Claude credited as co-creator of programming language Elo

A Belgium-based software developer and founder of multiple tech companies has created a new programming language called Elo, with a notable twist: he credits Anthropic's Claude Code as a co-creator. The project, which started on December 25, 2025, showcases a deep collaboration between human expertise and AI assistance, resulting in a complete language ecosystem built in roughly 24 hours of active work.

Bernard Lambeau, founder and CTO of Klaro Cards and CEO of app consultancy Enspirit, documented the process in a series of blog posts. The first post explicitly names Claude as a co-author, stating: "In roughly 24 hours of collaboration, we built a complete expression language with a parser, type system, three compilers, a standard library, a CLI tool, and a documentation website. Not bad for a day's work."

What Happened: A 24-Hour Language Sprint

Elo is an expression language that compiles to JavaScript, Ruby, and SQL. Its purpose is to provide a portable way to handle common data tasks like form validation, e-commerce order processing, and subscription logic. The language aims to be a safe, simple alternative to mainstream programming languages for non-experts, particularly in the context of no-code tools.

Lambeau, who holds a PhD in software engineering and has three decades of development experience, documented his entire process. The project's repository includes over 100 specific tasks he used to direct the AI model. He also published a video describing his AI pair programming methodology.

"I started in a setting where Claude Code asked for permissions every 20 seconds and I was checking everything it did," Lambeau explained. "After a few successes, I quickly set up safe environments to be able to let Claude Code run in full autonomy (isolated computer & isolated Linux user, or running in a Docker image)."

The Methodology: AI as an Autonomous Partner

Lambeau's approach evolved from constant supervision to strategic oversight. He uses a "plan mode" for complex tasks where he discusses requirements with Claude, reviews the proposed plan and test strategy, then switches to "autonomous mode" for execution.

"I review the plan, make sure we have a test strategy that's sound, then switch Claude to autonomous mode and look at the tests, code & results afterward," he said. "That's very similar to a lead-dev/CTO + QA role, btw; it's just much faster than with human devs."

The key to success, Lambeau emphasizes, is a rigorous testing methodology. "Claude Code falls short if you don't have a great methodology. It needs feedback loops to work fine; otherwise, it derails," he explained. "On both Elo and Bmg.js, I've started by making sure the testing methodology was effective and scientifically sound. Claude writes the tests, executes them, discovers where it's wrong, and corrects itself. Impressive."

This approach allows him to verify code correctness without reading every line. "If I read the tests, agree with them, and can check myself that they run fine, I'm 95 percent sure it's already correct as a black box (not even reading the code)," he said. "Then I can check the architecture and code quality as a white box by having a general look at the code, but I don't have to understand every detail."

The Broader Context: AI-Assisted Development

Lambeau is not the first to develop a programming language with AI assistance. Similar projects include Steve Klabnik's Rue (2025), Geoffrey Huntley's Cursed (September 2025), and Avital Tamir's Server (with the caveat that it's not for actual use). This trend reflects a broader movement where AI tools like Cursor have been used to create browsers and text editors.

However, Lambeau's project stands out for its comprehensive documentation and clear methodology. He has published the entire prompt sequence used to create Elo, providing a transparent look at how an expert developer guides an AI through complex software creation.

The Human Element: Expertise as a Prerequisite

Despite the impressive speed and output, Lambeau is clear-eyed about AI's limitations. "Claude Code requires experts (so far)," he stated. "You still need to guide it a lot to keep the quality high enough. You need very strong expertise to do it effectively. Currently (Claude will still improve a lot), if you don't have the expertise, you certainly end up with a big mess of unmaintainable code."

This sentiment echoes a common theme in AI-assisted development: AI tools amplify expertise rather than replace it. Lambeau draws an analogy to music production tools from half a century ago: "These tools enabled a lot of people who weren't great musicians to make music. But they didn't instill musical skill, and they produced the most interesting work in the hands of practiced musicians."

The cost of this collaboration has been a Claude Max subscription at €180 per month. In that time, Lambeau completed Elo, finished the Bmg.js project, completed its documentation, and created the first version of a Try page. "It would have required several weeks to do the same manually myself, and several months to ask another developer to do it," he noted.

The Vision: Safer Programming for a No-Code World

Elo isn't just an experiment in AI collaboration; it's an extension of Lambeau's academic work and his interest in the Relational Model. As a lecturer for database courses at Belgium's UCLouvain, he sees a critical need for better programming languages in no-code tools.

"I'm absolutely convinced that we need better/safer/simpler programming languages inside no-code tools and when interconnecting them (e.g., Zapier, Make, n8n, etc.)," he said. "Mainstream programming languages are very complex, error-prone, sometimes dangerous, and the programs are difficult to review for non-experts."

He points out that even simple data tasks become cumbersome. "Validating the schema and constraints of a data file at runtime tends to be a nightmare in existing languages. It's not built-in in any mainstream language; you immediately need validation libraries; most of them are limited in what they can easily check, so you need to add dedicated boilerplate code."

In a world where non-technical people will write untrustworthy code with AI assistance, Lambeau argues we need safer execution environments. "Elo aims at providing a safe & simple alternative," he said. "It will be a limited language (non-Turing-complete, as we say) but super safe & simple, and usable in 80 percent of common data use cases."

The first no-code tool to integrate Elo will be Klaro Cards, Lambeau's own product. The language is available at elo-lang.org, with related projects including Bmg.js and its documentation at relational-algebra.dev.

What Changes: A New Development Paradigm

Lambeau's project demonstrates that AI can be a legitimate co-creator when paired with human expertise and rigorous methodology. It shows how experienced developers can leverage AI to work at unprecedented speed while maintaining quality through strategic oversight and comprehensive testing.

However, it also reinforces that AI tools are not a shortcut for novices. The complexity of software engineering—understanding architecture, making design decisions, and ensuring maintainability—still requires deep expertise. AI can execute tasks quickly, but humans must guide the vision, set the strategy, and validate the results.

For the broader development community, Elo represents both an opportunity and a challenge. As AI tools become more capable, the value of human expertise may shift from writing code to designing systems, setting standards, and ensuring quality. The developer of tomorrow may be less of a coder and more of an architect, using AI as an infinitely patient, tireless assistant.

The project also raises questions about authorship and credit in AI-assisted work. By explicitly naming Claude as a co-creator, Lambeau sets a precedent for transparency in AI collaboration. As these tools become more integrated into development workflows, the industry will need to establish new norms for attribution and responsibility.

For now, Elo stands as a concrete example of what's possible when human expertise meets AI capability—not as a replacement, but as a partnership. As Lambeau puts it, "Elo isn't just a demonstration that AI can write code. It's a demonstration that humans and AI can build together – each contributing what they do best."

The language is open source and available for exploration at elo-lang.org.