It’s time again to make an important decision.
Do you flip a coin, roll the dice, or ask the Magic 8-Ball? Or do you return to first principles, consider everything you’ve learned, and reason your way to a solution?
We know what we would do. Which is why it feels a little strange that the services we’re increasingly looking to for answers are built around probabilities. Yes, we’re talking about AI: our latest and greatest technological innovation.
For acts of creativity, AI’s fuzzy logic can be remarkable at helping us imagine new solutions. But in the complex world of business, we need a lot more accountability. We need airtight, traceable processes for getting to answers… as much as we need the answers themselves. We demand a new kind of common sense made for our new AI era.
In short, we need evidence to justify important decisions like who gets a loan, which insurance claims are denied, what drugs get researched, or deciding who gets laid off. And with today’s AI, this evidence is abstracted into oblivion… and the risk of hallucinations threaten to make it all useless anyway.
And so, less than 6% of corporations are actively using AI to do anything more than create question and answer bots. To make AI truly invaluable to businesses, we need a new way of thinking. Throughout history, humans have developed computational systems, formal logic, and scientific methods to verify our thinking. Can we do the same for AI?
We believe the solution isn’t training larger models, illuminating their chain of thought, or implementing RAG systems, which are all still based on the same fundamental issues. So, we believe the path forward lies in a new kind of computing system that combines the creative problem-solving capabilities of AI with the determinism of traditional computational systems. An AI computer that shows its chain of truth, not just its chain of thought.
In this world, AIs can be trusted to act as intelligent problem solvers executing tasks, not mysterious oracles giving inscrutable answers. To us, this is the key that will take AI into its next age of utility. When AI evolves from a black box… to an open book.
Maisa is not an AI or an LLM, but a system for making them work better.
It’s a new kind of automation tool for enterprises, data teams, builders, and tinkerers who are tired of chasing ghosts and trying to divine the meaning behind AI’s answers. A self-learning intelligence built on fact, not fiction.
With Maisa, you can create accountable AI agents you can plug in to any part of your business. Define your desired outcome, set your goals, give them access to company knowledge and tools, and instruct them using natural language. Then, they approach problems by navigating all your knowledge, not just retrieving it, and processing information with a clear, auditable logic that’s easily traceable.
Think of Maisa as the next evolution of Robotic Process Automation. A system that makes reliable and intelligent automation truly possible. It’s a new way to ensure your automations are always working off the latest and greatest company-know and process. And even coming up with new processes of their own.
The core of Maisa is our Knowledge Processing Unit (KPU), which reasons and executes over multiple, flexible steps to reach your desired outcome. For each step, it takes action, leveraging tools or APIs as needed, and then computationally executing and deploying the results in production. With this much traceability, your time to production for new automations goes from weeks or months to days.
For example… When asked about the capital of Spain, our system doesn’t simply state “Madrid” with statistical confidence. It seeks a source of truth within a virtual context window (VCW) of all your company knowledge, extracts information, and crucially, shows how it got there. It’s AI… finally showing its work.
With every action fully auditable, it’s easy to continuously improve outcomes over time, and even update your company knowledge and instructions to make processes more replicable. In other words, Maisa may not always be right — but like with a human worker, you’ll know exactly where it went astray along the chain of facts it used to get there.
This is a level of transparency, efficiency, and reliability that businesses demand, and pushes the work of AI forward toward an intelligence we can all recognize. Because to us, intelligence is a process much more than it is a pattern.
We are twelve technologists from Spain: mathematicians, philosophers, and AI pioneers who see a looming crisis ahead of us. Without accountability and traceability for AI, we’re rapidly moving to a world where important decisions are made without human input… Toward a world built only on trends and consensus, not company values and knowledge.
So, our mission is audacious: to make AI accountable in a world looking for easy answers to complex problems. To us, this requires a new kind of computing paradigm. Instead off transistors, we use weights and networks. Instead of a CPU, we use our KPU: a breakthrough system that forces AI to think using first principles.
We believe that artificial intelligence is currently at its protocol stage, much like the early internet, waiting for the right tool to make it predictable, usable, and reliable for humans. So, we believe that the future of AI lies not in bigger models, but in smarter architectures that can guarantee reliability while harnessing the power of artificial intelligence.
This is a future where AI is just a part of a new computer we use each day. This places the decision making power back where it belongs…. with the people operating them.
David and Manu – Founders
