Eigent AI

Location
London, UK
Date
2025 June → Now

At Eigent AI, I own the whole product design for all our products. I designed, implemented, and shipped the core component library based on Radix. I also built and now maintain the marketing site for both our Developer Community and Business Customers.

Case Study
This video is password protected
November Release: UX Modernization & Functional ScalingBetween October and November, I led the end-to-end design and development of four major system features and a global interface update. This release focused on increasing workflow efficiency through multi-tasking capabilities, centralizing user data, and refining the visual hierarchy of the platform.

Intelligent Multi-Turn Chatbox

Designed and developed a new chat interface capable of handling complex, multi-turn conversations. I implemented a task-queuing system that allows users to line up multiple operations seamlessly without interrupting the flow of the current dialogue.

Centralized Dashboard

Transformed the static "History" page into a fully functional, centralized Dashboard. This redesign gives users better visibility and control, serving as the new hub for tracking activities and managing system status.

Nested Project Architecture

Refactored the project management system to support a multi-task hierarchy. Users can now create multiple distinct tasks under a single parent project, resulting in a cleaner workspace and better organizational logic.

Core System & Layout Enhancements

Implemented essential backend support for browser cookie management to improve session stability. Additionally, I deployed a global UI layout adjustment to ensure visual consistency and responsiveness across the entire application.

Version MVPBuilt an open-source AI workforce Desktop app for Mac & Windos with 5 key features in 2 months.
Eigent Interface: run a sample task for analysing stock surge

Eigent Interface: run a sample task for analysing stock surge

Employs a team of specialized AI agents that collaborate to solve complex tasks. Eigent dynamically breaks down tasks and activates multiple agents to work in parallel.

Employs a team of specialized AI agents that collaborate to solve complex tasks. Eigent dynamically breaks down tasks and activates multiple agents to work in parallel.

Customise workers with your selected tools and instructions to build a team of multi-agent workforce.

Customise workers with your selected tools and instructions to build a team of multi-agent workforce.

If a task gets stuck or encounters uncertainty, Eigent will automatically request human input.

If a task gets stuck or encounters uncertainty, Eigent will automatically request human input.

Deploy Eigent locally with your preferred models.

Deploy Eigent locally with your preferred models.

Eigent comes with massive built-in Model Context Protocol (MCP) tools (for web browsing, code execution, Notion, Google suite, Slack etc.), and also lets you install your own tools. Equip agents with exactly the right tools for your scenarios – even integrate internal APIs or custom functions – to enhance their capabilities.

Eigent comes with massive built-in Model Context Protocol (MCP) tools (for web browsing, code execution, Notion, Google suite, Slack etc.), and also lets you install your own tools. Equip agents with exactly the right tools for your scenarios – even integrate internal APIs or custom functions – to enhance their capabilities.

Eigent WebsiteDeveloped and currently maintain Eigent’s marketing website. I designed the site’s layout and built the frontend user interface. Key features include a dynamic landing page, detailed use case sections, pricing and payment integration, a CMS blog, a user authentication system, and comprehensive technical documentation.
Within two months of launch, the website delivered 7,000 registered users.

Within two months of launch, the website delivered 7,000 registered users.

2025 © Douglas Yueming Lai