We use AI to solve problems that were considered unsolvable until recently, within a few months and at a fixed price. We come from AI research at TU Wien, and we build systems that hold up in daily operation.
We are most interested in problems where nobody can yet say whether they are solvable. Contact →
What we do
AI Sprint: from idea to working prototype in three to six months
The price is fixed in advance. At the end you have a working system and know whether the problem can be solved and what it will take to put it into operation. If the problem convinces us, we carry part of the risk ourselves.
Into operation
We run what we build, on your own servers if you wish. Then your data stays with you.
Orientation
Together with you we find use cases, assess them and decide where to start. We also tell you which ideas are not worth pursuing.
Training
Drawn from our teaching at TU Wien and tailored to your organisation: understanding AI well enough to take part in the discussion for executives, hands-on skills for specialist and development teams, up to agentic software development.
Confidential sparring for leadership
For board members, managing directors and senior civil servants we offer one-to-one conversations without an audience. Ask every question about agentic AI, governance and liability that you would rather not ask in front of your own organisation.
Applied research
Research collaborations and funding applications, together with partners from universities and research institutions.
Why people come to us
“We have hundreds of thousands of pages nobody can read.”
Handwriting, scans, forms, legacy holdings. We make them searchable and index their content. Your experts check what the AI recognises before it is adopted.
“When Ms M. retires, her knowledge goes with her.”
In the coming years many experienced colleagues will retire, taking with them knowledge that was never written down. We help secure that knowledge while it is still there, and make findable what lies scattered across files and documents.
“Our people use ChatGPT, including with data that doesn’t belong there.”
We set up AI models on your own servers and anonymise data before it is processed externally. That gives your people an official route, and they no longer need the unofficial one.
“We search by keyword and still don’t find what belongs together.”
We match what fits in meaning, even when the terms differ: CVs and vacancies, start-ups and corporations, a current project and comparable past ones.
“We have twenty AI ideas and don’t know which one is worth it.”
We assess them with you and build the most promising one in an AI Sprint.
“The board is supposed to decide on AI, but nobody wants to admit what they don’t know.”
That is what our confidential one-to-one sparring is for.
Many requests fit none of these patterns. Get in touch anyway.
Selected work
- Vienna City LibraryHistorical handwriting, machine-readable
- A vision language model of our own, trained on the European supercomputer Leonardo. Four models vote word by word. Even on pages of Kurrent, the historical German handwriting, that were not part of the training, the quality is high enough to open up extensive collections. The library’s experts review the transcriptions.
- International retail groupThe entire project portfolio in view
- A large, centrally managed portfolio of digital projects that had never been analysed as a whole. We show which projects resemble each other, which past projects are similar to a current one and how they turned out. That way, projects at risk can be spotted while there is still time to steer.
- Financial services providerOfficial documents, processed automatically
- For an Austrian financial services provider we process official documents from PDF all the way to matching against the company database. The pipeline runs in daily operation on the client’s own AI server, and the documents never leave the company.
- National trust labelIT security
- We built the platform and have been operating it for years: the application process for three levels, the connection of audit partners and the automatic evaluation of the security questionnaires.
- Industrial groupPlanning and staffing
- For an Austrian industrial group we built the central planning and staffing system: time tracking, deployment and project planning, apprentice qualifications, interfaces to payroll and other systems. We have been developing it further for years.
We are happy to name further references in person.
Why not simply a big consulting firm?
You talk to the people who do the work
We are a small team. Whoever discusses your project with you also works on it.
We come from research
We teach generative AI at TU Wien, and Georg Gottlob has been researching artificial intelligence for decades. That is why we see early what is becoming possible.
After an AI Sprint you know where you stand
At the end a prototype is running, or you know why it fails. The price is fixed in advance.
Independent of vendors
We have no partner agreements with cloud or model providers and sell no licences. We recommend what suits your task, often a model on your own servers.
Our systems are in use
Our clients use what we build in daily operation, some of it for years.
Focus areas
- Understanding documents. Forms, official documents, handwriting, historical holdings, including where conventional text recognition fails.
- Preserving knowledge. Securing experience and making knowledge scattered across files and documents findable.
- Assessing texts. Judging against a transparent standard: job descriptions, submissions, contracts.
- Matching and recommendation. Bringing supply and demand together by meaning.
- Local, sovereign AI. Models that run on your premises and are trained on European infrastructure.
- Agentic systems. Developing software with AI agents. We work this way every day and teach it.
- AI Act and governance. What you need to do, and how to demonstrate it credibly.
- Data protection through semantic anonymisation. Measuring re-identifiability and reducing it in a targeted way.
- Bilateral AI. Combining neural networks with rules so that decisions remain verifiable.
Stance
People decide
We build systems that support people in their work. The decision stays with them.
Not every problem needs a chatbot
A chat window shifts the work onto the user: they have to know what to ask and check every answer. We build AI into the place where the work already happens, with results that can be checked at a glance. Agents get only as much room to act as the task requires.
Sovereign intelligence
For us, sovereignty means using AI competently and staying in charge of it. Organisations need their own expertise for this; Austria and Europe also need their own infrastructure and control over their data.
You need to see why the AI does what it does
Our systems give reasons for their assessments, link recognised text to its source and show the cases a recommendation is based on. That way, what a system decides can be checked.
Digital humanism
We are committed to the Vienna Manifesto on Digital Humanism and serve on the board of the Digital Humanism association. AI should give people more room to shape things.
For policy makers, the public sector and the media
Austria is making decisions about artificial intelligence in public administration, education, research and infrastructure right now that will have effects for decades. They call for first-hand advice.
We are available to ministries, public authorities, interest groups and newsrooms for background talks, statements, expert opinions and lectures. We are independent of vendor interests and know what research can do today.
AI in public administration
Many public offices have long been using AI, often through private accounts with external services and sometimes with confidential data. At the same time, federal and state governments are building central services. We offer an independent assessment: which tasks are suitable for AI, what the available tools achieve there and what to look out for with data and data protection. On request, we accompany a small pilot for which the conditions for ending it are agreed in advance.
Topics we speak on: AI in public administration · sovereign AI infrastructure for Austria · AI in schools and universities · implementing the AI Act · AI and public discourse · digital humanism
Teaching, research, talks
Generative AI at TU Wien
We have taught the subject since 2023, now in two courses (theory and practice). So far there have been well over a thousand students and hundreds of supervised team projects, in which knowledge management is a recurring focus. Consulting firms also send their staff to our courses. We work closely with the Christian Doppler Laboratory for Recommender Systems.
Research
Patents on information extraction, access documents and conversational decision processes, publications on visual document understanding, supervision of master’s theses.
From our research: semantic anonymisation
Anyone who wants to share documents containing personal data, or process them with AI, has to anonymise them. Redacting names is not enough, because occupation, age and neighbourhood together can also make a person recognisable. Our multi-agent approach finds such indirect identifiers considerably more reliably than conventional methods and removes them from the texts.
Talks
We speak regularly at international conferences, at universities, in continuing education and in companies, including the Wiener Vorlesung, the DigHum Lecture Series and the TU Wien Academy for Continuing Education.
Team
Georg Gottlob
First AI professor at TU Wien, professor at Oxford and Calabria. Fellow of the Royal Society, Wittgenstein Award, Ada Lovelace Medal. Serial founder, each company successfully acquired (McKinsey, Meltwater).
Bernhard Krüpl-Sypien
Managing Director. Teaches generative AI at TU Wien and coordinates the Generative AI group at CAIML. Software architect, inventor of several patents, board member of the Digital Humanism association.
Johannes Oster
Lead AI Engineer. Teaches generative AI at TU Wien and speaks at the Wiener Vorlesung and in the DigHum Lecture Series, among others.
David R. Prasser
Entrepreneur and innovation strategist, founder of StartUs Insights. He assesses which ideas stand a chance in the market, who else is already working on them and how a prototype becomes a business.
Contact
Tell us what you are stuck on.
A first conversation is free and without obligation. Afterwards you will know whether an AI Sprint is worth it.
hello at became.ai
(Apply your human knowledge to turn this into an email address.)