It’s Groundhog Day: Lack of an Integration Strategy Will Inhibit AI, Too

Introduction

The undisputed hottest topic in technology now and for the near future is LLMs and Generative AI. There’s a lot of talk about how to design prompts and get ChatGPT4 to do cool things for you, but not a lot about how to get value across an entire enterprise. 

That’s what we’ve been up to with our R&D team at Green Irony.

Killer Use Cases Beyond the Imagination

Today’s Generative AI capabilities unlock high-ROI use cases that were unthinkable a year ago. Green Irony’s R&D team has many in the works that we can’t wait to show you. For now, imagine the following scenario in the Travel & Hospitality industry:

A business traveler named Chris is currently in Dallas for some client meetings. It’s summertime and not only is there significant demand for air travel but there is also severe weather including tornadoes, hail, and severe thunderstorms wreaking havoc on the major airline hubs of the midwest. This passenger has a family emergency and needs to get back to Tampa, FL as soon as possible, no matter the cost.

Prior to November 2022’s release of ChatGPT, this would have required a sophisticated travel agent with expert knowledge of flight and rental car booking systems and lots of time with Google Maps and other utilities. Possibly even a spreadsheet, and who wants to use one of those?

What if instead Chris could just say this to an AI service?

“Give me your top 3 options for getting me from my current location to Tampa, FL, by 5 PM tonight. Car travel should be limited to 120 miles or less. Optimize first for arrival time, then for premium seat availability, then for driving distance. Do not risk any connecting flights in the midwest.”

So what’s stopping us from doing this RIGHT now?

Hint: It’s the same thing that always stops us, and MuleSoft Founder Ross Mason was prescient enough to warn us about it for AI in 2018.

Last decade’s disruptor: Mobile and Tablet Devices

2013 saw a huge shift of web traffic from desktop to mobile and this was incredibly impactful to businesses, especially those like retail that rely on web funnel conversion metrics as key business drivers. Mobile was arguably the first major disruptor that truly exposed the perils of siloed enterprise technology systems and lack of a clear, scalable integration strategy. 

I remember seeing it first hand. As my team and I worked with retailer HHGregg to deliver the #1 mobile experience in their space, what do you think our biggest inhibitor was to providing this exceptional customer experience?

If you said “integration”, you’re catching on to the theme of this blog. Attempting to get the right data to drive the right mobile user interactions and respond to these user actions within systems of record was by far our biggest inhibitor. Despite the fact that web browsers and JavaScript frameworks to drive the right mobile behaviors were still considered “cutting-edge” back then (Angular 1.2 was released November 15, 2013!), they were still the easy part. 

Integration was our clear-cut biggest hurdle to creating an award-winning e-commerce mobile experience for our partners at HHGregg.

Today’s Landscape for Scalable Integration

History again repeats itself, but this time with much higher stakes. Insert your preferred doom and gloom messaging about AI and existential risks to the viability of businesses and a high-stakes, zero-sum game arms race here.

The needle simply has not moved fast enough for most organizations over the past decade in terms of scalable integration. Most of them now are stuck with Ross Mason’s “big ball of mud” and every project, big or small, becomes bogged down by this situation. 

Just about every conversation I have with customers about a failed Salesforce implementation comes down to one thing: lack of access to data and business capabilities in other systems. Most of the time, in-house IT teams have built some Frankenstein’s Monster set of data synchronization capabilities that fail to scale with the purchase of new systems and software, evolution of business processes, and marketplace disruptions due to new cutting-edge technologies. In an ironic twist of fate, their Salesforce implementation team tends to spend their time attempting to solve systems integration problems that are not solvable within the Salesforce platform itself.  

These Salesforce implementations are inhibited by the same challenges we saw with mobile e-commerce websites in 2013.

AI will be no different, because today’s LLM’s like OpenAI’s GPT4 heavily reward enterprises with composable integration strategies.

Anybody Heard of This ChatGPT Thing?

Enter the most disruptive technology any of us will ever see in our lifetimes, a technology disruptive enough to disrupt even Google’s core business. 

Clearly, it’s important for businesses to get this right, and the sooner they get it right, the greater their competitive advantage will be. But without a scalable, composable API strategy that unlocks the capabilities of the business for consumption, broader AI efforts won’t get off the ground. 

In the aforementioned article from Mason, he wrote the following:

“Organizations first need to become more composable, building a connected nervous system called an application network, which enables AI to plug in and out of any data source or capability that can provide or consume the intelligence it creates. The point-to-point integrations of the past won’t be practicable in the AI-world, where things can change in an instant. Instead, organizations need a much more fluid approach that allows them to decouple very complex systems and turn their technology components into flexible pieces.”

Our R&D efforts with OpenAI, which we plan to showcase extensively in the coming weeks, have reinforced Mason’s point of view on this topic. GPT-4, the engine behind ChatGPT, can generate fantastic answers to questions that rely on generally available, non-specialist knowledge. In order to equip it with Enterprise-wide capabilities, we need composable APIs that allow us readily-available access to business capabilities so that GPT can solve real, enterprise-level problems. 

It’s Groundhog Day and we’ve seen this all before. Every innovative breakthrough levies additional burdens on an IT organization’s integration strategy. With the game-changing nature of AI, composable integration is needed now more than ever before.

We’ve Got So Much More to Say On This Topic

We hope you enjoyed the first post in this series. At Green Irony, scalable integration is in our DNA and we are incredibly passionate about this topic and the benefits it provides to our customers. Future posts will cover:

• A real-life, in-production application that Green Irony has used to exponentially scale its candidate interview process and save hundreds of hours across key members of staff while increasing its applicant quality.
  
• A prototype for the Travel & Hospitality industry that unlocks a vastly superior way to purchase products and services in this industry.
  
• Several deep dive spotlights into the engineering behind both solutions, showcasing how the Green Irony OpenAI Connector can be used broadly for any OpenAI use case.
  
• A comprehensive white paper on why composable integration is an absolute must for companies who are serious about leveraging AI that builds upon the concepts in Ross Mason’s 2018 blog.
  

Supercharge your AI readiness by combining our MuleSoft OpenAI Connector with an AI-ready integration strategy.