Thinks 1177

NYTimes: “BYD’s sales, over 80 percent of them in China, have grown by about a million cars in each of the past two years. The last automaker to accomplish that in even one year in the American market was General Motors — and that was in 1946, after G.M. had suspended passenger car sales during the four preceding years because of World War II. “BYD’s growth is unlike anything the industry has seen in many decades,” said Matt Anderson, curator of transportation at the Henry Ford Museum in Dearborn, Mich. Based in Shenzhen, the hub of China’s electronics industry, BYD has shown how Chinese carmakers can tap the country’s dominance of electrical products. No company has benefited as much from China’s embrace of battery-electric cars and plug-in gasoline-electric cars. These vehicles together make up 40 percent of China’s car market, the world’s largest, and are expected to be more than half next year.”

Rahm Emanuel: “Before I arrived in Tokyo as ambassador two years ago, a number of foreign policy experts cautioned me that Japan moves slowly. They urged me to find a virtue in patience when dealing with the government — which I knew would be tricky for someone like me who has zero patience. I needn’t have worried. Two years later, one thing is clear: The experts didn’t know much about the new Japan. No one predicted that this would be an era of Japanese transformation, a time when the Japanese surprised nearly everyone with what they can and will do.”

McKinsey: “For decades we’ve seen companies’ fortunes rise and fall based on their ability to react to, and recover quickly from, geopolitical shocks, technological advances, economic uncertainty, competitors’ bold moves, and other disruptions. Amid this volatility, which these days is accelerating rather than abating, many have a hard time staying the course. But some continue to survive and thrive despite the challenges. Why do these companies manage to succeed, year after year—operationally, financially, and otherwise—while others don’t? Twenty-plus years of proprietary McKinsey research tells us that one of the main reasons is organizational health. Organizational health refers to how effectively leaders “run the place”—that is, how they make decisions, allocate resources, operate day to day, and lead their teams with the goal of delivering high performance, both near term and over time. Organizational health comprises three elements: how well the entire organization rallies around a common vision and strategy, how well the organization executes its strategy, and how well the organization innovates and renews itself over time.”

Wanted: A Constellation Software for Martech (Part 7)

Critique

I asked ChatGPT and Claude for a critique of the MarCo idea.

ChatGPT

The MarCo concept, inspired by Constellation Software’s successful model in acquiring vertical market software companies, proposes a novel approach to consolidating the fragmented martech industry. While the idea holds promise, there are several challenges and considerations that merit a critical examination.

Firstly, the martech sector’s inherent complexity and rapid pace of innovation present significant hurdles. The diversity in the needs and technologies across different marketing domains—from email marketing and social media analytics to customer relationship management and ad tech—means that a one-size-fits-all approach may not be feasible. The risk of homogenization could stifle innovation, leading to solutions that are jack-of-all-trades but masters of none, potentially compromising the specialized services that many martech companies offer.

Secondly, the cultural and operational integration of acquired companies poses another challenge. Constellation Software’s model thrives on a hands-off approach, allowing acquired companies to operate independently. However, in the martech space, where integration and interoperability between different solutions are key, this decentralized approach might impede the creation of a cohesive product suite. Ensuring seamless integration while maintaining the autonomy and unique value proposition of each entity would require a delicate balance.

Furthermore, the focus on tapping into ‘AdWaste’ as a primary growth lever might oversimplify the complexities involved in reallocating advertising budgets towards martech solutions. The effectiveness of advertising spend is not solely a function of the tools used but also of the strategies, content, and execution. Merely shifting budgets from adtech to martech without addressing the underlying inefficiencies in marketing strategies may not yield the expected returns.

Another concern is the scalability of the MarCo model in a sector as dynamic as martech. Rapid technological advancements and shifting marketing trends could render acquired solutions obsolete, requiring continuous investment in innovation and development. This need for perpetual modernization could strain the financial model, especially given the high valuations and competitive funding landscape in the tech sector.

Lastly, the success of MarCo would heavily rely on the execution capabilities of the anchor martech vendor. While the vendor’s deep industry knowledge and customer base are advantageous, managing a portfolio of acquired companies, integrating their technologies, and driving synergistic growth would demand a level of operational sophistication and agility that may be challenging to achieve.

In summary, while the MarCo idea is an intriguing proposition for consolidating the martech industry and capitalizing on untapped opportunities, it faces substantial challenges. These include ensuring effective integration and innovation across a diverse portfolio, navigating the complexities of the martech sector, and maintaining a sustainable growth model in the face of rapid technological evolution.

Claude

Strengths:

  1. Leverages proven model of Constellation Software. MarCo seeks to apply the successful acquisition and decentralized management strategy of Constellation Software specifically to the martech industry. This model has a strong track record of creating shareholder value.
  2. Consolidates fragmented industry. Martech is highly fragmented with over 11,000 companies. MarCo can roll up smaller players to achieve economies of scale and provide an integrated stack of solutions to customers.
  3. Taps into large market opportunity. Shifting ad spending waste to martech provides fuel for significant growth in total addressable market. If even a fraction of estimated $250 billion in ad waste can be captured, it massively scales up the market.
  4. Win-win for multiple stakeholders. MarCo offers exit for struggling startups, integrated solutions for customers, and investment leverage for participating funds/investors. Broad value creation.

Weaknesses:

  1. Execution complexity and risk. Acquiring and integrating companies across continents adds managerial complexity. Need systems and leadership to make model work efficiently.
  2. Competitive risks. Larger players may compete more aggressively if market expands substantially. Margins could get compressed despite wider reach.
  3. High debt burden initially. Interest costs are front-loaded before benefits of consolidations kick in. Need patience from funds on financial payoffs.
  4. Culture mix challenges. Blending work cultures across acquired companies can be tricky. Need to preserve autonomy while creating common identity.

In summary, MarCo is a bold strategic idea to consolidate the martech ecosystem. It addresses the needs of various industry stakeholders and has multi-billion dollar potential if executed systematically. However, investors should weigh the managerial and competitive risks inherent in a complex global roll-up strategy built primarily through acquisitions. Overall an idea with merit but not without risks.

Thinks 1176

WSJ on Apple’s Vision Pro: “The $3,500 strap-on device has confused early reviewers about its purpose…Many early users have already concluded that it is a device in its infancy, and its true purpose won’t become apparent until it becomes cheaper, lighter and more capable. But the future of the Vision Pro is already apparent. Its target market is you, if you’re a knowledge worker. And its use case is every day, as you do your job. Since its Feb. 2 launch, many early adopters have chronicled their adventures on social media. Their experiences suggest we may already know Apple Vision Pro’s killer app: Microsoft Excel. But wait, don’t click away yet. It’s also email. And Slack. “I’ve been seeing a lot actually, in the last week, people being surprised that they can use it for work, especially as a virtual desktop,” says Ethan Kaplan, a tech adviser at a venture-capital firm and former chief digital officer at Fender Musical Instruments. “It’s really good—I’m staring at it right now, actually.”” WaPo: “After…two weeks, I’m sold on what the Vision Pro can do. I want to keep app windows around me in just the right places, shut out the world sometimes when I need some alone time, and pop back in when I’m ready. I just don’t want to wear a hefty headset on my face to be able to do these things, or shell out at least $3,499 for it.”

FT: “London Business School academic Lynda Gratton spends her time advising employers about how to better organise their workforce. But she no longer thinks much about jobs: lately, she has noticed, specific roles have been replaced with lists of desired skills and character traits. “When I work with companies now the matrix they have is not jobs, it’s skills,” she says. Employers are looking not for specific roles but people who can be creative, experiment with new ideas or manage complex stakeholders. “Don’t get hung up about job titles: ask, what are the skills that are going to give you opportunities to grow?” One in 16 workers globally may have to switch occupations by 2030 as their roles become obsolete, according to consultancy McKinsey, and nearly nine in 10 executives say they face imminent skills gaps. Faced with the need for new and developing skills, many employers are choosing to retrain their own workers rather than recruit externally.”

Andy Kessler: “Today more than ever, investing is a fashion, especially in technology and biotech. Every single cycle, technological obsolescence is unseen. The new comes along and the old—mainframes, minicomputers, dial-up internet access, flip phones, homework-helper apps—gets milked for too long. Investing fads emerge, get overblown, and go out with an intense selloff. Examples are personal computers, client-server, dot-com, cloud and now artificial intelligence. Momentum investors jump in late and often get burned when something unseen sneaks in. Often it’s supply. There is currently a shortage of chips for AI, so Nvidia (57% operating margins) has pricing power. But silicon comes from sand; only capital and time are in short supply. Same with obesity drugs. There’s a shortage now, but many new versions are awaiting approval over the next several years. When pricing power disappears, margins crater. Foresee the unforeseen.”

Peter Diamandis on the AI Assistant: “Here are a few others that may be coming soon: “JARVIS, please locate my kids, and show me a video of what they’re doing at the moment. And, do you happen to know if they’ve completed their math homework yet?” Or “JARVIS, did you happen to watch that last conversation I had with my friend Walter? It looks like something is really troubling him. Any clue or guess as to what it might be?” That last point is fascinating.  As your digital assistant gains access to imagery and video, it will gain another critical skill: better understanding human emotions and subtle communications.” [via Arnold Kling]

Wanted: A Constellation Software for Martech (Part 6)

Making MarCo Happen

MarCo is about bringing three ideas together:

  • The business model of Constellation Software
  • The partnership of an anchor martech vendor with a fund
  • The scale-up of the addressable market by tapping into AdWaste

We have discussed the first and third points. The second one needs an explainer.

Funds typically don’t like to get into running businesses. While some PE funds do take over and operate businesses, they do so on a big scale (hundreds of millions of dollars to a few billion dollars). Its typically a single business where they work with the existing or new management team to build out the business after their entry, in preparation for an exit in a few years, hopefully generating an IRR of 25% or more.

MarCo has a different approach. The anchor martech vendor becomes the operator of the acquired businesses. It has deep understanding of the martech space and also a base of customers and existing tech. As such, it is ideally placed for doing roll-ups. But because of the constraints I mentioned earlier (slowing market growth and limited availability of capital based on its own balance sheet), it cannot make the bigger acquisitions on its own. The fund structure gives it the leverage to do bigger deals.

For investors in the fund, they get a partner who has skin in the game by virtue of the anchor martech vendor’s investment. They get access to a management team which knows how to build and scale businesses. They can consolidate a fragmented industry to create more value. The AdWaste opportunity becomes an added attraction. For entrepreneurs and founders seeking an exit in troubled times, MarCo becomes the perfect partner – an alternative to shutting the business down when capital runs out. For digital businesses, they get better products which are tightly integrated rather than loosely coupled together. They also can look at solving problems with off-the-shelf solutions rather than trying to build them on their own. They don’t need to worry about their seller failing or shutting down. In short, it’s a win-win for everyone on the ecosystem.

Over time, MarCo can create a playbook like Constellation Software has done to simplify the acquisition process. It can also create a business system that ensures management and operational efficiencies. The growth by acquisition model has been used in many industries. What is new here is its application to a single software domain (martech) to build and realign one of the most important industries of our times – selling to billions of customers digitally and making money from them.

MarCo is an idea whose time has come!

Thinks 1175

MobiHealthNews about a digital twins company: “Unlearn uses machine learning to create digital twins of clinical trial participants before being randomized in a controlled trial. The digital twin can provide researchers insight into the participants’ health outcomes. The startup pitches its technology as a way to run smaller clinical trials more quickly, since researchers can find fewer participants for the control group…”Pharmaceutical companies are spending over $100 billion dollars a year on clinical research, yet the industry remains skeptical about new technology that has the power to truly transform research,” said Charles Fisher, founder and CEO of Unlearn. “Breaking down these barriers and proving the value of digital twin technology continues to be a main driver for us at Unlearn. And, this round of financing will allow us to not only grow our team but also expand our capabilities into more therapeutic areas to build awareness and prove the value.”

FT: “The starting point is to recognise that bots are essentially “counterfeit” humans, as the philosopher Daniel Dennett has noted. This suggests, as historian and author Yuval Harari recently told me, that we should explore how governments have battled “counterfeits” elsewhere — most notably, through history, in the sphere of money…The key takeaway from financial history is that it is possible to create a cultural frame that criminalises counterfeiting. Now that would certainly not address all the deepfake problems online.”

WaPo: ““Why We Read: On Bookworms, Libraries and Just One More Page Before Lights Out, a warm and funny memoir in essays from the appropriately named Shannon Reed. Covering topics ranging from the deliciousness of that twist in “Gone Girl” and the joy of Amish romance novels to the semester she spent decoding George Saunders’s “Lincoln in the Bardo,” Reed — who teaches writing and contemporary fiction at the University of Pittsburgh — chronicles her lifelong relationships with books and reading. Underlying each essay, though, is a conviction that people should read what they want to read. The latest Emily Henry book, “Moby-Dick” and tomes on U.S. history, she explains, all offer value to the reader. “There are simply too many rules about reading,” she writes. “Worse, the higher up the ladder of being a Good Reader … people go, the more rules they seem to have internalized.””

Arnold Kling: “Economist Thomas Sowell is known for saying “There are no solutions, only trade-offs.” That should be known as Sowell’s Law. When we are faced with a set of binary decisions of a given sort, Sowell’s Law can be described as the trade-off between making two types of mistakes. In classical statistics, a Type I error means claiming that the evidence for a hypothesis is strong when it isn’t. And a Type II error means failing to recognize that the evidence for a hypothesis actually is strong. But Type I and Type II errors can be used to describe many more situations. For instance, in a court case, the jury must find the defendant guilty or not. One mistake would be to convict an innocent defendant. Call that a Type I error. The opposite mistake would be to fail to convict a guilty defendant. That is a Type II error. By setting a standard of “innocent unless guilty beyond a reasonable doubt,” our legal tradition is saying that we should try to minimize Type I errors, at the risk of committing Type II errors.”

Wanted: A Constellation Software for Martech (Part 5)

MarCo

MarCo (Martech Consolidator) can start life as a fund which partners with a martech company (like Netcore). This mirrors the beginnings of Constellation Software, as outlined by Speedwell Research:

Over [his] next 11 years in VC [venture capital], Mark Leonard would solidify what he wanted to build. He would fondly recall how fulfilling it was to build something properly as a masonry, which required mastery and would be there 100 years later. (To his surprise, this was in contrast to many of the start-ups he worked with that had a “build to sell” mentality). His masonry experience, coupled with some mentorship that that exposed him to the Buffett & Munger orthodoxy, inspired his plan to construct an enduring company. This nebulous desire, however, only started to calcify after a novel insight about the success of Venture Wests’ portfolio companies. He noticed that their most successful venture investments were vertical market software companies, which to Leonard seemed to have all of the business virtues Buffett would want with a competitive “moat”. The problem though, was that each vertical market software (VMS) company was relatively unimpactful to the overall portfolio results because of their small size. His idea was to create a holding company that would just focus just on acquiring VMS companies, which he imaginatively wanted to call Software Co.

Mark’s reputation as a sharp thinker with an indisputable work ethic made many of his Venture West colleagues enthusiastic to seed his idea, which, alongside an old business school buddy who happened to work at OMERS (Ontario Municipal Employees Retirement System) pension fund, allowed him to raise a full $25mn CAD. There was one piece of feedback though; the name Leonard picked was terrible. And so Software Co. became Constellation Software, a reference to seeing a unifying picture of otherwise unconnected pieces, and officially launched in 1995.

In the early years of Constellation Software, Mark Leonard would lead the acquisition process, focusing on wholly acquiring their first VMS companies. The attraction to VMS was born from the fact that each software offering tends to be mission critical to users and each market is small enough that competition is insulated from the big players who could not rationalize spending in these small TAMs. Additionally, the recurring nature of most revenues and minimal maintenance capex makes software inherently attractive.

Recurring revenue is what SaaS companies get. The challenge for many is that the sales and marketing costs are high (remember: 11,000+ martech companies!) and this hurts their ability to generate consistent and scalable profits. What MarCo therefore needs is one or more anchor martech SaaS companies (like Netcore) which have access to a large portfolio of digital businesses.

Imagine a $100 million fund to begin with — $10 million coming from the anchor martech vendor, $40 million from investors, and $50 million in debt. Assume the debt will come in at 10%, and thus need $5 million in annual interest payments.

Next, let’s assume there is a target martech company with $5 million in revenue and about $1 million in operating losses. So, the split of the $6 million in costs would be something like this:

  • $1.5 million in cloud costs (assuming 75% gross margin)
  • $1.5 million in product, engineering and R&D
  • $1.5 million in marketing and sales (30% of costs)
  • $1.5 million in general & administration costs

Three costs can be reduced after a takeover by MarCo:

  • A third of the product, engineering, and R&D costs – by shifting some operations to India
  • A third of the marketing and sales, by leveraging the strengths of the anchor martech vendor and cross-sell across the growing portfolio
  • A third of the G&A costs – by consolidating across the group

Together, this can bring in savings of $1.5 million, converting the $1 million loss into a 10% positive EBIDTA of $0.5 million.

Half of this would be used to service the debt on the deal, and the other half becomes the cashflow used for expansion of the business and MarCo.

Growth will also accelerate because of the benefits of cross-sell and integration into the stack, thus leading to higher profitability and more free cash generation.

So far, we have not even factored the benefits of expanding the market size by shifting the AdWaste.

Taken together, this can create a very powerful flywheel for growth – just like what Constellation Software has done.

Thinks 1174

Mint: “The time that the salesperson spends with us in a physical shop, patiently showing various options, does impact our shopping behaviour. The effort of the salesperson generates a reciprocal mindset in many a shopper that makes it difficult to leave the shop without buying at least one item. There is another important thing that a salesperson will often do in a brick-and-mortar store. Savvy salespersons reduce the cognitive load on shoppers by constantly removing rejected items from their sight. They make sure that at any point of time, there are only three or four items in front of the shopper. This greatly helps the shopper to take a decision with ease. With no such human interface in a digital transaction, there is no chance for a sense of reciprocity to arise in the digital shopper. Too many choices in the digital world create confusion during decision-making. So, to mitigate the returns problem of online shopping, platforms need a deeper understanding of the non-conscious factors of brick-and-mortar shopping. These behavioural learnings could be incorporated into their software algorithms.”

Kara Swisher (in her new book): “Consider that the revenue at the Times, widely considered to be the gold standard in making the digital transition and transformation, was $2.4 billion in 2023, while Facebook clocked in at $135 billion. Oh. Yes. That. There are better paths for all of us, for the health of our democracy and to restore our sense of truth and social cohesion, than allowing the angriest and loudest and most nonsensical voices on social media (and I am not just talking about Musk, but him, yes, perhaps most of all right now). Which is why we need to continue to press our elected leaders for guardrails for tech to limit its unaccountable power and put in place reasonable protections around a range of inventions that have the potential to cause more harm. My digital journey in media has been a long one, and perhaps it’s okay that we had to be destroyed — or nearly so — to become something else. What I am certain of is we don’t have to be yet another meal for big tech to Google, oops, gobble up.”

strategy+business: “Foundation models are an excellent tool for interacting with large volumes of information; generating content, reports, and code; and augmenting and automating tasks. Because their capabilities are so wide-ranging, foundation models can serve as the basis for creating more focused AI solutions via a small amount of refinement, which reduces development time and cost. Hence the name: they are the foundations on which many bespoke AI systems are built. Foundational models that are coupled with enterprise knowledge, augmented with interfaces to simplify use, and paired with prompts to generate consistent outputs are poised to revolutionize how we work, live, and interact. Foundation models may be most useful in helping with business problems if they are equipped with specific business context and information to narrow the potential range of responses.”

WSJ: “In the future, there will be fewer meetings and they’ll go faster, in large part due to a new corporate concept: pregaming. Colleagues will add their thoughts, ideas or feedback on the set agenda for a planned meeting to a shareable online document at least a week prior. Doing so, companies can reduce the number of meetings by 30%, says executive coach and author Keith Ferrazzi. As a result, more workers will have a chance to express their thoughts, he says. In a traditional meeting, “some people aren’t as effective in the spur of a moment in a room. Some people are talked over, maybe because they are women, or they are a minority. For whatever reason, some people just don’t get a shot,” says Ferrazzi. This method assumes everyone will feel comfortable putting their thoughts in writing with their names attached. Ferrazzi advises clearly communicating to employees beforehand the benefits of contributing to the shareable document, mainly that it enhances the chance of diverse views being heard on important corporate decisions. Time will get saved because there will be no need for the obligatory information update that typically starts a meeting, says Ferrazzi. With that info already in a one-page document accompanying the editable document, participants can just cut to the chase. Fewer people would have to attend since they have already weighed in.”

Wanted: A Constellation Software for Martech (Part 4)

Consolidation

Martech has become a crowded space with many companies facing an existential crisis because funds have dried up and marketing spends from businesses have reduced. Some will die, others will get sold to either PE firms or larger marketing cloud or enterprise software companies. This Darwinian process of natural selection will ensure only the best survive.

This assumes a given current market size for martech software. What if this market could be grown by many times? That may still not guarantee survival of everyone, but it could open new opportunities for growth for many companies. Some costs are common across companies – especially in marketing and sales. Buyers, especially in the mid-market, would prefer a more unified stack than spending money on integrating different point solutions. A simpler tech stack will also ensure data is not siloed enabling AI models to work better. While roll-ups of smaller martech vendors by the bigger ones is an obvious solution (and is already happening), the diversity of B2C/D2C/eCommerce/retail creates opportunities for a larger universe of companies under one roof. Exactly the way Constellation Software has done for vertical market software companies.

The opportunity in martech comes from rethinking the size of the pie. As I have explained in previous essays, about half the spending on digital advertising is being wasted. Businesses spend about 80% of their budgets on acquisition (adtech), 10% on branding, and 10% on CRM (retention and growth of existing companies, the world of martech). As I wrote in Nucore: A Thought Experiment [LINK]: “The global eCommerce industry generates trillions of dollars in revenue. Email is one of the key enablers for customer engagement, conversion, and retention. Yet, its size is in single-digit billion dollars. Add all the other engagement channels and martech solutions, and the figure will go to maybe $50 billion. Compare that with adtech, which powers new customer acquisition. Global spending on digital advertising platforms is expected to be $500 billion. In other words, even as the adtech industry makes 10 cents of every dollar of revenue that ecommerce generates, the CPaaS and martech industry generates just 1 cent.” My estimate is that about half of the money spent on adtech is being wasted on wrong acquisition and reacquisition. Half of $500 billion comes to $250 billion. This is AdWaste.

Until recently, it was very difficult to solve for AdWaste because it was not easy for marketers to build deep relationships with existing customers. Now, several tech and business model innovations like Unistack, Channels 2.0, and Progency can help tilt the scales towards retention and growth rather than continuous acquisition.

The AdWaste thus becomes the fuel for martech companies to tap with innovations to solve the allied problems of siloed data and funnel friction (besides that of marketing waste). Only by shifting the adtech budgets to martech will martech companies multiply their addressable market. A byproduct will be an increase in profitability for digital businesses, especially those which are consumer-facing. This will create the flywheel for value creation in martech.

The question is: how to unlock this opportunity and create a Constellation Software for martech? My answer: MarCo – a Martech Consolidator, which acquires, manages, and builds martech software.

Thinks 1173

WaPo: “Buying planes and maintaining them is fantastically expensive. The industry is heading into its 110th year of not earning back its capital costs. Even profitable airlines tend to careen between single-digit profit margins and periods of epic economic disaster. Moreover, there are only three ways to make their investments more profitable: fly each plane more often, put more people in each plane or increase what you charge passengers per flight. The first is hard to do, though airlines constantly look for ways to reduce turnaround time. The second is the reason they pack us in like sardines. And the third is the reason they let us buy our way out of sardine class: They get more money from the same number of passengers.”

Bloomberg: “If India wants to build a robust computer and electronics manufacturing industry, it needs to shift focus, fast. Instead of concentrating on the domestic market, it should become regionally competitive and export- driven. That means recognizing that Vietnam, not China, is its biggest rival…For India to succeed, it needs to start thinking outward, which means understanding that the investment and business environment there isn’t competitive. Research shows that for more than 85% of the tariff categories within electronics, India’s duties are higher than each of China, Mexico, Thailand and Vietnam.”

Jennifer Burns: “Friedman simply did not believe policy-makers could accurately grasp what was happening in the economy, respond in a timely fashion, and correctly anticipate the outcome. Instead, his countervailing vision focused on stable monetary growth as the government’s chief responsibility toward economic life. Beyond that, allocation and exchange should be governed by prices, pulsing through the economy as signals of countless faceless exchanges. Prices couldn’t play favorites. Prices couldn’t be lobbied.” [via CafeHayek]

Cory Doctorow: “So what’s enshittification and why did it catch fire? It’s my theory explaining how the internet was colonised by platforms, why all those platforms are degrading so quickly and thoroughly, why it matters and what we can do about it. We’re all living through a great enshittening, in which the services that matter to us, that we rely on, are turning into giant piles of shit. It’s frustrating. It’s demoralising. It’s even terrifying. I think that the enshittification framework goes a long way to explaining it, moving us out of the mysterious realm of the “great forces of history”, and into the material world of specific decisions made by real people; decisions we can reverse and people whose names and pitchfork sizes we can learn…et’s examine how enshittification works. It’s a three-stage process: first, platforms are good to their users. Then they abuse their users to make things better for their business customers. Finally, they abuse those business customers to claw back all the value for themselves. Then, there is a fourth stage: they die.”

Wanted: A Constellation Software for Martech (Part 3)

Constellation Software – 2

I asked ChatGPT for a summary of Constellation Software’s strategy:

  1. Focused Acquisition Strategy: Constellation Software has a highly focused approach to acquisitions, targeting vertical market software (VMS) companies. These companies often provide specialized software solutions for specific industries, which tend to have stable, recurring revenue streams and high customer retention rates.
  2. Decentralized Management: Post-acquisition, Constellation Software maintains a decentralized management structure, allowing its acquired companies to operate independently. This autonomy encourages the entrepreneurial spirit of the acquired companies, fostering innovation and operational efficiency while benefiting from the resources and stability of a larger parent company.
  3. Disciplined Financial Approach: The company is known for its disciplined approach to acquisitions, emphasizing cash flow, profitability, and sustainable growth. Constellation Software carefully evaluates potential acquisitions to ensure they meet strict financial criteria, which helps in maintaining overall financial health and stability.
  4. Long-Term Growth Focus: Constellation Software focuses on long-term value creation rather than short-term gains. This long-term perspective guides its acquisition strategy, investment in product development, and customer service, contributing to sustained growth and profitability.
  5. Market Niche Specialization: By focusing on niche markets, Constellation Software mitigates competition from larger software companies. This specialization allows for a deeper understanding of customer needs, leading to the development of highly tailored solutions and stronger customer relationships.
  6. Continuous Innovation and Customer Focus: Despite its acquisition-driven growth model, Constellation Software remains committed to innovation and customer satisfaction within its individual business units. This ensures that products stay relevant and continue to meet the evolving needs of their specific markets.
  7. Scalable Business Model: The company’s business model is designed to be scalable, enabling efficient integration of new acquisitions and leveraging synergies across its portfolio of companies. This scalability is key to managing a large and diverse portfolio of software businesses.
  8. Talented Management and Operational Excellence: Constellation Software has a strong leadership team and places a high emphasis on operational excellence. It attracts and retains talented management teams within its acquired companies, ensuring best practices in software development, sales, and customer support.

These two graphics from The Generalist capture the essence of its model.

As The Generalist puts it: “In almost every respect, Constellation Software is an abnormal business. Founded by a disgruntled gravedigger-turned-venture-capitalist, Constellation is a PE firm that never exits, a compounder that buys its growth, a fine-tuned conglomerate with minimal management, and a culturally defensible business skeptical of the very notion. More than a company, it is a teeming ecosystem of entities, each with distinct personalities and ambitions. And yet, each element serves to help the whole thrive.”

Additional resources: