Skip to content

Xavier Basset

AI • Software • Engineering • Entrepreneur

Hello 👋
I'm a tech enthusiast passionate about creating technology that gives people superpowers—whether for work or fun. I founded Hoomano, diving into natural interactions and AI, and explored the use cases of LLMs before ChatGPT ever existed. I've co-chaired a human-machine interaction AI research lab and built tools like a complete enterprise-grade AI Assistant platform –Mojodex, 1000+ onprem users–, a developer-oriented prompting-toolkit –Instruct, similar to Prompty by MS–, and a realtime AI blueprint –Rico, no equivalent yet– to advance the world of AI applications.
My goal? To create trustworthy ways for everyone to interact with technology—be it for communicating, learning, or just playing around.
Want to talk about AI, natural interactions, or building the kind of tech we'd want our kids to use for their entire lives?
Reach out!

Blog

What I build

My interests revolve around natural interactions with digital services and AI as a tool to make it happen.

Motivations

My goal?

Create ways everyone can trust when interacting with technology. Be it for communicating, learning, or just playing around.

But here’s the thing.

How we connect with the digital world keeps evolving. We started with punch cards, then screens and keyboards. Then came the mouse and GUI. We got touchscreens, then pocket-sized devices. Now, it’s voice interactions.

More input. More ways to connect.

And with more input comes a deeper understanding of people.

But the big question: as things change, how important is data ownership in our future with digital assistants?

I want to build a world with the kind of tech I’d want my kids to use and live with for their entire lives.

Projects

Rico LeBot open-source (MIT) - GitHub

Real-time Voice Interface MVP

In November 2024, I've had the opportunity to participate in the OpenAI Builders Lab in Paris, where I was able to explore the potential of the Realtime API. I was amazed by how quickly I could build a prototype for a real-time web-based voice interface that uses function calls.

The initial prototype was focused on a cooking guide where you could ask for a recipe or ask for instructions on how to prepare a certain dish. It was an amazing and inspiring experience to me because I've spent the last 10 years building a similar technology. And it just works.

To go further, as I explored the possibilities of this prototype, it became clear there were some challenges to overcome before it could become a deployable product. That's why I created an open-source toolkit to address those problems.

Challenges and Solutions

  • WebSockets not well suited for longform connections: The official OpenAI Realtime API toolkit relies on WebSockets, which proved unstable for long-term sessions over HTTP. The OpenAI team suggested using WebRTC bridges for better stability. The toolkit implements WebRTC with a LiveKit integration.

  • Dynamic UI: I wanted a dynamic UI that could respond to user input in real-time. This meant connecting the function calls from the model to the front-end functions using remote procedure calls (RPC) over WebRTC. This brings the voice interface to life, allowing users to interact with different functions of the app seamlessly.

  • Architecture: A clear separation was needed between the web app's backend, the AI agent's backend, and the front-end. The toolkit achieves a lightweight design that is modular, has few dependencies, and is easy to use.

  • Roles: To quickly iterate on the user experience, you need to refine the prompts / instructions of the agent very frequently. That's implemented through an architecture where the 'roles' are separated from the code, and allows to add and modify them very quickly

Learn more in the blog post

Mojodex open-source (MIT) – GitHub

I've started to design and work on Mojodex as part of Hoomano's product with the team. It's been created hand-in-hand with our users. Initialy released as a SaaS product, it's been open-sourced because our clients wanted a way to build their own tool and create their future AI assets. That's what Mojodex provide them.

Mojodex has been designed as a fullstack AI assistant platform, bigger than Chat-based LLM projects.

If I can be of any help in your strategy of integrating AI in your business, don't hesitate to reach out

Instruct open-source (MIT) – GitHub

As a developer, I've felt like a lack of tools to interact with LLMs in an appropriate way. They are probabilistic interpretation engines using long sequences of texts as inputs.

Based on my own experience of writing LLMs instruction inside a project codebase, I've identified a few challenges:

  • I wanted a way to create one input file per task which would adapt to many different LLMs.
  • Templating is a must have
  • Integrated in VS Code

Instruct is an open-source library and a VS Code extension to help developers integrate LLM-based features in their source code.

Sharing

Year Event
2024 Unapei – Le prendre soin au défi de l'IA
2022 Ecole LDLC > intervention de Xavier Basset Hoomano
2020 TEDx Que révèlent nos interactions avec les machines ?
2019 SIDO #SIDO2019: Xavier Basset présente HOOMANO
2018 Interview Xavier Basset
2017 AI StartUp Contest Xavier Basset (Hoomano), lauréat des Trophées des start-ups
2016 IBM Business Connect Caroussel du Louvre, 1000+ attendees