Thinks 1244

Mark Zuckerberg on AI: “I think it’s going to be pretty fundamental. I think it’s going to be more like the creation of computing in the first place. You’ll get all these new apps in the same way as when you got the web or you got mobile phones. People basically rethought all these experiences as a lot of things that weren’t possible before became possible. So I think that will happen, but I think it’s a much lower-level innovation. My sense is that it’s going to be more like people going from not having computers to having computers. It’s very hard to reason about exactly how this goes. In the cosmic scale obviously it’ll happen quickly, over a couple of decades or something. There is some set of people who are afraid of it really spinning out and going from being somewhat intelligent to extremely intelligent overnight. I just think that there’s all these physical constraints that make that unlikely to happen. I just don’t really see that playing out. I think we’ll have time to acclimate a bit. But it will really change the way that we work and give people all these creative tools to do different things. I think it’s going to really enable people to do the things that they want a lot more.”

From Michael Crichton’s 1995 “Jurassic Park” sequel “The Lost World”: “It means the end of innovation,” Malcolm said. “This idea that the whole world is wired together is mass death. Every biologist knows that small groups in isolation evolve fastest. You put a thousand birds on an ocean island and they’ll evolve very fast. You put ten thousand on a big continent, and their evolution slows down … And everybody on Earth knows that innovation only occurs in small groups. Put three people on a committee and they may get something done. Ten people, and it gets harder. Thirty people, and nothing happens. Thirty million, it becomes impossible. That’s the effect of mass media — it keeps anything from happening. Mass media swamps diversity. It makes every place the same. Bangkok or Tokyo or London: there’s a McDonald’s on one corner, a Benetton on another, a Gap across the street. Regional differences vanish. All differences vanish. In a mass-media world, there’s less of everything except the top ten books, records, movies, ideas. People worry about losing species diversity in the rain forest. But what about intellectual diversity — our most necessary resource? That’s disappearing faster than trees. But we haven’t figured that out, so now we’re planning to put five billion people together in cyberspace. And it’ll freeze the entire species … Everyone will think the same thing at the same time. Global uniformity.” . This is via Ross Douthat, who writes: “I think there’s hope of escape from the Crichton prophecy. But if we don’t escape, these will be the terms of our imprisonment: a wired-together environment that freezes us in place while being so perpetually stimulating and distracting that only the dropouts and the despairing notice what’s really going on.”

Shang-Jin Wei on India’s growth story: “Implementing sweeping anti-corruption reforms is a crucial first step. Over the medium and long term, India must invest in better infrastructure, raise education standards, and empower women to participate in the labour force. Achieving all this will not be easy. But without progress in these areas, India will not be able to live up to the hype and become the world’s next economic superpower.”

WSJ: “Today’s kids roam less than in earlier generations. Overscheduling and parents’ safety fears are part of the reason, but it’s also true that American suburbs built in the past 30 years are less walkable and bikeable than older neighborhoods. Walkability is seen mainly as a concern for urbanites, who want to be able to stroll to a cocktail bar, grocery store or museum. But walkability in suburban neighborhoods is a far more important issue. It requires building sidewalks, bike trails, playgrounds and crosswalks that are safely usable by kids. We know that is possible because much of the world already does it…Kids should be walking to school by themselves. They should be riding to the corner store with their brothers and sisters and wandering the neighborhood to make their own fun. We should choose kids over cars, and thus make our world both healthier and a little more family-friendly.”

New SaaS: Services, AI Agents, Sharing (Part 8)

S+AA+S

The three ideas together become the new foundation for “New SaaS” (beyond just the cloud-based software):

  • Services: which bring in people into the product proposition to ensure continuous monitoring and improvement. This component integrates human expertise and intervention into the digital offering, enhancing the adaptability and personalisation of the software. It ensures that the product not only meets the current demands of users but also evolves proactively through continuous feedback and improvement loops. This human-in-the-loop approach guarantees that the software remains at the forefront of user needs and industry trends.
  • AI Agents: which help automate conversations, tasks, and ‘next best action’ predictions. These autonomous, intelligent systems empower the platform by automating interactions, streamlining tasks, and providing predictive insights for the customer journey. By harnessing the capabilities of AI agents, the software transcends traditional functionalities to offer more intuitive, efficient, and personalised user experiences. This not only elevates the utility of the software but also optimises user engagement and satisfaction.
  • Sharing: a “progency” business model, combining product and agency, to price based on performance and outcomes. It redefines the economic relationship between service providers and their customers. By adopting a performance-based pricing strategy, the focus shifts towards shared success and outcomes. This ensures a more aligned partnership where the contributions of the software directly impact the client’s bottom line, fostering a collaborative environment geared towards mutual growth and achievement.

The “New SaaS” can be defined as an integrated, outcome-driven ecosystem that leverages the synergistic potential of services, AI agents, and performance-based collaboration. This novel model transcends traditional software delivery by embedding intelligent, autonomous agents within SaaS platforms to automate complex tasks, personalize user experiences, and drive operational efficiencies. It further enriches the value proposition by incorporating human insights and expertise through bundled services, ensuring that the software continuously evolves in alignment with user needs and market dynamics. The incorporation of a sharing or “progency” model signifies a shift towards aligning the economic interests of SaaS providers with the tangible business outcomes of their clients, fostering a partnership model that rewards innovation, effectiveness, and shared success. Together, these elements form the foundation of the New SaaS, marking a shift from conventional software as a service to a more dynamic, interactive, and value-oriented service model.

**

There are two “New SaaS” innovations which can underpin the New SaaS model for B2C Martech: a Digital Twin for a “segment of one”, and a Co-Marketer for a “department of one”.

Digital Twin: Envision a hyper-personalised AI companion for each customer, not just mirroring their actions but also predicting future behaviours (‘next best actions’) with remarkable accuracy. This advanced AI agent delves deep into individual customer data and journeys, using AI-driven insights to foresee and shape future interactions. It dynamically engages with the brand for tasks like tracking purchases, managing service requests, and filtering offers. This embodiment of the “segment of one” philosophy leverages AI to craft unique, waste-free experiences that maximise customer lifetime value. [Also see iDarpan: How Mirror Worlds and Digital Twins will Revolutionise eCommerce.]

Co-Marketer: A brand’s marketing team can also do with some help. A lot of time is spent in repetitive, time-consuming activities like identifying segments, making creatives, running campaigns, and analysing data. AI autonomous agents can offload many of these tasks. A Progency can oversee these agents and be incentivised based on outcomes. This could enable a “department of one” where the marketer lays out the objectives and the AI-enabled Co-Marketer works on the optimisations necessary to achieve the goals.

These innovations not only exemplify the New SaaS model’s potential in revolutionising B2C Martech but also underscore the synergistic integration of Services, AI Agents, and Sharing. By harnessing these components, brands can unlock unprecedented levels of personalisation and efficiency, propelling marketing into a new era of intelligence and customer-centricity, and a big leap forward in the quest to becoming a Profipoly.

Thinks 1243

Molly White on AI: “The reality is that you can’t build a hundred-billion-dollar industry around a technology that’s kind of useful, mostly in mundane ways, and that boasts perhaps small increases in productivity if and only if the people who use it fully understand its limitations. And you certainly can’t justify the kind of exploitation, extraction, and environmental cost that the industry has been mostly getting away with, in part because people have believed their lofty promises of someday changing the world. I would love to live in a world where the technology industry widely valued making incrementally useful tools to improve peoples’ lives, and were honest about what those tools could do, while also carefully weighing the technology’s costs. But that’s not the world we live in. Instead, we need to push back against endless tech manias and overhyped narratives, and oppose the “innovation at any cost” mindset that has infected the tech sector.”

Mint: “Set up a dedicated tech committee to watch for what is coming to the market, and make that a regular part of board conversation. This assures the company a regular touch- point on tech issues and aids the entire board’s understanding of technology trends, opportunities and risks. A tech committee can have 3-4 members. It should meet quarterly and its charter could spell out a broad range of issues for monitoring, such as cyber risk, digital efforts, AI and the Internet of Things. It can start with a few items and then update the charter. Chair duties can involve working closely with the management to review matters that come up, before assuring a full readout of the minutes to the entire board.”

WSJ: “When we stress test our memories, we expose the weaknesses of existing neuronal connections in a way that ultimately strengthens what’s useful and prunes away what’s not. Rather than relearning the same material over and over—rereading the same textbook, say—it is more efficient to pinpoint the exact areas where our memory fails us, and then to update our memory with the right information. Of course, this works only if we understand where we went wrong, so we can correct for it. The point is to struggle, not to flail aimlessly.”

Vasant Dhar: “Central banks are a financial innovation of the 20th century. Over the centuries, a critical lesson we’ve learned is that politicians can’t be trusted with money. A central bank is the government’s bank, but it is staffed with expert professionals who are supposed to be independent of politics. A critical role of the central bank is to place shackles on the government, so that politicians won’t do dumb things like print money like they often did in the past, causing rampant inflation. In their book called The Narrow Corridor, political economists Daron Acemoglu and James Robinson describe how strong liberal democracies avoid despotic governments by shackling State power to ensure that the needs to the citizenry are met by credible rule-following institutions.  The role of the central bank is to shackle the government from screwing up the economic system, and to step in when necessary to maintain economic stability.”

Amartya Lahiri: “India’s demographic dividend is, however, a double-edged sword. On the one hand, it presents the country with a short window during which it will have a huge supply of young workers and human capital. On the other hand, it presents the country with a severe challenge in matching these workers to productive jobs. The labour market matching process is a challenging exercise in any country, leave alone one adding massive numbers of workers to an enormous labour pool. An additional complication to this labour market matching challenge is the ongoing transformation of India’s economy from primarily agrarian to more non-agrarian. This presents two challenges: First, people’s skills need to change in order to successfully transit from the agricultural sector to either manufacturing or services. Second, these transitions often require workers to also change location, since non-agricultural employment opportunities tend to be in urban centers far from rural India. Since migration is costly, both monetarily and socially, imperfections in the process can act like a massive handbrake for the economy.”

New SaaS: Services, AI Agents, Sharing (Part 7)

Services and Outcomes

To summarise the story so far, there are three new ideas which promise to reshape tomorrow’s software world: AI agents, services, and outcome-based pricing. We have discussed about AI agents. I will summarise my ideas about services and outcome-based pricing from my previous writings.

Bundled Kaizen Services:

[Software] Products [sold need] continuous improvement. Actions done yesterday by consumers could provide a feedback loop to make it better today. While automation and AI can drive significant enhancements in real-time, the understanding and adaptability of human intervention could elevate the product’s efficacy to new heights. By integrating a Kaizen-inspired layer of continuous and deliberate refinement, [sellers can] not only anticipate and adapt to the evolving needs of [their] customers but also carve out a distinct competitive edge. The Kaizen approach would transcend the conventional boundaries of SaaS offerings, transforming [the] product into a dynamic, ever-improving solution uniquely attuned to deliver unparalleled value and performance to…customers.

…By deliberately weaving human expertise into the fabric of the offering, SaaS platforms not only enhance the intrinsic value of the product but also redefine the paradigm of customer engagement and satisfaction. In doing so, they can not only bridge the gap between product potential and practical application but also pave the way for a new era of SaaS solutions, where the synergy between software and service elevates the efficiency and impact.

…This hybrid model combines product innovation with a services component, addressing the gap between product features and their utilisation while enhancing customer engagement and satisfaction. The proposition is to embed the services cost into the product pricing, making it more attractive compared to US-based competitors, potentially leading to significant savings for clients and a stronger competitive position for Indian SaaS companies.

Profishare:

Profishare is a concept that goes beyond the existing paradigms of selling software or services. Instead, it proposes a partnership model where software companies actively participate in the success of their clients’ businesses.

Under Profishare, a software company would generate new revenue streams by contributing directly to the incremental profits of their clients. Rather than charging a fixed fee or a standard subscription, the company would take a percentage of the additional profits generated as a result of using its software. This model creates a powerful alignment of interests, ensuring that the software company is directly invested in the success of its clients.

A practical example of this model could be seen in a “Martech Progency” – a hybrid of a product-led company and an agency. In this setup, the software company acts as both a product developer and a strategic partner. It provides not only the software but also the expertise and support to ensure that their clients can fully leverage the technology to improve their business performance.

…there’s a significant opportunity for martech companies to leverage AdWaste and transform their pricing models to be outcome-based. This approach aligns with the current market dynamics where brands are seeking more effective and accountable marketing spend, moving away from traditional adtech’s inefficient customer acquisition strategies to martech’s customer retention and revenue growth capabilities. The integration of performance-based pricing in martech could lead to more efficient use of marketing budgets, better engagement with existing customers, and ultimately, a more sustainable and profitable marketing ecosystem.

Thinks 1242

Rahul Matthan: “Now that AI is widely accessible, we all need to figure out how best to leverage AI so that we can address the inefficiencies that hold us back. What shape that will take, what it will actually do for us and how will surely differ for each of us, specifically suited to our individual ways of working. But one thing is clear: It is only those who learn to use AI most effectively who will have an advantage in a world where AI could become as ubiquitous as electricity.”

FT: “As I think back to the origins of service culture, to the close relationship between the customer spending money and the independent shopkeeper who has hit on a formula that keeps people coming back to spend more, I wonder, “How hard can it be?” Bosses cannot and should not rely on technology or statistics to do the job of telling them about the customer experience. They should regularly be “on the shop floor” (or in the contact centre or with the tech team) listening to staff and customers, asking questions and understanding precisely where they’re able to delight us, and frustrate us. In an online world, the need to make these human connections becomes more vital…Investing in customer service has proven benefits, but I fear it will take a while for the penny to drop. The best organisations will have someone on the board whose job title is customer service, but the ones who really need to improve are unlikely to do so. So let’s all resolve to make shoddy service a board-level problem by being more active with our custom.”

Laura Martin: “Once you’ve figured out your productivity patterns, you can narrow down what I call your “power hours”—the two to three hours a day when you feel most productive at focused, strategic work. It would be a real waste to spend those hours in low-energy meetings…If you sit down at your desk to do something and you’re thinking, “ugh!” it’s probably not the best time to do it. You want to feel like you’re floating downstream, not paddling against the current. Give yourself permission to rearrange your schedule, which often means tackling the toughest jobs when you’re best equipped for them.”

Economist: “Studios are reworking games and finding commercial and critical success. Last year “The Super Mario Bros” was the second-highest-grossing film at the worldwide box office. “The Last of Us”, a TV show based on a PlayStation game, won a haul of Emmy awards in January. More game adaptations are on the way: IGN, an entertainment website, counts more than 70 games in development for film or TV, including shows based on “Tomb Raider” and “League of Legends” and films based on “Zelda” and “Minecraft”. What explains the enthusiasm for these game-shows? One reason is that Hollywood’s favourite source of creative material, comic books, is getting boring. For two decades the box office has been ruled by superheroes. But more recently each Marvel film has seemed to be less successful and lauded than the last. “The Marvels”, released in November, was the lowest-grossing so far. Games offer an alternative: “A deep well of franchises, a built-in audience, years of storylines and endless spin-off franchise possibilities,” says Fred Black of Ampere Analysis, a research firm.”

Samiran Ghosh: “Commercial inclusion [in India] is as important as financial inclusion for true abundance to become a reality. We remain a country of fragmented micro-economies with high transaction costs. Only 5-6% of about 100 million MSMEs sell their wares on digital platforms. Ride-hailing serves account for less than 6 million of 100 million-plus daily public trips. Despite modern technology, 87% of retail is still unorganized and digital inclusion is just 7% of the market. This is so for most of the world.”

New SaaS: Services, AI Agents, Sharing (Part 6)

Sierra.ai

A pioneering company in the space of AI agents is Sierra.ai. “Agents are autonomous, AI-powered software systems that can interact directly with consumers to solve problems and take action on their behalf. The concept of an agent has its roots in academia, but for consumer brands, agents represent something simple: an opportunity to create an always-on, delightful, conversational customer experience for everything from support to retail, recommendations, subscription management, and more…Sierra’s conversational AI platform enables your company to tailor next-generation AI to your business and customers. With Sierra, you can enable your customers to get answers, solve problems, and take action through a conversational experience.”

DigitalDaze: “[Sierra’s] virtual assistants aim to streamline customer service, enabling rapid resolution of issues and facilitating task completion seamlessly…[Its] autonomous AI agents exhibit a high degree of operational independence. They integrate sophisticated systems capable of understanding and responding to customer inquiries in real-time. This distinct feature sets them apart, facilitating their ability to solve customer issues independently, without requiring human intervention…Sierra’s AI agents not only provide answer-based assistance, but they are also equipped to execute tasks at the customer’s request. Whether it’s managing subscriptions, booking flights, or making reservations, these AI agents bulldoze through mundane tasks, offering easy, swift, and seamless experiences…Providing personal attention to each customer traditionally demands human bandwidth. Sierra, however, leverages AI technology to transcend this limitation. With the capacity to engage multiple customers simultaneously without compromising the quality of response, Sierra’s AI agents manage customer engagement on an unprecedented scale.”

Techcrunch: “Sierra, the new startup from Bret Taylor and Clay Bavor, thinks that AI agents could be the next technology frontier, not unlike websites or mobile apps that came before them: essential digital assets for every company, and ones that could ultimately deliver on the promise of digital customer experience. Whether or not that’s true, the two founders fundamentally see AI agents as a new technology category, providing an entirely new way for customers to interact with brands to improve their overall experience. “Our thesis is really simple. We think that conversational AI will become the dominant form factor that people use to interact with brands, not just for the sort of current trends like customer service, but really for all aspects of the customer experience,” Taylor told TechCrunch…This new wave of AI will generate at least five to 10 meaningfully new independent enterprise software companies, Taylor said, not unlike when cloud and mobile came along. “There’s an opportunity for a new technology model. There’s no market leader in conversational AI right now because it’s new. It’s a year old, if that, and so, everyone’s figuring this out in real time,” he said…The founders also think a new platform should have a new approach to pricing, and they have designed an entirely new pricing model based on outcomes. Instead of tiered subscription fees or usage-based pricing we’ve seen with other software companies, they want customers to pay only for outcomes, when a problem is resolved. “We think outcome-based pricing is the future of software. I think with AI we finally have technology that isn’t just making us more productive but actually doing the job. It’s actually finishing the job,” Taylor said.”

From LinkedIn News:

Clay Bavor:If you look back over the last 30 years, every time there’s been a sea change in technology, it’s enabled businesses to interact with their customers in new ways. The internet enabled businesses to set up digital storefronts in the form of websites. Social networks enabled businesses to interact directly with their consumers via their profiles. Smartphones made it possible to engage much more directly with push notifications and mobile apps. The way businesses are going to interact with their customers in the future is not going to be the website or an app, it’s going to be having a conversation. If in 1995 you needed a website, in 2025 you’ll need an AI agent.”

Bret Taylor: “We believe that software is moving from being rule-based to being based on goals and guardrails, which is a very different way of building with large language models. Our AI agents can achieve basic human-level reasoning, like how to achieve a goal. So, for example, it can ask follow-up questions if you’re executing a return and actually reason about it — like is it within the return policy window?  Underlying this is autonomous agents, the idea of using AI systems for reasoning.

Fortune: “A typical agent based on Sierra’s technology uses four or five different AI models when it receives a message from a user – one of the models might generate a response, for example, while another model might be tapped to prevent hallucinations. Sierra uses a mix of proprietary and open source large language models, including frontier models from OpenAI and Microsoft that are tweaked by their team of researchers to fit a customer’s use case. The company trains its AI models to reason and make decisions by giving them specific goals and guidelines, similar to how a person might follow rules for their job. This approach allows them to onboard new customers quickly without needing a lot of their data, [Bret] Taylor said, and he believes this sets them apart because they can adapt to new policies or changes in a customer’s needs much faster than traditional AI models, which might take weeks or months to update.”

Wired: “To build its bots in a way that accomplishes that task effectively, pleasingly, and safely, Sierra had to concoct some innovations that will advance AI agent technology in general. And to tackle perhaps the most worrisome issue—hallucinations that might give customers wrong information—Sierra uses several different AI models at once, with one model acting as a “supervisor” to make sure the AI agent isn’t veering into woo-woo territory. When something is about to happen with actual consequences, Sierra invokes its strength-in-numbers approach…Because of the power, the vast knowledge, and the uncanny understanding of AI’s powerful large language models, these digital agents can grasp the values and procedures of a company as well as a human can.”

Thinks 1241

Biju Dominic: “In the traditional advertising industry, the creative brief was a well-thought-through document that was prepared after much research and discussions among the strategic minds both at the client’s end and within its advertising agency. A creative brief contained all the important elements needed to make a good advertisement: unique human behaviour insights, brand guidelines, the key response required from the particular campaign or ad, and so on. A close understanding of this brief is what guided human creative teams in developing various creative stimuli to generate the appropriate response from the target consumer. If GenAI is to take charge of advertising, the crucial role played by the creative brief in the traditional ad industry will have to be taken over by an effective prompt strategy. It will quickly be found that prompting cannot be a rational process managed by tech engineers. The prompt strategy would have to be developed by human behaviour and design experts tasked with getting GenAI to explore the depths of behaviour that qualitative research has not yet reached. The prompt strategy would then be the big differentiator in the brand’s Gen AI game-plan.”

WaPo: “How did life on Earth begin? Now, scientists at Ludwig Maximilian University of Munich have taken an exciting step forward by showing how more complex molecules crucial for life could have been synthesized from early Earth’s basic ingredients. In their study, published in the journal Nature, the scientists swapped test tubes for tiny networks of branching cracks that resemble those that naturally form in rocks. They flowed water through the cracks, along with key chemical building blocks, then applied heat, mimicking a process akin to what might happen near hydrothermal vents in the ocean or in porous rocks near a geothermal pool. They discovered that the heat flowing across these geologic networks sorted and filtered molecules, helping them create longer chains called biopolymers that are essential for life.”

FT: “Games are now huge business: while the fiction books market is thought to be worth around $11bn globally, the worldwide gaming market truly dwarfs it — projected to reach revenues of over $280bn this year, growing at nearly 9 per cent annually. Research suggests that it is not far off generating as much revenue as publishing and filmed entertainment combined…With immersive storylines and powerful, emotive writing, some of the most thrilling fiction out there is being created in game form.”

NYTimes: “Whether and how ardently governments should try to control their economies has been vigorously debated since the Industrial Revolution. The current wave of policies, though, is a stark contrast to the classic open markets, hands-off government ideology championed by the citadels of capitalism in recent decades. That faith in the superiority of free-market policies was deeply shaken in recent years by a string of global jolts — the pandemic, supply chain meltdowns, soaring inflation and interest rates, Russia’s invasion of Ukraine, and rising tensions between the United States and China. In many capitals, security, resilience and self-sufficiency were pushed to the front of the list of economic policy goals along with growth and efficiency.”

Tyler Cowen: “What do Presidents Javier Milei of Argentina and Nayib Bukele of El Salvador — as well as UFC champion Renato Moicano — have in common? They all admire an obscure libertarian economist [Mises]…That is an impressive comeback for Mises, who died in 1973 without ever receiving mainstream acceptance in academia. After emigrating to the US in 1940, he retired as a visiting professor in 1969. Yet as of this writing he has three titles on Amazon’s list of the 10 best-selling economics books. The (relative) rise of Mises has occurred both among the mainstream and within free-market circles. Externally, many countries in Latin America have been seeing their prosperity slip away. Argentina has been known since Peronist times for its poor economic performance, but more recently the decay has become more obvious. When I visited Buenos Aires last year, it was dirtier, poorer and more ill-tempered than when I visited in 2006. The country remains in the midst of a hyperinflation. Whether or not you agree with Milei’s policies, it should not be a surprise that the electorate has turned to radical remedies, including ideas from Mises and other libertarian economists.”

New SaaS: Services, AI Agents, Sharing (Part 5)

AI Agents – 3

I then asked ChatGPT about how AI agents can combine with SaaS.

AI agents can combine with Software as a Service (SaaS) to create more dynamic, intelligent, and responsive applications, enhancing both the functionality of the software and the value it delivers to users. This integration leads to a new generation of SaaS offerings where AI-driven autonomy, personalization, and efficiency are at the forefront. Here’s how AI agents can be integrated with SaaS:

Personalization: AI agents can analyze user data and behavior to tailor the SaaS experience to individual users or businesses. By understanding user preferences, habits, and needs, the software can adapt its functionality, recommendations, and content to offer a more personalized service.

Automation of Complex Tasks: AI agents can automate complex or repetitive tasks within SaaS applications, freeing users to focus on more strategic activities. This includes everything from data entry and analysis to more sophisticated decision-making processes, based on the AI’s learning and adaptation capabilities.

Enhanced Decision Support: Integrating AI agents into SaaS applications can provide users with advanced decision support by analyzing large datasets, identifying patterns, and suggesting actions. For example, in a business intelligence SaaS, AI can help predict market trends and recommend business strategies.

Real-time Adaptability: AI agents can enable SaaS applications to respond in real-time to changes in data or the environment. This is particularly useful in dynamic fields like stock trading platforms, where conditions change rapidly, and the software must adapt quickly to remain effective.

Improved Customer Support: SaaS platforms can use AI agents as intelligent virtual assistants to offer 24/7 customer support, answering queries, solving common problems, and providing personalized assistance based on the user’s history and preferences.

Predictive Maintenance: In SaaS applications that manage physical assets or IT infrastructure, AI agents can predict when maintenance is needed, reducing downtime and operational costs. By analyzing historical data and identifying patterns that precede failures, the software can alert users to potential issues before they become critical.

Enhanced Security: AI agents can enhance the security of SaaS applications by continuously monitoring for suspicious activities, identifying potential threats, and taking proactive measures to mitigate risks. This dynamic approach to cybersecurity can adapt to new threats more quickly than traditional, rule-based systems.

Scalability and Efficiency: By automating and optimizing tasks, AI agents can help SaaS platforms scale more effectively, supporting a larger number of users or transactions without a proportional increase in resources or costs.

Integration and Interoperability: AI agents can facilitate the integration of different SaaS platforms, allowing them to communicate and share data more effectively. This can create more cohesive ecosystems of applications that work seamlessly together, enhancing overall functionality and user experience.

In summary, the combination of AI agents with SaaS represents a significant evolution in the software industry, offering more adaptive, intelligent, and personalized services that can drive higher value and efficiency for businesses and end-users alike.

Thinks 1240

FT: “OpenAI’s latest artificial intelligence model has almost matched expert doctors in analysing eye conditions, according to research that highlights the technology’s potential in medicine. The Microsoft-backed start-up’s GPT-4 model surpassed or achieved the same scores as all but the top-scoring specialist medics in assessing ocular problems and suggesting treatments, according to a paper published on Wednesday. Ophthalmology has been a big focus of efforts to put AI to clinical use and fix obstacles to take-up, such as the tendency of models to “hallucinate” by creating fictitious data. “What this work shows is that the knowledge and reasoning ability of these large language models in an eye health context is now almost indistinguishable from experts,” said Arun Thirunavukarasu, the lead author of a paper on the findings published in PLOS Digital Health journal.”

Economist: “While some model-makers race for more resources, others see signs that the scaling hypothesis is running into trouble. Physical constraints—insufficient memory, say, or rising energy costs—place practical limitations on bigger model designs. More worrying, it is not clear that expanding context windows will be enough for continued progress. Yann LeCun, a star AI boffin now at Meta, is one of many who believe the limitations in the current AI models cannot be fixed with more of the same. Some scientists are therefore turning to a long-standing source of inspiration in the field of AI—the human brain. The average adult can reason and plan far better than the best LLMs, despite using less power and much less data. “AI needs better learning algorithms, and we know they’re possible because your brain has them,” says Pedro Domingos, a computer scientist at the University of Washington. One problem, he says, is the algorithm by which LLMs learn, called backpropagation. All LLMs are neural networks arranged in layers, which receive inputs and transform them to predict outputs. When the LLM is in its learning phase, it compares its predictions against the version of reality available in its training data. If these diverge, the algorithm makes small tweaks to each layer of the network to improve future predictions. That makes it computationally intensive and incremental.”

The Generalist: “Listen for the problem, not the solution. To build a great business, you have to develop genuine customer obsessiveness. But while listening to your users is essential, you shouldn’t expect them to have the perfect solution to their issue. Rather than implementing what a customer asks for directly, founders should think about addressing the root problem from first principles. By doing so, you’re likely to end up with a more powerful and valuable product.”

Business Standard: “The poor rates of growth and the fact that a large chunk of poor urban and rural India is switching to free TV are indicative of something…Prices of smartphones — the primary mode of entry into the internet for a large section of Indians — continued to rise on the back of a chip shortage. An average feature phone is less than Rs 1,200. The cheapest smartphone is Rs 5,500 and above. The gap of Rs 4,000 was too wide for many parts of India. That is why organic growth (from feature phones to smartphones) has slowed for almost three years. Even while Apple’s iPhone continued to do well, brands like Realme and Xiaomi that offer phones at the mid and lower end of the market have seen sales fall. Going by the IDC data in a country of 1.4 billion people, roughly 650 million, or only half, have a smartphone — read that as access to the internet. In the last part of 2023, the action in the second-hand market for smartphones has revived it somewhat. According to the Trai’s last available numbers for September 2023, broadband subscribers have risen at a healthier pace. The consumption story on entertainment will take some time to reach a happy ending.”

Raghu Raman: “The key differentiator of these world-leading conglomerates is that they genuinely encourage alternative thinking using three strategies. The first is establishing a structured outlier recognition programme that seeks to identify, empower and reward such individuals and create the initial set of change agents. Next is to create a culture of experimentation where success is measured by what was learnt, rather than whether the experiment was successful. This requires creating frameworks like hackathons, innovation labs and brainstorming off-sites, and investing in people, ideas and projects that are different from the norm. The third step is to make the rubber meet the road by implementing an outcome-oriented mindset. This involves transitioning from measuring outputs to evaluating outcomes in assessing the success of outlier-driven initiatives. This shift entails looking at the big picture aligned to the organization’s future objectives and emphasizing the impact of outlier ideas on those ambitions. Metrics like ‘speed of trust,’ business velocity and strategic capacity building are benchmarks to gauge the effectiveness of such projects. Furthermore, teams are constantly encouraged to set audacious goals and given a free hand to deliver on them.”

New SaaS: Services, AI Agents, Sharing (Part 4)

AI Agents – 2

I asked ChatGPT (!) to provide an overview.

Autonomous AI agents are intelligent systems capable of making decisions and performing actions independently in their environment without human intervention. These agents combine various fields of AI, including machine learning, natural language processing, and robotics, to perceive their surroundings, interpret data, make informed decisions, and act upon those decisions to achieve specific goals or tasks.

How They Work:

  1. Perception: Autonomous AI agents start by perceiving their environment through sensors or data input. This can include everything from visual data captured by cameras, textual data from the internet, or any other form of data relevant to the agent’s tasks.
  2. Decision Making: After perceiving their environment, these agents process the information using AI and machine learning algorithms to make decisions. This process often involves analyzing patterns, predicting outcomes, and making choices that align with predefined objectives. Advanced agents might use deep learning, reinforcement learning, or other sophisticated AI techniques to improve their decision-making over time through experience.
  3. Action: Once a decision is made, the autonomous agent takes action to influence its environment or achieve its goals. This could involve physically manipulating objects (in the case of robots), executing a software function, or communicating with other systems and agents.
  4. Learning: Many autonomous AI agents have the capability to learn from the outcomes of their actions. Through techniques like reinforcement learning, they can improve their performance over time, adjusting their decision-making processes based on the success or failure of previous actions.

Applications:

  1. Autonomous Vehicles: Self-driving cars and drones that navigate and make decisions based on real-time data about their environment, such as traffic conditions, obstacles, and regulatory compliance.
  2. Smart Home Devices: Devices that manage home environments, like smart thermostats and security systems, adjusting settings based on user behavior patterns or external conditions.
  3. Healthcare: Robots or virtual agents that assist in surgeries, patient monitoring, and personalized healthcare plans, making decisions based on patient data and medical knowledge.
  4. Customer Service: Chatbots and virtual assistants that handle customer inquiries, provide personalized recommendations, and resolve issues autonomously, improving over time through interactions.
  5. Finance: AI agents in trading and investment platforms that analyze market data, predict trends, and autonomously make buying or selling decisions to maximize returns.
  6. Manufacturing and Logistics: Robots and systems that autonomously manage inventory, handle materials, and optimize production lines and supply chains for efficiency and reduced downtime.
  7. Environmental Monitoring: Agents deployed to monitor and respond to environmental conditions, like forest fire detection systems that analyze satellite imagery to detect fires early and coordinate response efforts.

Autonomous AI agents represent a significant advancement in AI, offering the potential to automate complex tasks, enhance efficiency, and provide intelligent, personalized services across various industries.