Maisa, a leader in developing hallucination-resistant AI agents, today announces a $25 million seed investment led by Creandum, with participation from Forgepoint Capital, via its European joint venture with Banco Santander.
The news comes only a few months after the company raised $5m pre-seed in December 2024 from NFX and Village Global, which is backed by Mark Zuckerberg, Jeff Bezos and Eric Schmidt. Both NFX and Village Global followed on and participated in today’s round.
The new funding will support hiring across AI R&D, engineering, sales and customer success, as well as expanding Maisa’s growing footprint in Europe and North America.
Alongside the fundraise, the company is launching Maisa Studio, an agentic process automation platform which enables ‘citizen developers’ - users who are experts in their business field but without an IT background - to deploy powerful and fully auditable AI ‘digital workers’ trained through natural language.
The platform is being piloted at scale inside global banks, car manufacturers and energy companies, among others, to run multi-step, complex and compliance-sensitive workflows with full traceability and reliability.
It allows non-technical staff to onboard digital workers with the ease of onboarding new colleagues. They can easily and quickly install a digital worker to perform complex, knowledge-intensive processes with full transparency, from evaluating risk and reconciling transactions to monitoring supply chain disruptions - any task that would traditionally demand extensive hours of repetitive human effort for poorly equated output.
The digital workers require no dataset or developers, and users only need to write a series of natural language commands into the platform. The digital workers learn on the job by doing, through a method Maisa calls ‘HALP’ (human-augmented LLM processing), which is a fast and enterprise ready way to train digital workers.
Maisa was founded in 2024 by CEO David Villalón and CSO Manuel Romero, two leaders in applied and foundational AI. Villalón was formerly Chief AI Officer at Clibrain and Director of Product at Voicemod. Romero is one of the top HuggingFace contributors globally, with more than 700 open-source models and 15 million downloads per month.
Today’s raise comes less than a year since the company raised $5m pre-seed in December 2024 from NFX and Village Global, which is backed by Mark Zuckerberg, Jeff Bezos and Eric Schmidt.
Last month Maisa was named beside Google and Amazon by top US research and advisory consultancy Gartner as a leading AI agent vendor in its Hype Cycle for AI and Future of Work reports. It was the first time a Spanish startup has been mentioned in one of its influential reports.
While AI adoption is on the rise, most enterprise efforts fail or are not implemented. A new report published by MIT’s NANDA initiative last week found that 95% of generative AI pilots are failing and delivering little to no measurable impact on P&L.
Elsewhere, recent IDC data shows four in five (88%) AI pilots fail to reach production and BCG found only one in five (22%) companies have advanced AI beyond the proof-of-concept stage to generate some value.
At the same time, HR research by i4cp reveals more than two thirds (70%) of organizations report struggling to equip their workforces with the necessary AI skills. Bain found almost half (44%) of executives say lack of in-house AI expertise is a barrier to implementing AI.
Maisa eliminates such barriers.
David Villalón, co-founder and CEO of Maisa, said: “This investment is validation that AI in business must be built on trust. Our platform gives teams the power to use AI workers which not only perform with incredible accuracy and intelligence, but also explain and prove their logic, and document every step in the work process. It means users can scale AI at pace, do so safely and without the need for an entire development team to support.”
Peter Specht, General Partner from Creandum, said: “Maisa is solving one of the toughest challenges in AI: making it reliable and safe to use in mission-critical business operations. With a string of top global companies already using the technology and massive demand, we are extremely confident of seeing significant growth at scale.”
Alberto Yepez, from Forgepoint Capital International, said: “Maisa’s platform is purpose-built for compliance-conscious industries like finance, where decisions must be traceable and outcomes consistent. The company’s early success demonstrates there’s real market pull for AI done the right way and Studio, launched today, will make it easy for anyone in an organisation to use digital workers quickly and effectively."
Model agnostic
Maisa’s system is model-agnostic - turning general-purpose LLMs into safe, specialized AI agents that execute reliably across regulated industries. The platform can run in Maisa’s secure cloud or be deployed privately to meet enterprise compliance needs.
It is built on a computable system called the Knowledge Processing Unit (KPU), a proprietary reasoning engine that turns large language models (LLMs) into trustworthy task executors, delivering faithful and reliable results.
Rather than relying on probabilistic guesswork, Maisa’s digital workers are powered by AI which directs them through logical, step-by-step computation to undertake tasks. Every action taken by a digital worker is recorded in what Maisa calls its Chain-of-Work: a transparent, auditable record of logic and execution that lets businesses see exactly how each outcome was reached, reducing hallucinations.
Enterprise deployment
Studio’s early traction shows the potential for this new form of automation:
A global investment bank has replaced its manual media screening process with Maisa digital workers, which extract relevant facts from news articles, assess reputational risk and produce audit-ready summaries in minutes, at scale.
A large financial services firm has automated transaction checking and reconciliation using Studio, enabling it to filter out 99% of false positives and see a 10x improvement in productivity per person. The entire rollout was completed with no engineering work - just three onboarding sessions.
These are not experiments or prototypes. They are operational deployments, in production, inside organizations with high regulatory and accuracy requirements.
Studio integrates with more than 450 third-party systems out of the box. It connects automatically to any documented API and, when updated with specification, to any custom undocumented API. Automations can be triggered via web, email, api or webhook, and updated continuously through the same conversational interface used to create them. It also interacts with websites and legacy systems.