The client is an IT behemoth, specializing in delivering cutting-edge digital services and consulting to Fortune 500 companies. Notably, they have harnessed the power of SaaS-based low-code platforms, enabling their customers to deploy robust tools and construct entirely new applications effortlessly. Recognizing the need to speed up the app development process to bring numerous use cases to market quickly, they approached us to infuse Generative AI capabilities in their low-code platform. Leveraging our strong partnership spanning over 4+ years, we successfully developed an AI-based code generation platform and integrated it with their low-code solution. We transformed the platform into an all-encompassing solution within a mere span of 12 weeks.
With an illustrious track record spanning over three decades, the customer is an IT leader in efficiently managing global enterprises' intricate systems and operations. Boasting an expansive global presence across 8+ countries, 5+ Fortune 500 customers, and a 10000+ workforce, they have been skillfully building transformative journeys for Enterprise clients.
Their offerings include integrated AI platforms, renowned management consulting, cloud-centric enterprise transformation, advanced analytics, and internationally recognized banking platforms. Additionally, they offer cloud suites and engineering services.
They are headquartered in India and are one of the top IT giants, with over $45M in annual revenue in 2022.
The customer has a low-code platform that enables rapid design of enterprise-ready apps, beautiful UIs, and integration of people, technologies, data, and systems into a single workflow. The platform minimizes hand-coding, supports multiple development languages & frameworks, and provides all the tools developers need in one IDE. It helps manage modules, components, and business rules in one location to use them across all applications. Its support to deploy on multiple cloud platforms surpasses platform, database, or interface lock-ins.
The platform has helped build 200+ applications using the low-code approach across the Healthcare, Finance, Public sector, Supply Chain, and Retail Industry.
They wanted to transform how users experience their platform, make it even easier to use, and further unlock its power with Generative AI to help enterprises decode a range of use cases.
Consider a user asking the platform to “create an application for a home loan” and quickly selecting from a list of suggested auto-generated stages and workflow steps to generate a new application. With the existing low code capabilities, the platform should auto-complete, optimize, review, and deploy the code. Additionally, it should detect bugs, perform Security Analysis, and generate Test cases and documentation, making it an all-in-one solution for software development teams.
Most of all, the customer aimed to optimize the speed of experimentation. While some products take up significant resources to reach the market faster, with Low Code Platform + Generative AI, the cost of experimentation should be so low that anyone who decides to spend time with it should eventually create a successful application much faster than they otherwise would have.
"Team Velotio has played an exemplary role in elevating our Low-Code platform. They skillfully integrated our objectives and their technical competencies to infuse AI capabilities into the platform. Since then, we have assisted multiple customers in developing applications with lightning-fast development cycles. We look forward to bringing numerous use cases to life and creating endless possibilities through the platform."
Solution Architecture -
We developed the NL Platform as an application, with its framework based on Python. This framework supports interactions with various Low-Code platforms, allowing users to create, modify, or delete specific functionalities. Initially, users are required to connect to the Low-Code platform. Post-connection, the NL Input Processor aids in interpreting user intents, extracting critical information, and generating meaningful commands or responses. This functionality is powered by Large Language Models (LLMs). Additionally, we harnessed OpenAI's fine-tuned models through APIs to enable this feature. Moving forward, these commands are processed, and relevant actions are executed at the core of the NL platform.
Understanding the Data flow -
The user NL queries will be sent to the NL platform core, which further sends the inputs to the processor and generates the command of action with the help of OpenAI fine-tuned Large Language models. The core will then process these commands of action, and appropriate actions, such as code completion, code generation, code optimization, etc., will be taken. Once the action is completed successfully, the vulnerability detector checks the performed action for security-related vulnerabilities. This way, the user will be notified of the changes on the platform.
The customer aimed to provide startups and enterprises with a comprehensive solution enabling them to develop applications and quickly bring their ideas to market. Velotio took up the challenge of creating a unique platform within the given timeframe with a team of front-end engineers, back-end engineers, UX designers, and QA specialists.
We structured the complete project in four parts. Initially, we comprehensively analyzed the customer's platform. After thorough research and brainstorming, we devised a plan to develop an NL Platform for code generation, completion, review, optimization, bug detection, test cases, and documentation generation. We planned to harness the power of OpenAI's codex to generate code based on natural language prompts. In part 3, we integrated the Low code platform with the NL platform. Lastly, we constructed a smooth system for Maintaining, monitoring and supporting the platform in multiple aspects.
Part 1 – Understanding Customer’s Low-Code Platform
During the initial phase, we conducted multiple sessions with the customer's teams to gain a deep understanding of their low-code platform, focusing on its backend, frontend, and underlying technological aspects.
Part 2 – Building the NL Platform
Test Case Generation and Documentation
Part 3 - Integration of Low-Code Platform & NL Platform
Part 4 – Maintenance, monitoring, support, and future areas of enhancements
Future areas of enhancements
“Amplified the speed of experimentation by 2x, unlocking a multitude of potential use cases and saving humongous costs.”
“Attained a 20% faster Development Time for Web/Mobile Applications, empowering platform users with increased efficiency and productivity.”
“Proactively facilitated the onboarding of over 12+ customers post-integration, delivering a competitive edge to the customer and expanding their market reach.”
“Pioneered the platform by infusing AI capabilities, creating a revolutionary “All-in-One” solution for development teams.”