Ancient Greek mathematician Archimedes once said, “Give me a lever long enough and a fulcrum on which to place it, and I shall move the world.” He was right. When you intelligently use the right tools, you can move worlds and accomplish what on the surface seems impossible.
Right now, developers are doing the impossible—building applications in record time that truly transform industries, improve business processes, and unlock radical productivity. And they’re doing it with two tools—generative artificial intelligence (AI) and low-code.
Combining generative AI and low-code enables developers to build powerful applications at a whole new pace—making these employees more productive and valuable than ever and reducing both time and costs in the development process.
[ How much faster can you build applications with low-code and how can you improve processes? Get the Forrester Total Economic Impact™ of Appian study. ]
Generative AI tools have received the lion’s share of the press recently due to the release of ChatGPT, the large language model-based chatbot from OpenAI. But what is generative AI? In short, these tools create content such as text, code, images, and even videos through statistical methods. ChatGPT generates text, Dall-E and Midjourney generates images, and Synthesia generates videos, just to name a few examples. In development work, generative AI creates code from a natural language text prompt such as, “Write a Java function that sorts data records on a screen in descending order.” The output is code.
In development work, generative AI creates code from a natural language text prompt.
Low-code is a type of development that lets you create applications and workflows for full end-to-end processes with a drag-and-drop, visual interface. You use business process model diagrams to map out a workflow, then add drag-and-drop components, The low-code tool then generates the underlying code in a way that’s effective, performant, and secure. The output is applications and workflows for full end-to-end processes.
Let’s explore four essential things to know about how generative AI and low-code tools work together.
Low-code development is fast. Generative AI speeds things up even more. It’s like adding a nitro booster to an already-powerful, souped-up engine.
In addition, low-code balances out many of generative AI’s limitations. For example, generative AI can write code, but usually only in pieces for simple applications. Low-code, especially when native to a wider AI-powered process automation platform, offers enterprise-grade development tools with built-in best practices for security, performance, cross-compatibility, lack of bugs, and more. This means you can build far more than just code quickly—you can build enterprise-scale applications and automations fast.
Here’s another example of these tools’ complementary strengths and weaknesses. A common problem with generative AI are hallucinations—a fancy term for when an algorithm confidently provides a wrong answer from predictions on the next word, number, or element of code in a sequence. These predictions are not necessarily truthful. Developers then have to track down and debug these issues—and have the requisite knowledge to do so. This can slow down the development process without the guardrails that low-code naturally offers. Although hallucinations do occur in low-code, occurrences are much fewer and can be nearly eliminated with well-tuned models because components are pre-built and it’s hard to break things with it.
[ Want to learn how to revolutionize productivity with an AI-powered process platform? Watch the webinar. ]
Enough explaining. Let’s show a few examples of what can you do with generative AI and low-code combined:
Text completion: With generative AI and low-code combined, you can easily deploy chat bots within the context of a larger process such as fielding basic customer service requests or generate emails for human employees to review before sending.
Build an interface from a PDF: As mentioned above, generative AI can build designs as well. You can pair it with low-code to generate a full interface or form from a PDF, with proper working code and no need to check for hallucinations.
Generate a workflow: Here’s another option: Give a low-code platform instructions to build a workflow for an area like billing management. It will generate the workflow, with working code and a visual business process model diagram to represent the full process, in seconds. If the workflow isn’t perfect, you can respond by asking the system to update the process model and have it build the underlying code for it again. From there, you can use other low-code or process automation tools to complete the automation.
[ Learn about the differences between generative AI and large language models. ]
Over the past few decades, application development has expanded beyond people with computer science degrees to include self-taught developers, bootcamp graduates, and citizen developers.
Artificial intelligence and low-code will further democratize participation in application development, both separately and combined. Generative AI allows new programmers to create rudimentary code. Even though expertise is still required to ensure the code lacks errors, performs well, and follows security best practices, it can get people started—and generative AI has been a major timesaver for experienced developers.
Low-code democratizes development for professional and citizen developers. A citizen developer can create full applications and automations simply by dragging and dropping elements in a business process model, and a professional developer can map out processes for business partners in a shared common language. The advantage of low-code over AI, as mentioned earlier, is that the drag-and-drop components are pre-built. With low-code, you don’t have to worry about AI errors like hallucinations, security issues, or performance drains.
Generative AI paired with low-code further add to the democratization of development. Take the previous example of workflow generation. With generative AI and low-code combined, a new low-code developer could work with a business team, generate a workflow with natural language, gather feedback, then quickly update the workflow diagram with another natural language query.
As generative AI and low-code democratize development, it’s important to retain strong governance. Luckily, low-code offers natural guardrails for preventing issues. The low-code components of a good AI-powered process platform are pre-made, preventing developers from deploying code with security vulnerabilities or unreliable or unknown dependencies or applying code that degrades the overall performance or maintainability of the solution. This prevents a lot of the issues that can come from using generative AI alone for code.
AI-generated low-code created on a AI-powered process platform offers even more guardrails. An enterprise-grade platform offers features that define and enforce authorization, and ensure proper governance, around any digital solutions built on the platform, such as defining who can modify or use an artifact, control over modularity and propagation of functional capabilities, and defining the privacy of data elements.
A strong AI-powered process platform also offers built-in guardrails around the deployment process, to ensure code is properly tested and won’t break anything in production. This is why it’s critical to take a platform approach. Tools are already available to prevent issues from arising.
Low-code has been around the block. It’s established. Enterprise-grade AI-powered process platforms have powerful tools built in that make development much easier. As generative AI speeds things up like never before, both tools together enable citizen development and strong governance.
It’s a powerful symbiosis that leads to dramatically improved development, and true overhaul of end-to-end processes.
What’s coming next from an AI-powered process platform with low-code design? What benefits could you gain? Get a peek behind the curtain on the future of AI and the Appian Platform by watching the Appian World 2023 Product Vision Keynote.
Want to learn more about how a platform approach to AI and automation can help? Get the Gartner® Emerging Tech Radar: Hyperautomation report.