Software is the universal language of innovation, powering everything from global enterprises to small businesses.
Creating software, however, remains the domain of a select few — those with years of technical training and engineering expertise. Despite the advent of AI assistants like ChatGPT and GitHub Copilot, turning an idea into working software still demands deep technical knowledge.
Agemo exists to change this paradigm. We envision a world where anyone can create sophisticated software tools simply by describing what they want to achieve. The future of software creation1 lies not in writing code, but in expressing ideas and problem solving.
This idea would have seemed impossible just a few years ago. Since then, large language models (LLMs) have revolutionised the practice of writing code, finding a killer use-case in programming assistants and autocomplete. However, the fact that software creation remains stubbornly inaccessible reveals a deeper truth: the real challenges exist and always have existed beyond just code.
Building software involves understanding requirements, designing systems, ensuring reliability, and managing deployment — aspects that demand human-level reasoning capabilities beyond the reach of traditional AI systems.
This insight drives our mission at Agemo.
We're developing AI systems that can reason about software at a fundamental level — systems that understand not just how to write code, but how to transform ideas into reliable, production-ready solutions.
Designed to be Turing-complete2 and with self-improving abilities, these systems will be the foundational engine of our vision to bring software creation to everyone.
The AI Status Quo for Intelligence
With increasing scale, transformer-based LLMs have demonstrated remarkable abilities at a wide range of complex tasks, from answering medical queries to performing olympiad-level mathematical problem-solving. Within the software domain, these models impress with their ability to produce semantically and syntactically functional code, solve isolated programming challenges and provide coherent explanations for their solutions.
Yet, something crucial is missing: the ability to reason about software as a complete system.
While it is tempting to keep extrapolating and assume that AI-powered software creation will be solved by simply scaling up transformers to ever-larger datasets and parameter counts, their failure modes (remember glue on pizza?) reveal a fundamental limitation. LLMs by themselves aren’t really reasoning about the world — they’re reproducing patterns from their training data, even when those patterns represent dangerous or nonsensical outliers.
This limitation becomes critical in software development. Consider how an experienced software developer approaches a new problem. They don't immediately start writing code. Instead, they think through the requirements, consider different architectural approaches, plan how to test and validate the solution, and design for maintainability and scalability. They reason about the software as a whole, understanding how different pieces will work together and anticipating potential issues before they arise.
To emulate this kind of systematic reasoning, we must look beyond scale for a solution.
The path forward lies in developing hybrid approaches that combine the pattern recognition strengths of neural networks with the rigorous reasoning capabilities of symbolic systems. This isn't just about making current approaches incrementally better. It requires rethinking how AI systems approach software development: from treating it as a sequence of tokens to be predicted, to viewing it as a reasoning problem where solutions must be systematically planned, implemented, and verified.
Reasoning beyond Code Generation
Driven by our conviction that true software reasoning requires more than just pattern matching, we have developed Dunia, a neurosymbolic system for software reasoning, continuous validation, implementation and deployment. It approaches software development the way experienced engineers do and at its core lies a neurosymbolic reasoning engine that can decompose complex requirements into concrete plans, verify its decisions through formal methods, and learn from its own successes and failures.
We call this Reinforcement Learning from Machine Feedback.
This methodology enables us to bridge the gap between human intent and working software in ways that pure neural systems cannot.
Today, Dunia can take high-level descriptions of user requirements and transform them into fully functional backend systems. It handles everything from initial design through implementation, testing, and deployment — all while maintaining a clear chain of reasoning that can be inspected and verified.
From automating repetitive workflows to building single-use APIs, Dunia can tackle a wide range of software development tasks that previously required teams of engineers.
While the scope of software it can generate today focuses on single-purpose backend systems, this represents just the beginning of our journey. Our research continues to push the boundaries of what's possible in automated software development, with automated function composition, dynamic UI generation, statefulness, and complex system architectures already on the horizon.
The implications of this technology extend far beyond just making developers more productive. By abstracting away the technical complexity of software creation, this opens up new possibilities for how we think about and create software.
The product manifestation of such a system will pave the way for a new class of software workers with a shift from writing code to expressing intent - from telling computers how to do something to telling them what we want to achieve. From “Software-as-a-Service” to “Service-as-a-Software”.
Building Agemo
Building a generational company starts with a special group of individuals. Our engineers, researchers, and product experts bring together expertise from leading institutions such the University of Cambridge, École Polytechnique, Imperial College, and The Alan Turing Institute, complemented by industry experience from Microsoft, Palantir, Meta, PolyAI, TikTok, and Goldman Sachs.
But credentials are just one side of the equation. We index on grit over talent, we care about excellence of the craft, and we are relentless in our focus. We’re driven by a shared conviction that building truly intelligent systems4 requires more than following the status quo. Our approach to innovation is guided by three core principles:
- Systems over models. We believe that scaling current transformer architectures alone will not lead to systems capable of human-level reasoning. We’re betting on neurosymbolic approaches that combine the best of neural and symbolic methods to create truly intelligent systems.
- Owning the whole value chain. AI is an enabler, not a panacea. With intelligence becoming commoditised, defensibility comes from building solutions that fuse all layers of the stack — from infrastructure to application — to deliver the best possible user experience.
- Data, network effects and velocity remain the moat. The fundamentals of building an enduring technology company remain unchanged, with or without AI. We obsess over crafting elegant solutions with compounding effects to solve the most complex problems in software creation.
We are fortunate to be backed by Fly Ventures and firstminute capital, alongside angel investors and advisors such as Olivier Pomel (CEO of Datadog), Jon Reynolds (Founder of Swiftkey), Tim Rocktäschel (Head of Open-Endedness at Google Deepmind), Mehdi Ghissassi (Head of Product at Google Deepmind), Amar Shah (co-founder of Wayve), Roxanne Varza (Director of Station F), senior researchers from Meta’s Llama team and many others.
This is just the beginning of our journey and the future cannot wait. If our mission resonates with you, we invite you to join us or follow us (X and LinkedIn).