being agile. This means transforming mindset and culture. It is currently unlikely that ChatGPT will have this capability as transformations are complex with the real need to experiment (e.g., probe, sense, response) toward progress.  Coaches and consultants are still important to help transform organizations and more importantly to help leaders and teams make the mindset-shift to truly becoming Agile. 

-------

If you are interested in learning more about ChatGPT in relation Agile, Teamwork, or experimentation, consider reading these additional articles:

Monday, January 30, 2023

Breaking Bad Story Point Anti-Patterns

There is occasional controversy in the Agile coaching community on whether to apply Story Points on user stories. This often stems from the challenge where some think that story points are a direct replacement for estimation and an expectation of precision while others suggest that instead of story point sizing, we should focus on focusing on small pieces of work. In other words, when applying a practice (e.g., story points), a bad pattern is implemented which is opposed to the way practice is meant to be applied. This is known as an anti-pattern. Anti-patterns lead to results that are counterproductive to the intent of the practice and reduce their effectiveness. In other words, not good. 


What is Story Point Sizing? 

Before we go further, let’s take a moment to define what is a story point? A story point is a unit of measure describing the size, complexity, and risk to gauge the amount of work needed to complete a particular user story. 

Story points are also a relative measure to a specific team. Every team creates their own story point sizing framework based on the type of work they do, the skills and experience of the team, and what they personally perceive to be a small, medium, or large amount of work. The team collaboratively determines the story points for each story based on its perceived size, complexity, and risk. 

Story points are often correlated with small, medium, and large sized work. Some use the Fibonacci as it provides a numeric distribution that can be used to differentiate between sizes of work typically using 1, 2, 3, 5, 8, 13, 21. When using Fibonacci numbers, 1, 2, and 3 are aligned with small work, 5 and 8 are medium sized work, and 13 and 21 denote large pieces of work. 

Velocity is a metric that can help a team understand their sustainable pace by identifying the amount of story points of work a team can complete in an iteration. In each case (e.g., story points and velocity), this is why you should not compare the story point velocity across different teams. Story points and velocity are very specifically a team measure and should not be tampered with by those outside of the team. 

Anti-patterns of applying Story Points 

The reason there is concern surrounding applying story points is the ways it gets applied. As mentioned, story points are a combination of size, complexity, and risk of that specific piece of work (aka., user story). This means they are not meant to be used as a predictor or for accuracy. Here are several anti-patterns of story points in the way they get applied: 
  • Unfit Translation anti-pattern - Some apply story point sizing as if it is nothing more than an estimate of hours and days (and weeks and months). There is often a direct translation of small, medium, and large to days. 
  • Pretend Certainty anti-pattern - There is often ascribed a sense of certainty when applying story point sizing where it gets used to predict when work will get done. At best, it can help with understanding progress, but you would never estimate “all” of the work up front anyway as priorities (and requirements) tend to shift so it would be a waste to do so. 
  • Pretend Precision anti-pattern – There is precision when using story points which isn’t appropriate. The numbers that story points represent are meant to be ball-park numbers as it is an amalgamation of size, complexity, and risk. 
  • Contrived Comparison anti-pattern – Some organizations attempt to compare story points and velocity across teams even though they are relative to the team’s composition and the type of work they focus on. This is inappropriate and decreases the integrity of story points and velocity. 
  • Effort Tampering anti-pattern – This occurs when someone outside of the team (usually management) attempts to influence the amount a work a team does by insisting on improvement. This impacts the integrity of the story point sizing framework and the velocity data as those are meant specifically for that team to have meaning. 
  • Inflation anti-pattern – This can be the result of when someone outside of the team applies the Effort Tampering anti-pattern by attempts to make the team “work harder”. The result may be that the team inflates their numbers to ‘satisfy’ the influencer and effectively impact the integrity of the story point sizing framework. 
  • Productivity anti-pattern – This is when story points and velocity get conflated as a productivity measure by those outside of the team. They are not productivity measures and will warp the intent of both story points and velocity. 

Mending Anti-Patterns  

The best way to eliminate or reduce anti-patterns, is to first understand what anti-patterns look like (see Anti-Pattern section above and search of other information on anti-patterns). Then do detective work to uncover what anti-patterns may exist. Follow this with determining an action to remove or eliminate them. You can do this through a theme-based retrospective where the focus is on identifying anti-patterns. 

Anti-patterns within an organization are more commonplace than you think. They are often due to a lack of clarity of what are story points, how they should be applied, and a lack of awareness that they are specifically a team-based measure. There may also be management or team member influence to use the practice or technique incorrectly. If too many of these anti-patterns exist, then the value of using story points as a team measure and as an instructive tool to help team gauge what is considered small diminishes.