KAI: an AI-powered web module development
Description
KAI is a London-based startup product development company specializing in AI learning software that improves verbal interactions between sales and marketing representatives and their clients in the healthcare supply chain. KAI’s artificial intelligence solutions analyze all types of interaction (online, over the phone, and in-person) and suggest ways to make them more effective, client-oriented, and positive.
NERDZ LAB’s task was to develop an integrated web-based module as an additional internal component to the client’s AI solutions.
Challenge
- A custom text editor.
- Lengthy conversations.
- Text and audio synchronization.
- Search and edit issue.
Solutions
- We created a custom text editor tailored to the client’s needs. The editor is a technologically complex solution with advanced markup features such as highlights, tags, badges, and more. It also allows testers to edit a conversation quickly and seamlessly. For instance, a tester can add a new speaker by simply hitting Enter to insert a paragraph break. When this happens, the system automatically identifies a change of speaker. Conversely, removing a paragraph break adds the line to the previous speaker.
- We modified the component hierarchy to reduce the impact of changes to elements. With this solution, we tackled the challenges above in three steps:
1. We changed the component logic from word-based to speech-based.
2. We added rules to define which components are affected by changes. With rules, when a specific component is changed, only the components defined by the rule are re-rendered. This achieves the desired goal of preventing the entire text from re-rendering after changes.
3. We designed an algorithm to recalculate timecodes.
Impact
- Upgraded AI learning software helped our client meet their project deadline and successfully launch their software.
- The module has halved the time required to process end-client calls.
- Optimized performance allows testers to work more efficiently and has reduced buffering during speech-to-text conversion.
