How is Generative AI Being Applied? - Poll Results

Steven Forth is a Managing Partner at Ibbaka. See his Skill Profile on Ibbaka Talio.

Generative AI continues to draw a lot of attention and investment. This led us to ask our networks how generative AI is being used in business today.

Before we check in on the poll results, here is a quick description of generative AI and some of the ways we have seen it being applied.

Prompt

What is generative AI? Please provide a short summary for business readers.

ChatGPT

Generative AI refers to a category of artificial intelligence (AI) that focuses on creating new, original content rather than simply processing or analyzing existing data. It employs generative models, such as Generative Adversarial Networks (GANs) or language models like OpenAI's GPT, to generate diverse outputs like images, text, or other forms of data.

For business readers, generative AI holds significant potential in various applications, including content creation, creative design, natural language processing, and problem-solving. It can automate and enhance creative tasks, streamline content generation processes, and contribute to innovation by producing novel ideas. Businesses can leverage generative AI to develop personalized content, improve product design, and explore new solutions, ultimately driving efficiency and fostering innovation in various industries.

The poll was conducted the week of February 19, 2024, across the Software as a Service - SaaS, Product Management and Development Association (PDMA), Professional Pricing Society (PPS), and Design Thinking groups on LinkedIn.

The poll question was

“What is the 'low hanging fruit' for AI adoption at your company?”

  • Internal business processes

  • External marketing

  • Enhance the value of our offers

  • Other

There were 173 responses at the time of writing.

Not surprisingly, the most common application was internal business processes. Given the variety of generative AI applications, this is not surprising. Some of the applications we have seen include …

  • Summarizing content

  • Generating content for presentations and specific content types such as

    • User personas

    • Ideal customer profiles

    • Sales communications

    • Customer support and customer success

    • Requirements documents

  • Supporting coding and other engineering work

  • Innovation

    • Idea generation

    • Concept blending

    • Exploration of alternatives

    • Scenario planning

External marketing is one of the uses that gets the most attention. All of us are getting emails written by one or other generative AI applications, and there is a proliferation of blog and social media posts generated by AI. LinkedIn has its ‘Rewrite with AI’ button prominent every time one tries to make a post and there are many tools available with everyone from Hubspot to Wrtitio or Copymatic playing in this field. With video generation the current hot thing, the release of Open.ai Sora has drawn a lot of attention, expect to see a lot of generative AI content in your various feeds over the coming months.

All of this has led to concern about the possibility of model collapse, as transformers consume more and more synthetic data to build future models, see for example The Curse of Recursion: Training on Generated Data Makes Models Forget by Ilia Shumailov et al. Many possibilities branch off from this, but that is a topic for another day.

Only 21% of respondents said that AI is being used to enhance the value of their offers. That will grow over time as virtually all software will be built on AI platforms of one form or another in the coming years, just as it is built on relational databases today.

Ibbaka conducts ongoing research into how B2B SaaS companies are innovating and creating value using AI, and specifically how they are monetizing that value.

Get the AI Monetization in 2024 Report.

At his point, most major B2B SaaS verticals have at least one company that is AI native (built on an AI platform, often a language model of some flavor, developed using a transformer architecture). Older vendors generally take a different approach, adding an AI module (see Hubspot AI above and Microsoft Copilot) or slipping AI functionality into their applications (which is what Squarespace, the platform used for this website) has done.

There are some established B2B companies that have taken a different approach, re-platforming onto their AI module. See AI Pricing: AI as an extension or platform.

This introduces all sorts of interesting pricing opportunities. Will the platform be priced? If there is a scaling mechanism in the pricing will be be put at the platform level, on the modules, or both? How will the impact of computing on operating costs be managed …

Pricing AI enable functionality is the future of pricing work.

 
Previous
Previous

PeakSpan Master Class: Optimize Pricing & Packaging to Minimize Churn led by Karen Chiang & Steven Forth

Next
Next

SaaS Valuation and Early Exits: An Interview with David Rowat of Strategic Exits