An AI onboarding assistant to build custom applications

Client:

A leading no code work management platform.

Background:

Low- and no-code platforms allow non-technical users to build powerful projects quickly and efficiently. However, the traditional process of building a project within these platforms often involves manually adding data to tables and their associated rows.

This manual approach not only consumes significant time and effort and for more complex projects requires some knowledge of data modelling. To simplify the process of building projects, our client wanted to create a virtual assistant that could generate custom software platforms based on natural language prompts.

This required leveraging robust natural language processing capabilities to interpret text descriptions and automatically produce relevant data schemas.

Solution:

The solution streamlines the onboarding process for the client by giving users a way to quickly generate projects based on text inputs. This eliminates the need for manual data entry and reduces the time and effort required to get started with a new project.

Microsoft’s Azure OpenAI Service was chosen for this project because it provides access to OpenAI’s pre-trained large language models, including GPT-3 and Codex, via its REST API. This API can then be leveraged to create generative language processing tools. Azure OpenAI Service is also compatible with open-source framework LangChain to allow users more granular control over the training of these large language models.

Key steps included:

• Engineering detailed prompts to provide application context
• Leveraging the completions endpoint to generate JSON schemas
• Parsing model outputs to dynamically create data structures
• Integrating the assistant into the no-code platform's UI
• Implementing content moderation and enterprise security

The virtual assistant interprets text prompts and automatically generates tailored data models required for custom platforms. This streamlines the manual process of building new projects.

Results

Azure OpenAI service gives users the ability to build custom software solutions by interpreting and processing natural language text inputs. For example, by interreacting with the AI and providing a request like “I want a CRM platform” users will receive a custom CRM platform to fit their needs. This approach revolutionises the traditional process of building these platforms, as it eliminates the need for extensive business and process analysis. 

Providing benefits in:

• Access to large language models (LLMs): OpenAI Service leverages OpenAI’s most powerful language models such as ChatGPT and GPT-4, enabling users to create powerful natural language processing tools.
• Speed: The API contained within Azure’s OpenAI Service reduces the chances of bottlenecks compared to using OpenAI’s API, where users would be contending with the traffic from ChatGPT.
• Content moderation: Azure OpenAI includes a content management system that filters potentially harmful content alongside the models. For detecting misuse, this system runs both input prompts and generated completions through a series of classification models.
• Security: OpenAI service comes with enterprise-grade security features, such as role-based and access control.

Key results included:

• Automatic custom app generation from text descriptions
• Conversational interface requiring no coding
• Significant time savings over manual data entry
• Reliable content moderation and security