How we helped Accern design an AI research product that powered $40M growth and acquisition

While designing Rhea’s interface, we avoided overwhelming researchers with unnecessary features. Instead, we focused on delivering only what they need to make informed financial decisions, rather than replicating traditional research methods.

We built a hybrid interface that combines prompt-driven AI functionality with dynamic widgets and graphics. This offers a seamless research-to-report workflow with an intuitive split-screen mode.

Given Rhea’s use cases, where users frequently work with graphics, tables, and interactive elements, a purely chat-based interface with text inputs wasn’t enough.

Instead, we designed a widget-based system with a dynamic UI that adapts to the flow of conversation. Rhea can surface references, charts, footnotes, or graphical controls in response to voice or text prompts.

At the core of Rhea’s capabilities is an adaptive natural language communication system. When AI-generated answers are unclear or users struggle to frame their queries, Rhea steps in with clarifying questions, suggestions, and hints to help users get more accurate results faster. The feature that started as a differentiator is now industry standard, even OpenAI has followed suit

Rhea goes beyond natural language understanding, covering user comprehension, personalization, file management, and task assistance. This comprehensive suite is supported by robust data processing and synthesis on the backend.

At Lazarev, we committed to actualizing this functionality by transforming the chat field into an advanced search bar and a command line.

We wanted to make Rhea a multifunctional solution that offers greater value to users. To achieve this, we transformed the standard prompt field into an advanced command line.

This upgrade allows users to search for files, set up notifications, manage automated emails, schedule calls, issue alerts, and handle other key tasks as part of their daily workflows.

In the settings, people can select pre-configured datasets, called Lenses, or connect their own through Accern's NLP Platform. We added options to upload and manage files and folders, providing essential context for Rhea’s data analysis.

Additionally, we developed custom email notifications to deliver alerts and reports on specific topics, keywords, industries, or any other information researchers find valuable.