New SaaS: Services, AI Agents, Sharing

Published May 21-30, 2024

Background – 1

The growth of SaaS (software as a service) has been one of the big stories of the past 10+ years. A few weeks ago, I discussed how Indian SaaS companies could offer Bundled Kaizen Services to gain an advantage over their US counterparts. A few months ago, I discussed how “Profishare” could become a new business model for enterprise. In this series, I will add another angle: AI-driven autonomous agents. Taken together, they herald a new era for SaaS – one which goes beyond just providing software from the cloud.

Two X threads by Manav Shah set the foundation. The first thread discusses how Indian IT services could be disrupted:

India exports a combined $250B of software a year. Out of which over $240B is pure play IT Services (well it’s a lot more than just ‘IT’ or ‘Services’)
For the past 50 years, business & IT outsourcing has primarily been focused on staff augmentation & increasing the total number of human hours billed. While this was massively successful; we feel that with the advent of generative AI, and everything that gets unlocked with it; the broader outsourcing space across IT & BPOs will get disrupted.
We have an entire industry of $240B+ to help large scale enterprises realize value/ get a return on their software procurement purchase & broader digital relevance.
The needs of an enterprise are super nuanced, and things like regional nuances, taxes, returns, policies all need to be baked in and hence you need a specialized provider who can take these tools and more and deliver a fully baked solution on the other end. And this is where the industry comes in.
The pace at which enterprises have been trying to implement AI is even faster than cloud, and the skill required to do so is not as simple, leaving a small sliver for a new entrant to get in and create a large scale business.
The biggest change we feel is going to be a tectonic shift from selling services, to selling work & outcomes. We see a huge potential for new entrants that are focusing on leveraging product & AI to deliver outcomes across industries & across service lines.

This graphic by Manav show the opportunity for IT Services:

The second thread builds on this thinking:

Up until now, we have been looking at our world of B2B software as a split of software and services. And we feel this is where the largest shift lies.
I think what the future holds is going to be fundamentally different, an amalgamation of software + services + AI agents Companies that will focus on selling outcomes & not just one piece of the puzzle.
This change is being unlocked, like all previous changes, by a massive infrastructural push. Historically all customer level changes have been powered by huge transformations at the underlying infrastructure level We believe that Foundational models are the biggest infrastructure shift we have ever seen.
As a consequence we might also see a shift from a traditional seat based/ usage based/ billing man-hours, to selling outcomes & work.

Background – 2

Manav pointed me to two interesting columns. Decibel VC writes about “Service as Software, powered by AI Agents”:

For every dollar we spend on software, we end up spending 1.5x times more on IT services to get that software operational and successfully deployed. This includes areas like BPO, outsourcing and consulting, which take up most of that extra cost. You could argue that that number is potentially even understated since a lot of companies use FTEs to do the manual work around tuning, maintaining, integration and operational work. Bain & Company suggests that around 37% of IT tasks could be automated using genAI.

…With the rapid innovation around AI Agents, software applications as we know them are in process of getting a major upgrade. Agents are programs that can make decisions or perform actions based on its environment, user feedback or experiences. In short, they mimic the subtle human behavioral characteristics that make us humans quite effective at taking actions or fulfilling tasks. What this means in practice is that instead of software simply being delivered to us as a service, agents and LLMs will power the service to be delivered to us in the form of software. Thereby this ushers in the Era of Service-as-Software.

… these agents to truly be disruptive and enduring—ready to be deployed at scale—they must be built with a vertical-first and maybe almost role based first strategy (and potentially scale horizontally from there). This approach isn’t just about achieving early wins; it’s about solving specific use cases while also aligning with already existing budget line items in the enterprise.

When considering which ideas to pursue first, the guiding star should be the urgency of labor need—roles that are hard to recruit for would allow agents to be adopted at a higher rate and provide a faster journey towards product-market fit.

This graphic from Decibel VC tells the story:

Sarah Tavel writes in a post titled “Sell Work, Not Software”:

For the past 25 years, application software startups have had a singular focus: increasing company and employee (including developer) productivity. This looked like building software that increased productivity at the employee level, increased collaboration across employees and teams, and/or enabled better oversight and management at the leadership level. More often than not, this software has been priced on a per seat basis, in essence benchmarked against the cost of the headcount itself and increasing that headcount’s productivity.

Enter Large Language Models (LLMs). The first tranche of products and startups leveraging LLMs has kept within the mental model of selling software to achieve step-function improvements in end-user productivity. The “Copilot for [x]” trend reflects this mental model. While there are fantastic startups innovating to improve employee productivity, LLMs create an opportunity for startups to look beyond this way of thinking and discover surface area that previously was out of bounds for selling software given the required GTM and pricing limitations of software. To do this, rather than sell software to improve an end-user’s productivity, founders should consider what it would look like to sell the work itself.

More: “One of the core hypotheses behind “selling work, not software” is that when you sell a 95% productivity improvement (vs squishier productivity improvement you sell against with software), you are able to charge *substantially* more for your service than you would have otherwise been able to if you sold software on a per seat basis. This can mean that the same end markets could be 10-50x larger than your software-model intuition would tell you.”

Emergence Capital writes: “Service businesses that leverage both AI and humans to deliver holistic solutions to clients are poised to outgun and outpace the services behemoths that’ve dominated for the last 50 years. Legacy providers are ripe for disruption: their business models rely on human labor and hourly billing which can be turned on its head by AI-enabled vendors. Further, their “product” (humans) is very difficult to integrate AI into. While software incumbents are having a relatively easy time adapting to the GenAI wave, services incumbents will struggle. Founders, this is a boomtown moment to seize. For a long time now, founders pursuing software exclusively have been strip mining for the same, highly competitive gold. There’s a bounty to be had by the few companies building disruptive AI-enabled services.”

Collectively, these insights suggest a future where the lines between software and services blur, with AI playing a central role in redefining value delivery in the IT and software industries. This shift emphasises outcomes over outputs, and tailored, AI-driven solutions over generalised software tools, marking a significant evolution in how businesses and enterprises approach digital transformation and operational efficiency. Think of this as the new SaaS: software AND services bridged by AI agents.

AI Agents – 1

Let’s begin by understanding AI Agents.

Biddwan Ahmed: “An AI agent is a computer program capable of performing tasks autonomously by making decisions based on its environment, inputs, and predefined goals. These agents represent a leap from traditional automation, as they are not just designed to follow a set of instructions but to think, adapt, and act independently. Imagine a digital entity that continually assesses its surroundings, learns from interactions and makes choices to achieve specific objectives. It is the essence of an AI agent. It’s akin to having a digital assistant that executes tasks, understands the context, adjusts strategies, and even creates new methods to attain its goals. In practice, AI agents can range from simple programs performing single tasks to complex systems managing intricate processes. They thrive in unpredictable environments where they can leverage their adaptability and learning capabilities. These agents can navigate the web, interact with applications, process vast amounts of data, and even engage in transactions, all while evolving their approach based on feedback and outcomes.”

Akash Takyar: “AI agents are emerging as a revolutionary force, poised to redefine the way we interact with digital systems. At the heart of this transformation are Large Language Models (LLMs), which equip these agents with the ability to understand and process language with a level of sophistication that mirrors human intelligence… A critical aspect of AI agents is their capacity for learning and adaptation. Through the integration of technologies such as Large Language Models (LLMs), they continuously improve their performance based on interactions, evolving into more sophisticated and intelligent assistants over time. In the realm of autonomous AI agents, multiple agents collaborate, each assuming specialized roles akin to a professional team. This collaborative approach allows for a more comprehensive and efficient problem-solving process, as each agent contributes its expertise to achieve a common objective… These agents, based on LLMs, can be broadly classified into two main categories: conversational agents and task-oriented agents…Conversational agents aim to provide engaging, personalized interactions, while task-oriented agents focus on achieving specific goals.”

BCG: “Autonomous agents use the power of LLMs to sense and act on their environment by creating, executing, and prioritizing tasks. The process starts when the agent receives an objective. The agent then breaks down the goal into individual tasks and creates a set of bite-sized prompts to tackle each one. These prompts are fed to an LLM iteratively and, as tasks are completed, the agent creates new, better prompts that incorporate the results of the preceding iterations. The agent’s process of generating prompts and building on the results may be parallel or sequential depending on the system design. The agent also actively reorders and prioritizes the tasks according to the results. The system continues this cycle of breaking down the goal into tasks, generating prompts, evaluating results, and prioritizing until the goal is met or deemed unattainable (in which case, the agent shuts down the process).”

ITmagination: “Autonomous AI agents are emerging as innovative solutions that can revolutionize the way businesses operate. These intelligent systems are designed to perform tasks independently, adapting and learning from their environment to achieve specific goals. The GPT-4 language model, a groundbreaking development in artificial intelligence, plays a pivotal role in the advancement of autonomous AI agents… Auto-GPT, an experimental open-source application, serves as a testament to the capabilities of the GPT-4 language model. By chaining together LLM “thoughts,” Auto-GPT demonstrates the potential for AI to autonomously accomplish a wide range of objectives.”

Shubham Tulshyan: “With OpenAI’s revolutionary GPTs (Generative Pre-trained Transformers), we’re now seeing AI agents not just assisting but leading in various domains – from planning trips to analyzing customer service requests. The key here is shareability; these AI agents encapsulate domain knowledge and expertise, making it globally accessible. Imagine harnessing this power within your organization, utilizing AI trained on your internal knowledge base. It’s a game-changer!. Another fascinating development is the concept of digital twins – virtual models of physical entities capable of running simulations. These are not just 3D models but dynamic systems that predict real-world scenarios and outcomes, revolutionizing everything from product development to process management…This new era of SaaS, powered by AI agents and digital twins, offers unparalleled efficiency and predictive power.”

Axios: “Moving to a world in which AI systems take actions rather than just provide insights will requires a significant shift in both technology and human behavior. “Once we get agent-like systems working, AI will feel very different to current systems, which are basically passive Q&A systems, because they’ll suddenly become active learners,” Google DeepMind CEO Demis Hassabis told Wired… As businesses hand off more tasks to agents, their customers will, too — speeding us toward a world in which “my bot will talk to your bot.””

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:

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.
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.
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.
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:

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.
Smart Home Devices: Devices that manage home environments, like smart thermostats and security systems, adjusting settings based on user behavior patterns or external conditions.
Healthcare: Robots or virtual agents that assist in surgeries, patient monitoring, and personalized healthcare plans, making decisions based on patient data and medical knowledge.
Customer Service: Chatbots and virtual assistants that handle customer inquiries, provide personalized recommendations, and resolve issues autonomously, improving over time through interactions.
Finance: AI agents in trading and investment platforms that analyze market data, predict trends, and autonomously make buying or selling decisions to maximize returns.
Manufacturing and Logistics: Robots and systems that autonomously manage inventory, handle materials, and optimize production lines and supply chains for efficiency and reduced downtime.
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.

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.

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.”

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.

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.

Summary, Critique, Enhancements

ChatGPT

Summary

The essay presents a forward-looking perspective on the evolution of Software as a Service (SaaS), introducing the concept of “New SaaS,” which integrates Services, AI Agents, and Sharing. It begins by highlighting the transformative potential of AI-driven autonomous agents in disrupting traditional IT and software service models, emphasizing a shift from offering mere software to delivering value-driven outcomes. The essay delves into the mechanics of AI agents, their ability to automate tasks, personalize experiences, and enhance decision-making processes, thereby redefining customer interactions and operational efficiencies in businesses. The narrative further explores the practical applications of this new paradigm in B2C Martech through innovations like Digital Twins and Co-Marketers, which exemplify personalized customer engagement and streamlined marketing operations, respectively. This “New SaaS” model is posited as a comprehensive ecosystem that transcends traditional software delivery by harnessing AI for automation and personalization, embedding human expertise for continuous improvement, and adopting a performance-based collaboration model.

Critique

Depth on AI Agents: While the essay provides a broad overview of AI agents, it could benefit from deeper insights into the technological intricacies and challenges of integrating these agents with SaaS platforms. For instance, addressing data privacy concerns, the complexity of AI models, and the scalability of AI solutions could offer a more rounded view.
Implementation Strategies: The essay outlines the high-level benefits and potentials of the New SaaS model but lacks detail on implementation strategies. Businesses seeking to adopt this model would benefit from guidance on transitioning from traditional SaaS to this new approach, including best practices, potential pitfalls, and case studies of successful implementations.
Economic Considerations: While the essay touches upon the economic benefits of outcome-based pricing, it could further explore the financial implications of adopting the New SaaS model for both providers and consumers. This includes cost considerations, ROI analyses, and how this model might alter the competitive landscape of the SaaS industry.

Enhancements

Technological Blueprint: Elaborate on the technological requirements and architecture needed to support the integration of AI agents within SaaS platforms. This could include discussions on cloud infrastructure, data analytics pipelines, and the role of emerging technologies like edge computing and blockchain in enhancing security and performance.
Adoption Roadmap: Offer a step-by-step guide or framework for businesses to transition to the New SaaS model. This roadmap could include stages like assessment, pilot projects, scaling strategies, and metrics for measuring success, accompanied by real-world examples.
Economic Impact Analysis: Conduct a detailed economic impact analysis of adopting the New SaaS model, including cost-benefit analyses, pricing models, and market trends. This could be supported by data-driven projections to help businesses make informed decisions about embracing this new paradigm.

Claude

Summary

The essay presents a vision for a “New SaaS” model that goes beyond traditional software-as-a-service offerings. It proposes combining three key elements:

Services: Integrating human expertise by bundling services with the software product to enable continuous improvement and personalization based on user feedback.
AI Agents: Incorporating autonomous, intelligent AI agents that can automate conversations, tasks, and predict the “next best action” for improved user experiences.
Sharing/Progency model: Adopting an outcome-based pricing strategy where software providers participate in their clients’ success by taking a share of the incremental profits generated through the use of their software.

The New SaaS model aims to create an integrated, outcome-driven ecosystem leveraging the synergies of these three components. It envisions AI agents embedded within SaaS platforms to automate tasks and personalize experiences, while human services ensure continuous evolution aligned with user needs. The sharing/progency model aligns the economic interests of providers with tangible business outcomes, fostering a partnership geared towards mutual growth and success.

The essay also highlights two specific innovations that exemplify the New SaaS model in the B2C Martech space: Digital Twins (hyper-personalized AI companions for individual customers) and Co-Marketers (AI agents supported by human expertise to optimize marketing activities).

Critique

Pros

Novel approach that addresses key challenges faced by traditional SaaS models, such as lack of personalization, inefficient user experiences, and misaligned incentives.
Leverages the strengths of AI and human expertise to create a more dynamic, adaptive, and customer-centric offering.
The outcome-based pricing model encourages a partnership approach and shared accountability for success.
Specific examples like Digital Twins and Co-Marketers demonstrate the potential applications in the B2C Martech space.

Cons

Implementing the New SaaS model requires significant changes in business processes, pricing strategies, and organizational culture, which may face resistance or adoption challenges.
Balancing the roles and contributions of AI agents and human services could be complex, potentially leading to inefficiencies or conflicts.
The sharing/progency model may be more suitable for certain industries or use cases, and its universal applicability could be limited.
Concerns around data privacy, security, and ethical considerations with the extensive use of AI agents and personalized customer data.

Enhancements

Provide more detailed examples and case studies of successful implementations of the New SaaS model, ideally across different industries, to demonstrate its real-world viability and impact.
Outline a roadmap or framework for existing SaaS companies to transition towards the New SaaS model, addressing potential hurdles, change management strategies, and best practices.
Explore the ethical and regulatory implications of the New SaaS model, particularly concerning data privacy, AI bias, and transparency in decision-making processes involving AI agents.
Discuss potential business models and revenue-sharing structures that could support the sharing/progency approach, considering different scenarios and industry-specific nuances.
Examine the impact of the New SaaS model on various stakeholders, such as end-users, employees, and the broader ecosystem, and propose strategies to address potential challenges or concerns.
Provide insights into the required technological infrastructure, data management strategies, and integration frameworks needed to seamlessly combine AI agents, human services, and existing SaaS platforms.
Explore the scalability and potential limitations of the New SaaS model, particularly in terms of managing a large number of AI agents, human resources, and personalized customer interactions.

Gemini

Summary

This essay explores the concept of “New SaaS,” a transformative model that transcends traditional software delivery. It argues that SaaS, while successful, has limitations in delivering concrete outcomes for customers.

The essay proposes three pillars for “New SaaS”:

Services: Integrating human expertise with AI for continuous improvement and personalization.
AI Agents: Automating tasks, personalizing experiences, and offering predictive insights through intelligent automation.
Sharing: A “progeny” model shifting the economic relationship towards shared success, with pricing based on performance and outcomes.

These elements combine to create an outcome-driven ecosystem that leverages AI, human expertise, and collaborative value creation.

The essay further explores how “New SaaS” can revolutionize B2C Martech with innovations like the “Digital Twin” (a hyper-personalized AI companion) and the “Co-Marketer” (an AI-powered marketing assistant).

Critique

The essay offers a compelling vision for the future of SaaS. It clearly defines the core components of “New SaaS” and provides strong examples of its application. However, a few areas could benefit from further elaboration:

Challenges: Briefly discuss potential challenges like the cost of implementing AI or retraining the workforce. Propose solutions like phased adoption or skill development programs.
Wider Applicability: Briefly discuss how “New SaaS” can be adapted to other industries beyond B2C marketing.
Conclusion: Summarize the key benefits of “New SaaS” and outline a roadmap for its adoption. Emphasize the potential for this model to usher in a new era of SaaS.

Enhancements

Address potential concerns about job displacement due to automation. Highlight how “New SaaS” can create new job opportunities requiring human-AI collaboration.
Briefly discuss potential regulatory considerations and ethical implications surrounding AI agents in SaaS, such as data privacy and bias.
Provide additional examples of how “New SaaS” can be applied in different industries to showcase its broader impact.
Conclude by emphasizing the potential of “New SaaS” to not only revolutionize software delivery but also foster a more collaborative and outcome-oriented future for businesses and customers alike.

More Martech Applications

I asked ChatGPT, Claude, and Gemini on how the “New SaaS” ideas could be applied to B2C Martech.

ChatGPT

Personalized Content Creation and Distribution

AI-Powered Content Platforms: Use AI agents to generate and distribute personalized content across various channels. For instance, an AI can analyze user behavior and preferences to create tailored blog posts, emails, and social media content, enhancing engagement and conversion rates.

Omnichannel Customer Experience Optimization

Integrated Customer Journey Mapping: Deploy AI agents to seamlessly integrate and analyze customer interactions across all touchpoints (website, mobile app, social media, and offline stores). These insights can be used to optimize the customer journey, offering a unified and personalized experience that boosts loyalty and customer lifetime value.

Dynamic Pricing and Promotions

AI-Driven Pricing Strategies: Implement AI agents that monitor market trends, competitor pricing, and consumer demand in real-time to adjust pricing and promotions dynamically. This ensures optimal pricing for various customer segments, maximizing revenue and competitive advantage.

Augmented Reality Shopping Assistants

Virtual Try-On and Showrooming: Leverage AI-powered AR applications that allow customers to virtually try products (e.g., clothes, glasses, or furniture in their home) before purchasing. These AI agents can offer recommendations based on the customer’s preferences and past purchases, enhancing the shopping experience and reducing returns.

Voice and Conversational Commerce

AI-Enabled Voice Assistants: Develop voice-activated shopping assistants that facilitate hands-free shopping and customer service. These agents can answer queries, recommend products, and even complete transactions, making shopping more accessible and convenient.

Predictive Analytics for Customer Retention

Churn Prediction and Prevention: Utilize AI agents to analyze customer data and predict potential churn. These insights enable marketers to proactively engage at-risk customers with personalized retention strategies, offers, or content, thereby increasing retention rates.

Social Listening and Sentiment Analysis

Brand Reputation Management: Employ AI agents to continuously monitor social media and online forums for mentions of your brand. These agents can analyze sentiments, identify trends, and alert you to potential PR crises before they escalate, allowing for timely and effective management.

Interactive Video Content

AI-Powered Interactive Videos: Create interactive video content where viewers can make choices that influence the story or outcome. AI agents can personalize the video content in real-time based on the viewer’s choices and preferences, leading to higher engagement and a more immersive brand experience.

Gamification and Loyalty Programs

Dynamic Loyalty and Reward Systems: Design AI-driven gamification and loyalty platforms that adapt rewards and challenges based on individual user actions and achievements. This personalized approach incentivizes continued engagement and loyalty.

Sustainable and Ethical Marketing

AI for Sustainable Consumer Choices: Implement AI agents that guide consumers towards more sustainable and ethical product choices, aligning with growing consumer demand for responsible brands. AI can highlight eco-friendly products, suggest alternatives, and educate consumers on sustainability.

Claude

Personalized Content Curation and Recommendations: The New SaaS model could power a highly personalized content curation and recommendation engine for B2C marketers. AI agents could analyze individual customer data, preferences, and behavioral patterns to dynamically curate and deliver highly relevant content, product recommendations, and offers. Human services could supplement this by providing expert oversight, creative input, and continuous refinement of the curation algorithms based on customer feedback and market trends.

Intelligent Campaign Orchestration: The combination of AI agents and human services could enable intelligent, end-to-end campaign orchestration for B2C marketers. AI agents could automate tasks such as audience segmentation, creative optimization, channel selection, and real-time campaign adjustments based on performance data. Human services could provide strategic guidance, creative direction, and oversight to ensure campaigns align with overall marketing objectives and brand positioning.

Conversational Commerce and Virtual Shopping Assistants: The New SaaS model could power advanced conversational commerce and virtual shopping assistants for B2C brands. AI agents could engage with customers through various channels (chatbots, voice assistants, etc.), providing personalized product recommendations, answering queries, and guiding them through the purchase journey. Human services could train and fine-tune these AI agents, ensuring they accurately represent the brand’s voice and values while continuously improving based on customer interactions.

Customer Experience Optimization: The New SaaS model could drive customer experience optimization for B2C brands by leveraging AI agents to analyze customer data, identify pain points, and predict churn risks. Human services could then design and implement targeted interventions, such as personalized offers, loyalty programs, or customer service improvements, aimed at enhancing the overall customer experience and reducing churn.

Dynamic Pricing and Promotions: AI agents could enable dynamic pricing and promotions strategies for B2C marketers by continuously monitoring market conditions, competitor actions, and customer behavior. Human services could define the overall pricing and promotion strategies, while AI agents could execute real-time adjustments and personalized offers to maximize revenue and customer satisfaction.

In each of these examples, the combination of AI agents, human services, and an outcome-based pricing model could create a more adaptive, personalized, and effective B2C martech solution. AI agents would drive automation, personalization, and real-time optimization, while human services would provide strategic guidance, creative input, and continuous improvement. The outcome-based pricing model would align incentives and foster a partnership approach focused on delivering tangible business results for the B2C brand.

Gemini

Content Creation and Personalization Engine:

Services: A team of content strategists and creatives curate high-quality content aligned with user personas and industry trends.
AI Agents: AI algorithms analyze user data and engagement patterns to personalize content recommendations, automate content creation (e.g., generating social media posts), and optimize content delivery channels.
Sharing: Pricing based on a combination of content performance metrics (e.g., click-through rates, conversions) and user engagement, creating a win-win scenario for both the platform and the client.

Smart Customer Relationship Management (CRM):

Services: Customer success specialists provide onboarding assistance and ongoing support.
AI Agents: AI-powered chatbots handle basic customer inquiries, automate lead scoring and segmentation, and predict customer churn to allow for proactive intervention.
Sharing: Pricing based on the number of nurtured leads converted into paying customers, aligning the platform’s success with the client’s sales pipeline.

AI-powered Social Listening and Influencer Marketing:

Services: Marketing specialists provide guidance on social media strategy and influencer selection.
AI Agents: AI tools monitor brand mentions across social media platforms, identify relevant influencers, and predict campaign performance with different influencers.

Sharing: Pricing based on the reach and engagement achieved through influencer marketing campaigns, ensuring a clear return on investment for the client.

Share this:

Like this: