dottxt raises $11.9M to make LLMs speak language of every application
dottxt, an emerging platform designed to enhance interactions with large language models (LLMs), has successfully raised $11.9 million across its Pre-Seed and Seed funding rounds, all within just over seven months.
The funds will primarily support the expansion of dottxt’s team, following a sharp rise in demand for its open source library and optimised proprietary tools since early 2024.
The funding was split between a $3.2 million Pre-Seed round, completed in December 2023 and led by the European tech-focused VC firm Elaia, and an $8.7 million Seed round, closed in August 2024 and led by EQT Ventures.
Several other notable participants also joined the rounds, including Seedcamp, Common Magic, Kima, and prominent figures like Roxanne Varza (Station F), Erik Bernhardsson (CEO, Modal Labs), Julien Chaumond (CTO, Hugging Face), Bob van Luijt (CEO, Weaviate), and Jean-Louis Queguiner (CEO, Gladia).
dottxt pushes LLM technology beyond basic conversation models, offering a platform that gives users greater control over how they interact with AI systems. Its tools enable structured information requests, seamlessly integrating LLMs into existing digital ecosystems.
With dottxt, LLMs become more reliable and versatile. Data scientists, for instance, can query databases using natural language and be assured of accurate results. Recruiters, overwhelmed with CVs, can use the service to filter candidates by specific criteria, significantly cutting down on time. Similarly, users can submit large sets of images and extract targeted information based on defined attributes with ease.
The rapid growth in AI-driven chat models has contributed to global awareness of AI technologies. Early leaders in the field, such as OpenAI and Cohere, have publicly acknowledged the use of dottxt’s open source code in developing their own LLMs.
Rémi Louf, CEO at dottxt, said: “Everyone will be using structured generation in a few years, there is no doubt about that. Model providers, including OpenAI, are lagging in terms of speed and capabilities, and we’re here to fill that gap. With these funds, we will keep pushing the limits of this technology and make it more widely available for everyone. We are shaping a future where generative AI delivers on the kind of automation we were promised.”
Co-Founders Rémi Louf, Dan Gerlanc, and Brandon Willard have worked together in various capacities for the past four years. During their last stint at a New York-based AI firm, Normal Computing, they started encountering issues with GPT-4, notably extracting data and information in a systemized order to bypass vast amounts of manual work. It was in solving this issue that the team ultimately invented a solution that no one else had been able to find, thanks to their unusual background in statistical modelling and compiler technology.
A year later, the code they open-sourced has received over 3 million downloads, 600,000 of which were in the last month. Companies, large and small, are using it in production.
Julien Hobeika, Partner at EQT Ventures, added: “From our first discussion with dottxt, we saw their potential to turn the stochastic nature of LLMs into something more programmatic and deterministic, enabling deep integration into software systems. This aligns with our belief that the future of AI agents will be shaped by those who can build the essential frameworks that make LLMs truly usable at scale in critical enterprise systems. We’re excited to support dottxt as they lead the creation of this critical infrastructure.”
The funds will be used to expand the team, bolster the number of software engineers, and bring in a Chief of Staff. Currently, at nine, the team has added six more employees, who will be focused on expanding the reach of dottxt’s technology and distributing it to enterprises and developers alike.
Clement Vanden Driessche, Investment Director at Elaia, said: “In a new software era led by the emergence of AI agents, developers experiment with a strong need to constrain the LLM models' behavior to make the final applications faster, robust, and reliable. At Elaia, we are proud to support dottxt team, from their inception and even before, who developed a proprietary technology inspired by compilers. We are excited to see them grow in the open-source ecosystem with an incredible developers adoption to date.”
Ultimately, dottxt's mission is simple: to make AI programmable so its potential meets the reliability demands of real-world systems. With $11.9 million in fresh funding, it is well-positioned to transform this vision into reality.
Sia Houchangnia, Partner at Seedcamp, said, “LLMs already have the potential to unlock tremendous value, but their lack of reliability has been the key barrier to wider adoption. dottxt solves this problem. By applying their expertise in Bayesian statistics, Remi, Brandon, Dan, and their team have created the most accurate and high-performing platform for structured generation. We are proud to be day-one backers of the company and are convinced that dottxt has the potential to become the default framework for LLM programming.”
For more startup news, check out the other articles on the website, and subscribe to the magazine for free. Listen to The Cereal Entrepreneur podcast for more interviews with entrepreneurs and big-hitters in the startup ecosystem.
