Thesys uses MongoDB Atlas to power C1, our generative UI platform that transforms LLM outputs into adaptive interfaces. MongoDB's flexible schema and document model enable us to manage authentication, billing, and API operations while scaling fast without migrations.

As generative AI is reshaping the entire user experience of how software is built and used, developers are constantly seeking new types of infrastructure platforms—ones that will make it seamless to build, manage, and even scale intelligent applications.

We built Thesys to meet this moment. Our mission is to make generative UIs (interfaces that dynamically adapt to the user) accessible and put them in the hands of every developer.

Behind the scenes, MongoDB Atlas serves as the backbone of our platform, C1 by Thesys, powering everything from authentication and billing to API management with unparalleled flexibility and reliability.

What's Generative UI

0:00

/0:07

A generative UI is a UI that is dynamically created in real time to adapt to a user’s needs, context, and goals. Instead of showing every user the exact same static screen, a generative UI continuously reshapes itself–changing out components, surfacing insights, and even helping simplify workflows on the fly. While traditional interfaces are one-size-fits-all, generative interfaces are custom-tailored to the specific needs of the user.

Unlike AI-assisted design or development tools that help designers and developers create prototypes or mockups, generative UIs focus on the end-user experience. It’s not about designing faster; it’s about making the interface itself intelligent so it can understand user intent and respond visually, not just textually.

Why Generative UI matters

Even as AI models become trained on more data and, in turn, become smarter, most applications remain trapped behind static chat bubbles or dashboards. Developers hardcode countless screens, while users sift through text to find what truly matters.

The mismatch? AI that understands you but can’t show you. This gap kills engagement and can slow iteration—factors that are crucial for user productivity. Teams spend time rebuilding UI layers for each use case rather than focusing on the holistic experience itself.

Generative UI bridges this gap by making AI interfaces adaptive, expressive, and instantly usable, and as a result, they unlock a new frontier in human-computer interaction.

How Thesys is solving generative UIs' hard problems

Building a generative UI platform from scratch is incredibly complex. Developers have to orchestrate model parsing, real-time rendering, system design, and data synchronization, challenges that can quickly become unscalable.

We simplify this process with C1, an API middleware that sits between your large language model (LLM) and frontend. C1 transforms text-based model outputs into live, adaptive UIs in real time.

C1 acts as an intelligent UI layer that operates through a seamless flow:

It understands the context of user interactions.
It generates a UI dynamically using composable components based on that context.
It renders the resulting interface on your frontend.

Developers can simply call our C1 API (which is compatible with any LLM, framework, or model context protocol server), and the system handles all the complexity behind the scenes.

In short? We abstract away the complexities of generative UIs, enabling teams to ship AI-native, context-aware interfaces effortlessly.

How MongoDB gives us the flexibility to move fast

Under the hood, our platform relies on MongoDB Atlas to fully manage its operational backbone. From user accounts and API keys to billing and access management, every operation is backed by MongoDB Atlas—a data layer that is fully optimized for flexibility and performance.

MongoDB's document model means we can store related entities, such as users and usage data, within the same documents, enabling critical data to coexist naturally and simplifying operations for our engineering team. This, in turn, streamlines queries and simplifies code. As the platform scales in the hands of users, this architecture ensures consistent speed and reliability for our user base.

Our operational data is constantly evolving, with new metadata and features emerging weekly, but MongoDB's flexible schema gives us the freedom to adapt instantly without painful migrations or rigid table definitions.

In a fast-evolving environment, this adaptability is crucial. "For a startup like Thesys, speed of execution means everything. MongoDB helps us move fast in an ever-changing world," said Rabi Shanker Guha, Cofounder and CEO of Thesys. "The best database is the one you don't have to think about—it just works exactly where and how you need it. That's MongoDB for us."

How MongoDB for Startups helped

Our journey was accelerated through the MongoDB for Startups program, which provides founders with MongoDB Atlas credits, hands-on technical help, and access to various go-to-market opportunities. The program empowers emerging AI and infra startups to scale quickly and securely—just like us.

What to expect ahead

As we continue to expand globally, MongoDB Atlas will enable our next phase of growth: supporting new analytics, usage insights, and developer-facing capabilities. Flexible, schema-less storage means that as we evolve, our data layer evolves alongside us.

C1 by Thesys integrates seamlessly with your AI stack, from popular LLMs like OpenAI, Anthropic, etc. to frameworks like Vercel AI SDK, CopilotKit, Mastra, LangChain, LangGraph, CrewAI, Autogen, and Streamlit, helping you build Generative UI experiences that work everywhere.

Ready to build adaptive interfaces for your application? Get started with C1 by Thesys today.

Related articles

May 2026 Security Incident

Why We're Open Sourcing OpenUI

AI Copilots: A Complete Guide to Intelligent Assistance

What Are AI Agents: Types, Capabilities, and Real-World Use

ChatKit: What It Is, What It Isn’t, and Where C1 Fits In

PowerPoint Automation Reimagined with C1 Artifacts API

The Future of AI Interfaces is Generative

MCP UI: Making AI Apps Interactive

What Is AG-UI and Why It Matters for AI-Native User Interfaces

How to design AI-Native Conversational Interfaces : From Templates to Generative UI

GPT 5 vs. GPT 4.1

How to Build Generative UI Applications

Implementing Generative Analytics with Thesys and MCP

Evolution of Analytics: From Static Dashboards to Generative UI

Why Generating Code for Generative UI is a bad idea

Building the First Generative UI API: Technical Architecture and Design Decisions Behind C1

How we evaluate LLMs for Generative UI

Generative UI vs Prompt to UI vs Prompt to Design

Generative UI: What It Is and Why It Matters