Self-Leadership: Get Shit Done Without Losing Yourself. CHUMS, The CHU Management System.

, , , , , , ,

Summary / Net

Most senior executives do not have a productivity problem. They have an overload, attention, energy, relationship, and prioritization problem. The CHU Management System — CHUMS — is my personal operating system for getting shit done without letting the loudest, most urgent, or most emotionally reactive issue take over my life.

CHUMS is not a software platform, productivity app, or universal template. It is a weekly paper-and-Google-Sheet discipline I use to manage work, family, relationships, health, values, commitments, follow-up, and focus. The specific system is mine. The larger point is universal: every serious leader needs a system.

Why I Built CHUMS

I originally developed what became the CHU Management System during the seven years I founded and led The Loyalty Group, that created, launched and grew the AIR MILES Canada shopping reward program and database/ internet marketing business. Like many entrepreneurs and CEOs, I had too many priorities, too many people depending on me, too many ideas, too many meetings, too many relationships to maintain, and too many chances for something important to fall through the cracks.

Later, in 2016, I began using the system again while working at Year Up, where my work involved roughly 60 internal colleagues, more than 100 external partners, and 12 locations. That was the kind of operating environment where “I’ll remember that” is not a system. It is a fantasy.  It also served me well when I used it in 2020 as Vice Chair of Alan Khazei’s congressional campaign in Massachusetts 4th District.  I have described well-funded competitive political campaigns are like an “internet start-up on speed.”  Personal management systems are a life saver in these environments.

CHUMS is heavily influenced by Stephen Covey’s The 7 Habits of Highly Effective People, David Allen’s Getting Things Done, Jim Loehr and Tony Schwartz’s The Power of Full Engagement, James Clear’s Atomic Habits, conversations with friends and colleagues, and a lot of agile trial and error. It is also influenced by a simple, humbling reality I have learned repeatedly in my life: when I use my system, things get done. When I don’t, things fall off my plate, and I drift into a growing pile of “urgent and important” crises.

The “triple-infinity” symbol represents the need for leaders to keep the most important things, actions, tasks, and priorities among your business, your family, and yourself in balance.  This was something emphasized for me personally during the many years I was a member of The Young Presidents Organization, while CEO of The Loyalty Group in Toronto.

The name is slightly tongue-in-cheek: CHUMS stands for CHU Management System. But the point is serious. CHUMS is a personal operating system for self-leadership.

And for senior executives, self-leadership is not optional. If you cannot manage your own attention, energy, values, relationships, commitments, and follow-up, you will eventually transfer your internal disorganization to the organization you lead.

The Big Idea: Senior Executives Need a Personal Operating System

Most executives already have organizational systems. They have strategic plans, dashboards, CRM systems, board packets, financial models, Slack channels, calendars, and performance reviews. But many do not have an equally disciplined personal system for deciding what deserves attention this week, what must happen today, who needs care and connection, what values must be lived, and what can safely wait.

That gap is dangerous.

Without a personal operating system, leaders become reactive. They chase whatever is loudest. They answer the latest email. They respond to the most anxious stakeholder. They spend too much time in Covey’s “urgent and important” quadrant and not enough time on the important-but-not-yet-urgent work that actually builds a life, a team, a strategy, and an institution.

CHUMS is my attempt to solve that problem for myself.

It has 11 parts:

  1. Daily and weekly self-monitoring
  2. Personal must-dos
  3. Weekly to-do list
  4. Strategic priorities and relationships
  5. Calendar blocking
  6. Must do today before I sleep
  7. Rolling discussion lists, house list, and someday/maybe
  8. Live your values
  9. Feedback is a gift
  10. Weekly must-do / three priorities per day
  11. The 86,400 reminder

Here is how each part works.

1. Daily and Weekly Self-Monitoring

What is it?

The first section of CHUMS is a simple weekly tracker. It includes the people and practices I want to stay connected to each week.

For me, the initials and abbreviations on the left-hand side are personal:

J = Jordan, my oldest child.
M = Myles, my youngest child.
LEZ = my wife, Laura.
X = exercise.
S/G = spiritual practice and gratitude.
SSU = my sister Sharon.
CUF = my sister Cecilia.

This section is influenced by Stephen Covey’s “Sharpen the Saw” habit — the idea that we must renew ourselves across the physical, mental, emotional/social, and spiritual dimensions if we want to remain effective.

How do I use it in practice?

Each week, I track whether I have engaged with these people or practices. Did I connect with my kids? Did I connect meaningfully with Laura? Did I exercise? Did I do anything spiritual or gratitude-oriented? Did I check in with my sisters?

This is not meant to be a guilt machine. It is a visibility tool.

A senior executive can easily spend the week serving clients, employees, donors, investors, board members, political allies, or external stakeholders — and then realize that the people and practices that matter most personally received the least intentional attention.

This section makes that visible.

Why include it?

Because what gets tracked gets attention.

Executives are usually very good at tracking business metrics. Revenue. Margin. Retention. Pipeline. Fundraising. Cash runway. Employee engagement. Customer satisfaction. But we often fail to track the personal relationships and renewal practices that keep us grounded and human.

This section reminds me that productivity is not just doing more work. It is living the right life while doing the work.

If I say my family matters, my system should reflect that. If I say health matters, my system should reflect that. If I say spirituality, gratitude, or reflection matters, my system should reflect that.

Otherwise, my stated values and my calendar can be in conflict.

2. Personal Must-Dos

What is it?

This is the short list of the most important personal things I must get done this week.

Not someday. Not eventually. This week.

These are not necessarily the biggest strategic projects. They are the personal commitments that matter enough to deserve explicit weekly attention.

How do I use it in practice?

When I update CHUMS on Sunday night, I ask: what personal things must happen this week for me to feel I have honored my commitments to myself and the people closest to me?

That might include a family follow-up, a personal finance task, a health appointment, a home issue, a difficult conversation, a commitment to Laura, a call with one of my kids, or something I have been avoiding.

The key is that it gets written down in a place I will see all week.

Why include it?

Because personal obligations do not become less important because they are not professional.

Many senior leaders unconsciously privilege work commitments over personal commitments because work commitments come with meetings, deadlines, assistants, board pressure, customers, and money attached. Personal commitments are often quieter. They do not always send calendar invites.

But neglected personal commitments create stress, guilt, friction, and emotional drag. They also erode integrity. If I repeatedly fail to do what I told myself or my family I would do, I become less trustworthy to myself.

This section protects my personal credibility.

3. Weekly To-Do List

What is it?

This is the classic weekly capture list, heavily influenced by David Allen’s Getting Things Done. Allen’s GTD method emphasizes capturing what has your attention, clarifying what it means, organizing it where it belongs, reviewing it regularly, and then engaging with the right work.  Allen advises against keeping a long daily to-do list, as spending time on most nights moving things that did not get done that day to the next can become energy sapping.

In CHUMS, this becomes a weekly written list of work and personal to-dos.

How do I use it in practice?

The list is organized along the right-hand side of the matrix roughly by my most important clients, projects, and people.  CHUDOW – stands for CHU (to) Do Other Work related and CHUDOP – for CHU (to)Do Other Personal.  IC/ AI is a bucket to make sure I build intellectual capital every week and AI to remind me to keep up with the latest developments in artificial intelligence.

The point is to avoid what I call the “four-year-old soccer problem”: every kid chases the same ball.

Organizations do this. Leaders do this. I do this. The urgent issue gets the ball, and suddenly every person, meeting, and ounce of energy is chasing it while other important areas are neglected.

During the week, whenever something comes up, I write it down. I do not rely on memory. I do not assume I will magically remember it after the meeting, after the bike ride, after walking Izzy, or after the next call.

On Sunday night, I update the system in Google Sheets, print it, and carry it with me. Yes, I am trying to eliminate paper from much of my life. But for this, paper still works. I can fold it in half and keep it in my jacket pocket.  A few more folds and it fits in my jeans or cycling jersey pocket.  If something occurs to me while walking the dog, riding my bike, sitting in a meeting, or thinking through a client issue, I can write it down quickly and get it out of my head.

Why include it?

Because the brain is a terrible office.

It is wonderful for creativity, empathy, pattern recognition, judgment, and strategy. It is not wonderful as a storage facility for 73 unrelated commitments.

David Allen’s core insight is that unprocessed commitments create mental residue. The more open loops we carry in our heads, the less fully present we are for the task or person in front of us.

For senior executives, this matters enormously. Your attention is one of the most valuable assets in the organization. If your mind is cluttered with unrecorded obligations, you are spending executive attention on memory management instead of judgment.

Writing things down is not clerical. It is strategic.

4. Most Important Strategic Relationships and Priorities

What is it?

The last two columns force me to list 1-3 relationships in appropriate areas of focus that I must invest in during the week and to whittle down the many to-do items under each to the 1-3 that simply must get done by the end of the week.

How do I use it in practice?

I use the categories to force a broader scan.  The most important relationships and priorities in each category ensure that I narrow down and prioritize those actions and people that are most important for the period.

What needs attention in each major area? What am I ignoring? Which relationships need follow-up? Which strategic priority is quietly drifting? Which area has become too dominant? Which important work is not urgent enough to scream yet?

This section turns my week from a random pile of tasks into a portfolio.

Why include it?

Because executive work is portfolio work.

A CEO or senior leader is rarely responsible for one thing. You are responsible for strategy, people, capital, culture, customers, operations, governance, risk, external relationships, and often your own health and family system at the same time.

If you only manage the loudest category, you will underperform in the quieter ones.

This section creates balance. It forces me to ask: am I paying attention to the whole field, or am I chasing the ball?

5. Calendar Blocking

What is it?

I use this section to block out my calendar, identify major client and board meetings, presentations, and color-code travel dates. It gives me a high-level overview of the most important personal and business events that will require major prep work or personal planning over the next two months.

How do I use it in practice?

At the beginning of the week, I look at the major events and commitments coming up over the next 8 weeks and make sure the requisite pre-work is somewhere on the list above or elsewhere recorded in the system.

Why include it?

This section helps me connect intention to time. It also helps me see overcommitment before it becomes failure. If I have 30 hours of meetings and 50 hours of work I claim must get done, the math is not going to work. Pretending otherwise does not make me ambitious. It makes me irresponsible.

Calendar visibility is a form of honesty.

6. Must Do Today Before I Sleep

What is it?

This is the daily hard-stop section: what must I do today before I go to sleep?  With all due respect to David Allen, this is my daily to do list.  I use an erasable pen to fill it in each morning before starting my day and clear it by the end.

This includes any true Covey Quadrant I items — things that are both urgent and important. But it is not limited to crisis work. It can also include one or two actions that simply cannot be allowed to slip another day.

How do I use it in practice?

Each day, I identify the small number of things that must happen before I sleep. Not 20 things. Not everything. The real must-dos.

This is the section that confronts the day directly.

At the end of a long day, when I am tired, distracted, or tempted to postpone something uncomfortable, this section asks: what did I promise myself would get done today?

Why include it?

Because weeks are won or lost in days.

A beautiful weekly plan can still fail if there is no daily commitment mechanism. This section turns the system into action.

It also helps distinguish between “I was busy” and “I did what mattered.” Senior executives can be busy every minute of the day and still avoid the one conversation, decision, note, workout, apology, or follow-up that actually mattered most.

The phrase “before I sleep” creates useful pressure. It makes the commitment concrete.

7. Rolling Discussion Lists, House Perfect List, and Someday/Maybe

What is it?

The right side of the front page is a set of rolling lists.

I use it to track topics I need to discuss with team members, client contacts, consultants, family members, friends, and collaborators. Instead of immediately calling or texting every time a thought occurs to me, I write it down under the relevant person or project.

This section also includes ideas for articles, my “House Perfect List” — smaller or larger things I need to do around the house or yard — and a “Someday/Maybe” list, borrowed directly from David Allen’s Getting Things Done framework.

How do I use it in practice?

When I think of something I need to discuss with someone, I put it in that person’s box. Then, when we meet or talk, I have a ready-made agenda.

This improves the quality of meetings and reduces the number of interruptive one-off communications. Instead of spraying texts, emails, and half-formed thoughts throughout the week, I batch topics for the right moment.

For the Collaboration Evangelist articles, House Perfect List and Someday/Maybe list, the same principle applies: capture without overcommitting. Not everything belongs on this week’s must-do list. Some things simply need a trusted parking place.

Why include it?

Because not every thought deserves immediate action.

This is especially important for senior leaders. Executives generate a lot of ideas, questions, concerns, and follow-ups. If every thought becomes an immediate interruption for someone else, the leader becomes a chaos machine.

A rolling discussion list creates discipline. It respects other people’s attention. It makes meetings better. It lets me remember without reacting.

The Someday/Maybe list is equally important because it gives ideas a place to live without letting them hijack the week. That is a critical distinction. A good idea is not always a current priority.

8. Live Your Values

What is it?

The left side of the back page is my values reminder. It lists the personal values and commitments I am trying to live.

The emphasis is on trying.

This section is not a declaration that I am fully living these values every day. It is a reminder of who I want to be and how I want to show up.

For me, this includes being the best father I can be, being a good brother, honoring my parents by how I live and work, being respectfully and graciously honest, taking care of myself physically, emotionally, intellectually, and spiritually, using my experience and resources to help others, fighting for justice, being conscious of the impact of my words and actions, not judging others, being the best partner to Laura and best human to Izzy I can be, and passionately promoting what I believe in.

How do I use it in practice?

I keep it on the back page so I see it repeatedly. It is not a framed statement on a wall. It is part of the weekly system.

That matters. Values should not be separated from execution. They should shape execution.

When I review my week, I am not only asking, “What do I need to get done?” I am also asking, “Who am I trying to become while I get it done?”

Why include it?

Because productivity without values can become efficient selfishness.

Many senior executives are extremely productive by conventional measures. They clear inboxes, make decisions, hit numbers, raise capital, close deals, and move fast. But speed and volume are not the same as leadership.

This section forces me to connect action to identity. James Clear’s Atomic Habits argues that lasting behavior change is connected to identity — not merely what goal we want to achieve, but what kind of person we believe we are becoming.

For me, CHUMS is not just a task system. It is an identity system. It reminds me that the goal is not simply to get more shit done. The goal is to get the right shit done in a way that is consistent with the person I am trying to be.

9. Feedback Is a Gift

What is it?

This section captures some of the most important feedback I have received from supervisors, mentors, colleagues, friends, and role models.

It includes short reminders — phrases that mean something specific to me. Some are blunt. Some are cryptic to anyone else. Some are deeply personal. The point is not that the phrases would work for everyone. The point is that they work for me.

How do I use it in practice?

I keep the feedback visible so I cannot conveniently forget it.

Most of us say feedback is a gift. But in practice, we often treat feedback like a gift we would like to return, exchange, reinterpret, or bury in a drawer!

This section makes feedback operational. It turns lessons learned into recurring prompts.

Why include it?

Because leaders repeat avoidable mistakes when feedback is not converted into practice.

Senior executives often receive a lot of feedback, but not always honest feedback. The more senior you become, the more people manage you, flatter you, fear you, or soften the message. So, when you do receive real feedback, you should treat it as valuable data.

But insight fades. A hard lesson learned in March can be forgotten by June. This section keeps the lesson alive.

It also reinforces humility. No matter how experienced I am, I still have things to work on. The system reminds me of that every week.

10. Weekly Must-Do / Three Priorities Per Day

What is it?

The top right side of the back page can be used to list three priorities per day for the week. I have also used it as a blank note-taking space or as a place to list annual goals.

The three-priorities structure is intentionally simple.

How do I use it in practice?

For each day, I write the three things that would make the day successful.

Not 12. Not 27. Three.

This creates focus without pretending the day is clean, predictable, or fully controllable. It gives me a simple way to answer: if everything goes sideways, what are the few things that still matter?

Why include it?

Because constraints create clarity.

Executives are vulnerable to over-listing. We confuse ambition with volume. We put too much on the list and then feel behind before the day starts.

Three priorities force choice. Choice is the essence of strategy.

This section also creates a bridge between weekly planning and daily execution. The weekly system sets the field. The daily priorities define the play.

11. The 86,400 Reminder

What is it?

The final section is a visual reminder: 86,400; Be The Buffalo: Make The Next Best Choice; Proverbs 3:27.

There are 86,400 seconds in a day. Something I learned from my Pastor and Spiritual Entrepreneur friend Ray Hammond. For me, this symbol is a reminder to make the most of each day, confront challenges directly, not dwell endlessly on mistakes, and help others when I am able.

How do I use it in practice?

I do not use this as a productivity hack. I use it as a perspective hack.

Some days go well. Some do not. Some include progress. Some include mistakes. Some include conflict, disappointment, fatigue, or frustration.

The 86,400 reminder helps me reset. It says: this day is finite. Use it. Do not waste it in avoidance, resentment, self-pity, distraction, or fear.

Why include it?

Because time is the only non-renewable leadership resource.

Money can sometimes be raised. Staff can sometimes be hired. Strategy can sometimes be revised. Reputation can sometimes be rebuilt. But the day is spent once.

This does not mean every second should be optimized. That would be exhausting and inhuman. It means the day should be honored.

For a senior executive, the question is not merely “How do I get more done?” The deeper question is: “How do I make choices worthy of the time I have?”

Why the Whole System Works

CHUMS works for me because it integrates five things that are often separated:

  1. Tasks
  2. Time
  3. Energy
  4. Relationships
  5. Values

Most productivity systems over-focus on tasks. They help you capture, sort, and complete work. That is useful, but incomplete.

Senior executive effectiveness is not just task completion. It is sustained judgment, emotional regulation, strategic focus, relationship management, physical and mental energy, and values-based action under pressure.

That is why The Power of Full Engagement is such an important influence on CHUMS. Loehr and Schwartz argue that managing energy, not just time, is central to high performance. A leader with a perfectly organized calendar but depleted physical, emotional, mental, or spiritual energy is not operating at full strength.

CHUMS also works because it is reviewed weekly. A system that is not reviewed becomes clutter. A system that is reviewed becomes trusted.

My Sunday night practice matters. I update the Google Sheet, print the system, and carry it with me. That ritual turns CHUMS from a document into a discipline.

James Clear’s Atomic Habits emphasizes the power of small, repeatable systems. The point is not heroic motivation. The point is designing a structure that makes the desired behavior more likely. CHUMS does that for me. It makes remembering, reviewing, prioritizing, connecting, and acting easier.

It also creates accountability. Even when no one else sees the sheet, I see it. I know what I wrote down. I know what I said mattered. I know what I avoided.

That is powerful.

What Happens When I Do Not Use It

When I do not use CHUMS, my productivity does not collapse all at once. It degrades gradually.

First, I start relying on memory. Then I miss small things. Then I become more reactive. Then important-but-not-urgent work slips. Then relationships become less intentional. Then my day gets captured by other people’s priorities. Then I feel behind. Then I start chasing the crisis of the day. Or, at worst, fall into a state of depression or anxiety paralysis.

Eventually, I end up with exactly what Covey warned about: too much time in the urgent and important quadrant because I failed to invest enough time in preparation, prevention, relationships, renewal, and planning.

When I do not use CHUMS, I also become more likely to confuse motion with progress. I answer emails, create PowerPoint slides, attend meetings, respond to texts, and knock off visible tasks, but I may not be moving the most important priorities forward.

Worst of all, I become more likely to drift away from my values. Not because I stop believing in them, but because I stop seeing them.

That is how it happens for many leaders. They do not abandon their values dramatically. They simply get busy. Then they get reactive. Then they get tired. Then they rationalize. Then the urgent crowds out the important. Then, slowly, the life they are living stops matching the life they say they believe in.

CHUMS is my defense against that drift.

The System Is Mine. The Need Is Universal.

I do not recommend that everyone copy my exact system.

In fact, you should not. CHUMS is highly tailored to my priorities, family, relationships, passions, work, quirks, and flaws. Your system should be tailored to yours.

But I strongly believe every senior executive needs some kind of personal operating system.

It does not have to be paper. It does not have to be a spreadsheet. It does not have to have 11 parts. It does not have to use my language. It does not have to be called anything clever.

But it should help you answer these questions every week:

What matters most?
Who needs my attention?
What must get done?
What can wait?
What am I avoiding?
Where is my energy going?
Am I living my values?
What feedback am I trying to practice?
What must I do today before I sleep?

If your system cannot answer those questions, it is not yet a leadership system. It is just a task list.

A Note for CEOs and Senior Leaders

The higher you rise, the less anyone else can fully manage your attention for you.

An assistant can manage your calendar. A chief of staff can manage your meeting flow. A COO can manage execution rhythms. A board can help set accountability. A coach can ask hard questions.

But no one else can decide, week after week, what kind of leader you are trying to be.

That is your work.

CHUMS is one way I do that work.

It helps me get shit done. But more importantly, it helps me get the right shit done, with the right people in mind, for the right reasons, while trying — imperfectly but seriously — to live the values I claim to hold.

For me, that is the real productivity challenge.

Not just doing more.

Doing what matters.

Building Your Own GSD System

In my CEO coaching and productivity accountability partner (PAP) practice, this is one of the places where I believe I can be most helpful.

Not by handing leaders my system and pretending it will fit their lives.

But by helping them build their own.

A strong executive productivity system should be personal, practical, visible, reviewable, and honest. It should include the work, but not only the work. It should include relationships, energy, renewal, values, feedback, and follow-through. It should be simple enough to use when life gets busy, because that is exactly when the system matters most.

The goal is not to become a productivity robot.

The goal is to become a more intentional leader.

A leader who knows what matters.
A leader who writes it down.
A leader who follows up.
A leader who protects time and energy.
A leader who lives values in practice, not just in speeches.
A leader who gets shit done without losing himself or herself in the process.

That is what CHUMS does for me.

And that is why I still use it.  To paraphrase my son Myles, when I don’t use it, “Shit goes left.”

Here’s a link to the front page google spreadsheet you can edit to start building your own system.

Endnotes

  1. Stephen R. Covey, The 7 Habits of Highly Effective People. CHUMS is especially influenced by Habit 7, “Sharpen the Saw,” and Covey’s distinction between urgent/important work and important-but-not-yet-urgent work.
  2. David Allen, Getting Things Done: The Art of Stress-Free Productivity. CHUMS draws heavily on GTD’s core practices of capturing commitments, clarifying next actions, organizing reminders, reviewing regularly, and maintaining a “Someday/Maybe” list.
  3. Jim Loehr and Tony Schwartz, The Power of Full Engagement: Managing Energy, Not Time, Is the Key to High Performance and Personal Renewal. CHUMS reflects the book’s core argument that sustainable high performance requires managing energy across physical, emotional, mental, and spiritual dimensions.
  4. James Clear, Atomic Habits. CHUMS reflects Clear’s emphasis on systems, small repeatable practices, identity-based behavior change, and designing structures that make desired behaviors more likely.
  5. Gail Matthews, Dominican University of California, research on goal achievement and accountability. The CHUMS presentation cites Matthews’ findings that written goals and weekly accountability increased the percentage of participants who accomplished at least half of their goals.
  6. Craig Underwood, CHU Management System aka CHUMS — Overview, updated June 12, 2026. The structure, 11-part framework, personal examples, and CHUMS descriptions are based on the author’s original presentation.

APPENDIX I – FULL FRONT PAGE (BEFORE FOLDING)

APPENDIX II – FULL BACK PAGE (BEFORE FOLDING)

Want to Get Started with AI? Learn How to Ask Better Questions. Three free or publicly accessible ways for students, educators, nonprofit leaders, and executives to learn the basics of AI prompt engineering.

, , , , , , , ,

One of the most common questions I hear from nonprofit leaders, educators, students, and executives is deceptively simple:

How do I get started with AI?

My answer: start with prompt engineering.

That phrase may sound technical, but the basic idea is very practical. Prompt engineering is simply the skill of designing and refining instructions so AI tools can produce more useful responses.1

For students, it can mean learning how to use AI to prepare for interviews, improve writing, explore career paths, or summarize complex material.

For executives, it can mean using AI to draft memos, pressure-test strategy, analyze donor or customer segments, prepare for meetings, test a hypothesis, or turn rough ideas into clearer plans.

The good news is that no one needs to spend thousands of dollars to learn the basics. Here are three online resources I recommend; IBM SkillsBuild and Microsoft Learn provide free/publicly available learning resources, while the OpenAI Academy collection is publicly accessible and designed around practical workplace AI skills.2

You can also start by reviewing my article GOOGLE’S 9 HOUR AI PROMPT ENGINEERING COURSE – IN 1 CARTOON!, summarized in this cartoon:

Use the right resource for the right audience: students, executives, or time-constrained workplace learners.

1. IBM SkillsBuild: Prompt Engineering – Shaping Better AI Responses

This is my top recommendation for students and workforce-development programs.

IBM SkillsBuild offers a structured prompt-engineering module. The course page says learners identify applications of different prompt types used in generative AI, explore prompt-engineering techniques, select techniques suited to specific tasks, and review best practices for effective prompts.3

IBM SkillsBuild also describes its broader AI learning resources for adult learners as offering free access, practical AI courses, and opportunities to earn credentials.4

For youth-serving organizations, career programs, and adult-learning settings, this is probably the strongest standalone option.

2. Microsoft Learn: Create Effective Prompts for Generative AI Training Tools

This is my top recommendation for busy executives, educators, and organizational leaders who want a fast, accessible introduction.

Microsoft Learn lists this as a beginner module with seven units, and identifies relevant audiences that include business users, K-12 educators, higher education educators, and school leaders. The module covers basic prompt-engineering concepts, elements of an effective prompt, and prompting best practices.5

For executives, I would use this as pre-work before a 60- to 90-minute AI workshop. It gives everyone a shared vocabulary without overwhelming them.

3. OpenAI Academy: ChatGPT at Work

OpenAI Academy offers a ChatGPT at Work collection that includes workplace-focused videos such as Introduction to Prompt Engineering, Advanced Prompt Engineering, ChatGPT for Data Analysis, Deep Research, ChatGPT Search, and other work-related ChatGPT topics.6

This is not a full course in the traditional sense, but it is a terrific executive appetizer. The videos are short, practical, and focused on real work: writing, analysis, research, data, reasoning, and productivity.

For leaders who are curious but time-constrained, this may be the easiest entry point.

How I Would Use These Resources

For a student program, I would assign the IBM SkillsBuild course and then run a hands-on session where students use AI to improve a resume, prepare for an interview, research a career, or summarize a reading.

For executives, I would assign the Microsoft Learn module and a few OpenAI Academy videos before a live workshop focused on real organizational use cases: preparing a board memo, drafting a strategy document, analyzing donor prospects, or creating a first version of an implementation plan.

For both audiences, I would add one essential lesson: AI is powerful, but it is not magic. Users still need to check facts, protect sensitive information, and apply human judgment.

Additional CHU Tips

A few tips I have learned recently through other courses I have taken:

  1. Before asking the AI engine to execute on your prompt, ask it to “Please ask me any clarifying questions to help you answer this prompt/ conduct this research/ create this image/ etc.” I predict you will be surprised at how good the questions are.  They almost always make me think deeper and more clearly about what I want from the prompt.
  2. If appropriate – and especially for larger research projects – you can ask the AI engine to “Convene a panel of experts to ask me questions about the prompt from different points of view.”
  3. To cut down on errors, mistakes, and “hallucinations,” include the following:
    1. “Do not make any thing up.”
    2. “Do not guess.”
    3. “Do not use any sources or research material older than [ __ ] months. (For AI related research, I never allow AI to go back any further than 6-12 months.)
    4. “Please footnote or endnote all references and facts and include a bibliography of sources used in your research, whether or not you actually used them in your response.”
    5. For all footnotes, endnotes and the bibliography, please make sure you include the date that source was published and not just the date you accessed the information.
    6. Please include links to the source documents whenever possible.
  4. Jeff Bussgang, who is the smartest person I know in this space, also recommends using “Please” and “Thank you” in our prompts, so I figure this can’t hurt!

Please let me know your best prompting insights as we all travel this journey of discovery together.

The Bigger Point

Prompt engineering is not just a technical skill. It is quickly becoming a basic workplace and learning skill.

The people who learn how to collaborate effectively with AI will have a major advantage. They will be able to think faster, draft faster, test ideas faster, and learn faster.

That does not mean AI replaces human judgment. In fact, the opposite is true. The better the human judgment, the better the AI collaboration.

So if you are a student, educator, nonprofit leader, or executive wondering where to begin, start here:

Learn how to ask better questions.

That is the first step toward getting better answers.

Endnotes

Suggested for web publishing: convert the superscript numbers in the article to bracketed links that jump to these notes, or keep the notes as a simple source list at the bottom of the post.

  1. IBM defines prompt engineering as writing, refining, and optimizing inputs to encourage generative AI systems to create specific, high-quality outputs. IBM also emphasizes that better prompts directly influence the quality, relevance, and accuracy of generative AI outputs. Source: IBM Think, “What Is Prompt Engineering?”
  2. IBM SkillsBuild describes its adult-learner AI resources as offering free access and courses in generative AI and related areas. Microsoft Learn makes the cited module publicly available. OpenAI Academy makes the cited ChatGPT at Work collection publicly accessible. Source: IBM SkillsBuild, “Artificial Intelligence”; Microsoft Learn, “Create Effective Prompts for Generative AI Training Tools”; OpenAI Academy, “ChatGPT at Work.”
  3. The IBM SkillsBuild course page for “Prompt Engineering: Shaping Better AI Responses” lists the course as eligible for registered learners, available in English, Arabic, Brazilian Portuguese, and Spanish, and four hours in duration. It says learners identify applications of different prompt types, explore prompt-engineering techniques, choose techniques suited to tasks, and review best practices for writing effective prompts. Source: IBM SkillsBuild, “Prompt Engineering: Shaping Better AI Responses.”
  4. IBM SkillsBuild describes its AI learning resources for adult learners as offering free access, AI courses, and opportunities to earn industry-recognized credentials. Source: IBM SkillsBuild, “Artificial Intelligence.”
  5. Microsoft Learn lists “Create Effective Prompts for Generative AI Training Tools” as a beginner module with seven units for audiences including K-12 educators, business users, higher education educators, and school leaders. Microsoft says the module covers the basic concepts of prompt engineering, the elements of an effective prompt, and prompting best practices. Source: Microsoft Learn, “Create Effective Prompts for Generative AI Training Tools.”
  6. The OpenAI Academy “ChatGPT at Work” collection is categorized under Workplace & Business, ChatGPT, Advanced & Builder Skills, and Work. The page lists videos including “Introduction to Prompt Engineering” (5:52), “Advanced Prompt Engineering” (8:50), “ChatGPT for Data Analysis” (4:46), “ChatGPT Search” (5:43), and “Deep Research” (7:06). Source: OpenAI Academy, “ChatGPT at Work.”
  7. All graphics in this draft are original graphics created for this article; no third-party images were used. Source: Original graphics created for Collaboration Evangelist draft, June 5, 2026.

 

Bibliography / Links

Accessed June 5, 2026. All graphics in this draft are original graphics created for this article; no third-party images were used.

  1. IBM Think. “What Is Prompt Engineering?” https://www.ibm.com/think/topics/prompt-engineering
  2. IBM SkillsBuild. “Artificial Intelligence.” https://skillsbuild.org/adult-learners/explore-learning/artificial-intelligence
  3. IBM SkillsBuild. “Prompt Engineering: Shaping Better AI Responses.” https://skillsbuild.org/college-students/course-catalog/prompt-engineering-shaping-better-ai-responses
  4. Microsoft Learn. “Create Effective Prompts for Generative AI Training Tools.” https://learn.microsoft.com/en-us/training/modules/create-prompts-for-generative-ai-training-tools/
  5. OpenAI Academy. “ChatGPT at Work.” https://academy.openai.com/public/collections/chatgpt-at-work-2025-02-14
  6. OpenAI Academy. “Introduction to Prompt Engineering.” https://academy.openai.com/public/videos/introduction-to-prompt-engineering-2025-02-13
  7. OpenAI Academy. “Advanced Prompt Engineering.” https://academy.openai.com/public/videos/advanced-prompt-engineering-2025-02-13

FOMAT & THE AI PRODUCTIVITY TSUNAMI: WHY AI ISN’T MAKING SOME OF US WORK LESS

, , , , , , , ,

FOMAT & THE AI PRODUCTIVITY TSUNAMI: WHY AI ISN’T MAKING SOME OF US WORK LESS

By Craig Underwood | collaborationevangelist.com

Net/ Summary:

Artificial intelligence can absolutely make us more productive. But for executives, consultants, entrepreneurs, nonprofit leaders and other ambitious “power users,” increased productivity does not necessarily mean increased leisure. It can mean more ideas to evaluate, more opportunities to pursue, more reports to read, more decisions to make and more AI “staff” to manage.

The leadership challenge is no longer simply learning how to use AI. It is learning how to manage the tsunami of valuable output AI can create — without sacrificing judgment, relationships, focus or our lives outside work.

 

Figure 1. FOMAT — Fear of Missing Agent Time! A humorous beginning to a very real AI-era management problem.

A few months ago, I created a cartoon with AI called FOMAT: Fear of Missing Agent Time! In the cartoon, I awaken in a panic at 2:47 a.m. with a horrifying thought: “OMG, my agent doesn’t have anything to work on!”

OK, the joke is bit absurd. But, for those of us who have learned how to use generative AI well — through iterative prompt engineering, deep research and custom agents — it may also feel disturbingly familiar.

I use ChatGPT, Gemini and, most prominently, Claude Cowork, where I have begun creating my own custom agents. I also use a Plaud device to record, transcribe and summarize meetings. These tools have not made me less engaged in my work. They have increased my energy and engagement and expanded what I believe I can accomplish.

That is exhilarating. It is also a little exhausting.

Because once you discover that an AI agent can research a market, analyze a strategic question, summarize a meeting, develop a donor profile, create a first draft, recommend next steps or identify ten new opportunities before you have finished your coffee, your problem changes.

The question is no longer: “How can I get this work done?” The new question becomes: “How do I possibly keep up with all the valuable work my AI tools can now help me generate?”

Welcome to the AI Productivity Tsunami.

AI IS MAKING MANY OF US MORE PRODUCTIVE. THAT DOESN’T MEAN WE ARE WORKING LESS.

There is increasingly strong evidence that generative AI can improve productivity.

In a controlled experiment involving professional writing tasks, researchers Shakked Noy and Whitney Zhang found that people using ChatGPT completed tasks approximately 40% faster while producing work rated 18% higher in quality.[1]

In another major workplace study, researchers Erik Brynjolfsson, Danielle Li and Lindsey Raymond examined the use of a generative AI assistant by more than 5,000 customer-support agents. Workers using AI resolved approximately 15% more customer issues per hour.[2]

Research conducted with Boston Consulting Group consultants found similar benefits — but also an important warning. Consultants using GPT-4 performed substantially better on tasks within AI’s capabilities, but performed worse when they relied on AI for tasks outside what researchers called its “jagged technological frontier.”[3]

In other words, AI can help us do more, faster and sometimes better. But productivity does not automatically turn into free time. For ambitious people, productivity frequently creates more ambition.

A ten-hour research project that once seemed impractical may now become feasible. A strategic analysis that once required weeks may now be developed in days. A promising idea that previously remained on the “someday” list can suddenly become an active project. And every new project creates more material to read, test, edit, prioritize, validate, and act upon.

Figure 2. Separate studies find meaningful productivity and quality gains from generative AI; they do not measure a single combined effect.

MY OWN EXAMPLE: AN AI AGENT THAT CREATES OPPORTUNITY — AND MORE WORK

I currently help lead fundraising work for Sportsmen’s Tennis & Enrichment Center (STEC), a Boston nonprofit that provides tennis, academic support, health and wellness programs and community opportunities for thousands of young people and their families.

One important assignment is identifying companies and foundations in Greater Boston that may be strong prospective donors or sponsors.

Historically, researching hundreds of companies from the Boston Business Journal’s Book of Lists would require enormous staff time or outsourced to a charitable consulting firm: identifying companies, researching corporate citizenship priorities, determining whether they give directly or through foundations, reviewing charitable contributions and tax filings when available, assessing connections to youth development or Boston communities, and prioritizing outreach.

Today, I have created an AI-enabled workflow to help research and evaluate more than 500 companies and prioritize those most likely to contribute to STEC.

That is a remarkable capability. But it does not mean I now have nothing to do. Quite the opposite.

The agent can help identify prospects, summarize evidence, assemble information and suggest rankings. But a human still must decide whether the information is accurate and current; which opportunities deserve immediate attention; what kind of contribution to request; who might know someone inside the company; and how to convert intelligence into genuine human connection and financial support.

The agent produces information. The leader must still exercise judgment. And when the information is excellent, the temptation is to pursue more of it. That is exactly how the tsunami begins.

Figure 3. The AI Agents’ Productivity Tsunami: when valuable output creates a new prioritization challenge.

RESEARCH NOW SUPPORTS THE TSUNAMI HYPOTHESIS

My cartoon was intended to be humorous. Then I discovered research suggesting it may also be descriptive.

In February 2026, Harvard Business Review published an article by Aruna Ranganathan and Xingqi Maggie Ye of the University of California, Berkeley Haas School of Business. Based on an eight-month ethnographic study at a roughly 200-person U.S. technology company, their in-progress research found that generative AI did not simply free up time. Employees worked faster, broadened the scope of tasks they undertook and extended work into more hours of the day, often without being instructed to do so.[4]

The explanation is both simple and powerful: AI made doing more feel possible, accessible and rewarding. That is precisely the dynamic many AI power users are beginning to experience.

Figure 4. Recent Berkeley Haas research featured in Harvard Business Review closely mirrors the “productivity tsunami” hypothesis.

Microsoft’s 2025 Work Trend Index provides additional context. Its telemetry analysis found that the top 20% of Microsoft 365 users by ping volume received 275 meetings, emails or chats per workday — equivalent to one interruption approximately every two minutes during an eight-hour workday.[5]

Now add AI agents that can continuously create additional analyses, drafts, ideas, recommendations and action items. AI may help close the capacity gap. But unless leaders deliberately redesign how they work, it can also pour more water into an already overflowing ocean.

Figure 5. Microsoft finds severe input overload among its most highly pinged Microsoft 365 users.

To be clear, this is not everyone’s experience. OECD research on small and medium-sized enterprises using generative AI found that 32.7% reported decreased workload, while 11.8% reported increased workload.[6]

My hypothesis is narrower: for highly motivated leaders and professionals who become skilled AI users — especially those creating their own agents — AI may initially increase rather than decrease total work because it expands the frontier of worthwhile opportunity.

Figure 6. An important counterpoint: among SMEs using generative AI, more reported decreased workload than increased workload.

WHAT ABOUT JOB LOSS?

There is another side of this discussion that leaders should not ignore.

Some highly repetitive, process-oriented and entry-level roles are likely to shrink or change substantially as AI becomes better at routine research, summarization, document preparation, basic customer support, scheduling, data entry and administrative work.

The International Labour Organization has found that clerical occupations remain among those most exposed to generative AI transformation.[7] The World Economic Forum’s Future of Jobs Report 2025 similarly identified clerical and administrative positions — including data entry clerks, bank tellers, cashiers and administrative assistants — among the roles employers expect to decline most quickly through 2030.[8]

I believe leaders have the responsibility – some would say the moral imperative – to help employees learn how to use AI responsibly and efficiently and to move toward higher-value work involving judgment, relationships, creativity, influence, and accountability.  This is especially important for nonprofit leaders of work-force development and college access/ success organizations, and those whose missions include preparing those they serve for jobs of the future.  Imagine the different impression a young entry-level job or internship applicant would leave on a prospective employer when answering the question “Do you use AI?” between:

“[My training organization] has provided responsible AI literacy training and prompt engineering to all of its students.”

And

“I don’t use AI much at all.” Or even worse, “We are prohibited from using AI.”

 

THE SOLUTION: SURF. PRIORITIZE. IMPACT.

In the upper-left corner of my Productivity Tsunami cartoon is a simple phrase: Surf. Prioritize. Impact. I think this may be the practical leadership framework we need.

1. SURF: USE AI ENTHUSIASTICALLY — BUT PURPOSEFULLY.

The answer is not to run away from AI. It is too valuable. These tools can help leaders think better, research faster, communicate more clearly and identify opportunities that might otherwise go undiscovered.

But surfing a wave is different from letting it drown you.

Leaders should be explicit about what they want AI to help accomplish. Or, to borrow a phrase from Steven Covey’s The 7 Habits of Highly Effective People, “begin with the end in mind.”  Create agents around important outcomes, not simply because creating another agent is interesting. Keep a running “AI opportunity parking lot” for intriguing ideas that do not deserve immediate action.

2. PRIORITIZE: SCHEDULE MEETING TIME WITH YOUR AI OUTPUT.

If you manage human colleagues, you do not expect them to slide dozens of excellent reports under your door every night and assume you will process them all by morning. The same discipline should apply to AI agents.

Schedule regular “meeting time” to review AI-generated work: a weekly (or daily) review of agent findings and recommendations; a clear decision rubric for what moves forward, what gets delegated, deferred or discarded; limits on active AI-enabled projects; and a requirement that all AI research and other generated content receive human verification and reflection.

The ability to generate more options makes disciplined prioritization more important, not less.

3. IMPACT: PROTECT THE WORK ONLY HUMANS CAN DO.

AI can produce a donor prospect analysis. It cannot build trust with a prospective sponsor over coffee. AI can summarize a leadership challenge. It cannot look a struggling colleague in the eye and ask the compassionate question that changes a relationship. AI can generate executive coaching frameworks and meeting notes. It cannot replace the human wisdom, accountability and courage required to make a difficult choice.

Leaders should protect time for relationships, reflection and judgment — the very human activities that make AI-generated intelligence meaningful. And we should place boundaries around our AI-enabled work lives.  We must make sure that those of us who become highly productive through AI do not confuse increased output with increased impact — or silently turn every available evening, weekend, and quiet moment into additional time supervising our digital workforce.  Given my passion for and excitement about “living on an AI vertical learning curve, “ my wife and I often have “AI discussion timeouts,” where I am not allowed to talk about it – much less, fire up Claude on my laptop to show her the latest cool thing we generated together.

Not every new research question needs to be launched tonight. Not every good idea requires immediate development. Not every idle agent needs a new assignment before bedtime.

Sometimes the most productive instruction we can give our AI agents is: “Good work. We will review this tomorrow.”

THE HUMAN STILL HAS TO CHOOSE THE SHORE

Artificial intelligence is not simply reducing the burden of work. For many of us, it is revealing a much larger universe of work that could be done.

That is not necessarily bad news. It means that a small consulting firm, nonprofit leader, entrepreneur or executive can now access analytical, creative and research capacity once available only to organizations with large staffs and large budgets.

But abundance creates a new leadership obligation. The best leaders in the AI era will not be the people whose agents generate the most reports, the most ideas or the most activity. They will be the people who know which waves to ride, which opportunities to ignore, which decisions require human judgment and when to step out of the ocean entirely.

Because the goal of AI is not to keep every agent busy. The goal is to help human beings create meaningful impact — while still leaving enough time and energy to be fully human.

Footnotes

[1] Shakked Noy and Whitney Zhang, “Experimental Evidence on the Productivity Effects of Generative Artificial Intelligence,” Science 381, no. 6654 (2023): 187–192. Finding cited in the article abstract: average time decreased 40% and quality rose 18%.

[2] Erik Brynjolfsson, Danielle Li and Lindsey Raymond, “Generative AI at Work,” The Quarterly Journal of Economics 140, no. 2 (2025): 889–942. Published article reports a 15% productivity increase measured by issues resolved per hour.

[3] Fabrizio Dell’Acqua et al., “Navigating the Jagged Technological Frontier: Field Experimental Evidence of the Effects of AI on Knowledge Worker Productivity and Quality,” working paper, 2023; subsequently published in Organization Science.

[4] Aruna Ranganathan and Xingqi Maggie Ye, “AI Doesn’t Reduce Work—It Intensifies It,” Harvard Business Review, February 9, 2026; Laura Counts, “AI Promised to Free Up Workers’ Time. UC Berkeley Haas Researchers Found the Opposite,” Haas News, February 18, 2026.

[5] Microsoft WorkLab, “Breaking Down the Infinite Workday,” June 17, 2025; Microsoft, 2025 Work Trend Index Annual Report. The 275-per-day figure is based on the top 20% of Microsoft 365 users by ping volume received; the two-minute figure is calculated over an eight-hour workday.

[6] Organisation for Economic Co-operation and Development, Generative AI and the SME Workforce: New Survey Evidence (2025), Figure 3.5.

[7] International Labour Organization, Generative AI and Jobs: A Refined Global Index of Occupational Exposure (2025).

[8] World Economic Forum, Future of Jobs Report 2025 (2025).

Research Bibliography

Brynjolfsson, Erik, Danielle Li and Lindsey Raymond. “Generative AI at Work.” The Quarterly Journal of Economics 140, no. 2 (2025): 889–942.

Dell’Acqua, Fabrizio, et al. “Navigating the Jagged Technological Frontier: Field Experimental Evidence of the Effects of AI on Knowledge Worker Productivity and Quality.” Working paper, 2023; subsequently published in Organization Science.

International Labour Organization. Generative AI and Jobs: A Refined Global Index of Occupational Exposure. 2025.

Microsoft. 2025 Work Trend Index Annual Report. 2025.

Microsoft WorkLab. “Breaking Down the Infinite Workday.” June 17, 2025.

Noy, Shakked and Whitney Zhang. “Experimental Evidence on the Productivity Effects of Generative Artificial Intelligence.” Science 381, no. 6654 (2023): 187–192.

Organisation for Economic Co-operation and Development. Generative AI and the SME Workforce: New Survey Evidence. 2025.

Ranganathan, Aruna and Xingqi Maggie Ye. “AI Doesn’t Reduce Work—It Intensifies It.” Harvard Business Review. February 9, 2026.

University of California, Berkeley Haas School of Business. “AI Promised to Free Up Workers’ Time. UC Berkeley Haas Researchers Found the Opposite.” February 18, 2026.

World Economic Forum. Future of Jobs Report 2025. 2025.

 

CHU RECOMMENDS: 4 Books, 1 Novel, & 3 Podcasts to Learn About & Keep Up with AI

, , , , , , , ,

CHU RECOMMENDS: 4 Books, 1 Novel, & 3 Podcasts to Learn About & Keep Up with AI

Net/ Summary:

The Books:

  • The AI Driven Leader by Geoff Woods
  • AI First by Adam Brotman and Andy Sack
  • The Experimentation Machine by Jeffrey Bussgang
  • Human + Machine by Paul R. Daugherty & H. James Wilson

The Novel:

  • Coded Justice, by Stacey Abrams

The Podcasts:

  • The Most Interesting Thing in AI
  • Beyond the Prompt – How To Use AI In Your Company
  • Practical AI

More Details:

The Books:

The AI Driven Leader by Geoff Woods
This book blends strategic frameworks with real-world applications to help leaders understand and implement AI initiatives. Woods distills complex concepts into approachable tools for decision-makers.
Best for those wanting to translate AI potential into actionable leadership strategies.

AI First by Adam Brotman and Andy Sack
A practical playbook for leaders in any industry, AI First lays out the mindset and operating model needed to integrate AI into every level of an organization. The authors focus on customer experience, organizational design, and cultural transformation.
Best for those wanting to shift their business mindset to lead with AI from the ground up.

The Experimentation Machine by Jeffrey Bussgang
Bussgang, a venture capitalist and Harvard professor, explores how top startups use experimentation and data—especially with AI—to drive innovation. The book includes case studies from the tech world and frameworks for iterative learning.
Best for those wanting to understand how AI powers experimentation, especially in fast-moving startups and product teams.

Human + Machine by Paul R. Daugherty & H. James Wilson
This foundational book from two Accenture executives lays out how companies can combine human ingenuity with AI’s capabilities to reinvent business processes. It introduces the concept of “missing middle” jobs and augmented intelligence.
Best for those wanting to explore how AI augments—not replaces—human work across industries.

 

 The Novel:

Coded Justice by Stacey Abrams
Abrams weaves a fast-paced legal thriller around a deepfake video and a high-stakes courtroom battle. Beneath the drama lies a thought-provoking look at AI, surveillance, and ethics.
Best for those wanting to grasp the real-world potential in health care and the risks of AI through a gripping, fictional lens.

The Podcasts:

The Most Interesting Thing in AI
Hosted by Nathan Benaich, this podcast offers sharp insights into the latest developments in AI, from research to policy. With guests from DeepMind, OpenAI, and VC firms, it’s both accessible and rigorous.
Best for those wanting to stay current on breakthroughs and big-picture trends in the AI ecosystem.

Beyond the Prompt – How To Use AI In Your Company
This podcast focuses on real-world implementations of AI tools across functions like sales, marketing, operations, and customer service. It’s geared toward business leaders and internal innovators.
Best for those wanting to learn practical, tactical ways to embed AI in daily business workflows.

Practical AI
Produced by Changelog, this long-running podcast brings together developers, data scientists, and entrepreneurs to discuss AI applications, tools, and ethics. Each episode balances technical depth with big-picture thinking.
Best for those wanting to understand how AI actually works—and how to build with it.

Please let me know your recommendations! 

PS/ Disclaimer: One of the major debates about AI is “Does it/ can it/ or will AI make people lazy?”  FYI, I have actually read all 5 books (and others I have not recommended) and listen to these podcasts every week, but after outlining the article, I asked ChatGPT to write the short summaries and “best for” recommendations for each bullet from the summary.  I did not feel the need to edit what she wrote. Am I lazy or productive????

GOOGLE’S 9 HOUR AI PROMPT ENGINEERING COURSE – IN 1 CARTOON!

, , , , , , ,

Summary:

I recently completed Google’s Coursera course on prompt engineering to continue sharpening my use of AI—for both work and play. Like many of you, I want to get better, faster, and more reliable outputs from these powerful tools. To help me remember the core principles, I’ve adopted and modified a fun and memorable mnemonic (more on that in a second). But first, here’s the big idea:

To write effective prompts, you need to include seven core sections:

Teeny Tiny Crabs Riding Fat Enormous Iguanas
T = Task  T = Tone  C = Context  R = References  F = Format  E = Engage  I = Iterate

Include each of these elements in your prompt, and you’ll dramatically improve your results.

Where This Came From

Much of this is based on Tina Huang’s excellent YouTube summary, “Google’s 9-Hour Prompt Engineering Course in 20 Minutes.” (As someone once said: “If you steal from one person, it’s plagiarism. If you steal from many, it’s research.” I do a lot of research!)

The Google course itself is built around five inputs for effective prompt design:

Task, Context, References, Engage, Iterate

Their trainers introduced the mnemonic:

Thoughtfully Create Really Excellent Inputs

Tina found it hard to remember—and I agreed. She came up with a more vivid version:

Tiny Crabs Riding Really Enormous Iguanas

To that, I added two key concepts from my own experience—Tone and Format—to make it more complete.

The final version?

Teeny Tiny Crabs Riding Fat Enormous Iguanas

Why Add “Tone” and “Format”?

I’ve written hundreds of prompts across multiple platforms while using AI in professional consulting and nonprofit fundraising. Here’s why those two extra sections matter:

  • Tone is critical for anything involving writing. For example, when I want a professional yet conversational article (like this one), I say so in the prompt. Tone is often influenced by the Context section, especially when I open with something like:

“I am the head of a boutique consulting firm that specializes in…”
This helps the AI match voice, audience, and style.

  • Format becomes essential for large-scale research tasks. I’m currently using AI to research the charitable giving practices of 200+ companies to prioritize potential donors for several nonprofit clients. In this kind of work, it’s not enough to just get raw information—I need it delivered in tables, bulleted lists, or other clean formats that are easy to review and analyze.
    Gemini (Google’s AI) is particularly strong at formatting outputs into tables, and with one click, those can be exported into Google Sheets—saving tons of time.

A Quick Walkthrough of Each Section

  • #Task#: Be as specific as possible. Clearly define what you want the AI to do. I often assign the AI a role or persona, like:

“You are an expert content strategist writing a blog post on how to use AI in marketing research.”
This helps focus the AI’s responses.

  • #Tone#: Set the mood—professional, playful, technical, academic, or conversational. If your writing has a target voice, state it upfront.
  • #Context#: Describe who you are, why you’re asking the question, and who the audience is. The better the AI understands your intent, the better its output.
  • #References#: Upload or include everything relevant: job descriptions, resumes, bios, organizational goals, website URLs—whatever provides grounding for the AI’s output. The more context it has, the smarter it behaves.
  • #Format#: Be clear about how you want the information delivered. Want a comparison table? A checklist? A three-paragraph summary? Tell it.
  • #Engage#: Don’t copy and paste the output blindly. Engage with it. Review it. Challenge it. AI tools still make plenty of hallucinations (mistakes), so check citations, dates, and factual claims before you use them. Ask for sources. Fact-check relentlessly.
  • #Iterate#: Rarely do you get the perfect response on the first try. In my experience, it takes 2–3 iterations to get what I really want.

Here’s a fun example:
I used ChatGPT to create a cartoon for a party invitation featuring my American Bully, Izzy. I uploaded a photo and asked for a cartoon of her in a chef’s hat next to a grill.

  • Version 1: Looked like Izzy, but she was wearing her leather biker jacket from the photo.
  • Version 2: I asked for a chef’s jacket—got that—but the dog didn’t look like Izzy anymore.
  • Version 3: I asked to combine the head from version 1 and the jacket from version 2—and nailed it!

Iterating means providing clear, specific feedback. When the AI gets something wrong, tell it what and why. That’s how you teach it—and improve your results over time.

One Final Tip: Use Section Headers in Your Prompts

I have read several books and articles about AI and cannot remember where I learned this, but some recommend separating your prompts into the TTCRFEI sections and placing a “#” before and after the section title, e.g. #Task#.  Experts suggest this will improve the quality of your outputs by adding clarity and structure, focus, and reducing ambiguity.  By segmenting the prompt, you can make sure the AI knows what it is reading and how to use the information. For example, after reading # Task #, the AI knows the following text defines what it needs to do. After # Reference #, it understands that the text is supplementary information that it should consider. It also avoids or at least reduces misinterpretation.

Let’s Keep Learning Together

I hope this is helpful. If you’ve developed your own strategies for writing better prompts—or if you’ve tested this framework—I’d love to hear your thoughts. The more we share, the better we all get.

And Yes, I still recommend investing in the Coursera Google course.

One of my mantras as CEO of The Loyalty Group was “training without testing is little more than orientation.”  My (and Tina’s) shortened version/cartoons notwithstanding, if you are relatively new to AI, I would recommend taking the Coursera course.  It’s free, and if you have “fast ears” and can listen to the video portions at 1.5–2.0X speed, it takes far less than 9 hours.  The two things I like best about it are:

  1. Completing the course requires you to show actual prompts you have written, along with improvements you have made.
  2. The course has an exam at the end of each of the four major sections. If you score at least 80% on the exams, you receive this certificate:

CHU RECOMMENDS: PLAUD – THE ABSOLUTE COOLEST AI RECORDING DEVICE YET!

, , , , , ,

CHU RECOMMENDS: PLAUD – THE ABSOLUTE COOLEST AI RECORDING DEVICE YET!

OK, I admit it.  I am obsessed with this thing called Plaud.

Last week, I did a trial run of the AI-powered recording device Plaud.  It blew me away.  Here’s what it is and (at least some) of what it can do:

  • About the size of a credit card length and width. About as thick as 3 credit cards.
  • Appears to be very well made – out of metal, doesn’t feel like cheap plastic. Buttons function well.
  • Comes in a magnetic carrying case that attaches it to the back of your phone – even works over my QUAD iPhone 16 Pro case I use for cycling.
  • Records your calls and meetings. Change between the 2 modes by moving the small button switch on the top up for calls and down for recording what’s in the room, including multi-person meetings, Zoom calls, etc.  When it is attached to your phone, you can use speaker phone, ear buds, or just listen to the call next to your ear.
  • Plaud transcribes your calls with extremely high accuracy, in my experience over the past week. I don’t always have the best diction, but so far, Plaud has interpreted my occasional “mumbles” flawlessly.
  • BUT THESE ARE TEENY WEENIE FEATURES COMPARED TO THE MAIN EVENT – Plaud uses AI to brilliantly convert your calls, meetings, etc. into highly accurate, incredibly well-formatted summary notes. I tested Plaud the first day I had it, using it to record and summarize two calls:
    • The first was a call with an executive from a solar panel company. During the call, we discussed the HOA Board’s challenges to install solar panels on my townhouse.  I also made a referral to the executive for a friend whose home is a much better candidate for solar power.  One feature of Plaud summaries I appreciate and am amazed by is its ability to capture the subject matter/ purpose of the call or meeting in the summary title (this is a screenshot of the actual notes):

    • The second was a 45-minute meeting with an executive from The Possible Zone (TPZ). TPZ is one of my favorite clients that offers after-school and summer programming to provide hands-on teaching and experience instilling entrepreneurial spirit and capabilities for underserved inner-city high school students. The discussion centered on a new project that Underwood Partners is working on for TPZ.  And again, Plaud did an excellent job both transcribing and especially summarizing the meeting.
  • Plaud’s AI transcription & summarization capabilities have been developed on GPT-4.1, o3-mini, Claude 3.7 Sonnet, and Gemini 2.5 Pro tools. It supports 112 languages.
  • The Plaud app and website offer professional templates tailored for various use cases. Transcriptions and summaries are easily shared with yourself or others.

An Important Caveat:

As I wrote in my article Overwhelmed by AI Ubiquity?  You’re Not Too Late To Get Started – Here’s How,  you cannot use AI as a “set and forget” tool.  As amazing as current AI capabilities are (and they get better every day), AI is far from infallible.  This applies to Plaud summaries as well.  Reading over the excellent summary of my TPZ call, I found one major error.  During the call, I asked the TPZ executive for feedback on our work to date.  One of the things she recommended was to always give the CEO a “read ahead” before presentations, even if they are in draft form.  Plaud inaccurately reported in the meeting summary that the CEO did not want to receive materials in advance of meetings.  Several AI experts have written that AI is usually 50-80% correct.  In my experience, AI – especially Google’s Gemini – is closer to 80%, but as this example demonstrates, AI can make BIG TIME mistakes.  Always, always, always check AI’s work and sources.

My Only Recommendation for Improving Plaud

I am sure this is an indictment of my personality and ego, but I am usually frustrated when asked for feedback on something and nothing comes to mind.  Fortunately, that is not the case with Plaud.  My only suggestion for making Plaud easier to use is to enable the device to be charged with the nearly ubiquitous USB-C cable.  Yes, unfortunately, Plaud comes with its own unique charging cable. Ugh!  It’s a small magnetic device that connects to the back of Plaud and can be easily used with the magnetic case on.  But it is yet another separate “single-use” charging cord I need to have in my office, backpack, car, etc., and will undoubtedly be lost!  I hate whoever recommended this “blades and razors strategy” to Plaud, slightly tarnishing an otherwise flawless customer experience!

How Much $$$ and Where to Buy

The Plaud device costs $160, and you can purchase it directly from the company at www.Plaud.ai or from Amazon.

Plaud provides transcription and storage services with a “freemium” model.  Plaud comes with 30-hour continuous recording, 60 days of standby, and 64GB of storage.  For the cost of the device, Plaud provides unlimited cloud storage and 300 hours of transcription and summary services per month.  For an additional $100/ year, the Plaud Pro-Plan provides 1,200 minutes of transcriptions and summaries monthly, or $150/ year provides unlimited transcriptions and summaries plus additional goodies.

HAVE FUN AND PREPARE TO BE OBSESSED!