Rundify - read, understand, verify

Johannes Stiehler
Cover Image for Rundify - read, understand, verify

Each and every one of us has to absorb and process information every day and be able to retrieve it at the right moment. We are inundated with information from birth, through school and into our everyday working lives, but we can absorb very little of it and even less of it can be retrieved or used later.

On the one hand, technology has exacerbated this problem, but on the other hand, at NEOMO we have always been convinced that technology can also help solve it. That is why we still enjoy implementing search applications for large knowledge repositories. By helping people find the right information, we reduce the negative effects of information overload and maximize the positive effects.

When large language models first appeared, we realized that this could be another technology to change the way people deal with knowledge. Not because they could replace search engines or even human staff - they are far too imprecise and unreliable for that. But because they make it possible to "translate" content flexibly and scalably into other formats: LLMs can reduce a convoluted email to the point, summarize a 200-page PDF and turn a few bullet points into a text.

Consequently, we have started researching a specific application of LLMs as early as 2021: How can we automatically check whether information has been absorbed and understood? Pretty much everyone faces this problem in everyday life:

  • A teacher hands out a factsheet to his students. 50% read it, the others build paper airplanes from it, only 10% can later remember the knowledge it contains.
  • An HR manager gives a webinar on the GDPR. 80% of the employees continue to work and let the webinar run on the second screen.
  • A student reads dozens of factual texts to prepare for an exam. Shortly before the exam, he doesn't really know whether he has retained the key points in his memory.

With Rundify, we have recently launched a tool that creates a quiz from every factual text using a simple user interface and state-of-the-art technology. This quiz can then be sent to any number of participants and their results evaluated. All you need to do is upload the relevant text as a PDF, approve the generated questions and simply send a link by email. There you go...

  • The teacher creates a short quiz on the information sheet and knows who has read and understood it.
  • The HR manager sends out a test on the webinar content that not only assesses the most important content, but also simultaneously reiterates it. In this way, the employees remember the information and he can prove at any time that the staff have been properly trained.
  • If the student uploads all the texts he reads to Rundify, he can refresh and confirm his knowledge the evening before the exam using multiple-choice questions.
Working with Rundify

Rundify is a simple tool with countless possible applications. We believe that it can be an interesting building block on our way to dealing with knowledge more effectively.

Johannes Stiehler
CO-Founder NEOMO GmbH
Johannes has spent his entire professional career working on software solutions that process, enrich and surface textual information.

There's more where this came from!

Subscribe to our newsletter

If you want to disconnect from the Twitter madness and LinkedIn bubble but still want our content, we are honoured and we got you covered: Our Newsletter will keep you posted on all that is noteworthy.

Please use the form below to subscribe.

NEOMO GmbH ("NEOMO") is committed to protecting and respecting your privacy, and we'll only use your personal information to administer your account and to provide the products and services you requested from us.

In order to provide you the content requested, we need to store and process your personal data. If you consent to us storing your personal data for this purpose, please tick the checkbox below.

You may unsubscribe from these communications at any time. For more information on how to unsubscribe, our privacy practices, and how we are committed to protecting and respecting your privacy, please review our Privacy Policy.

Follow us for insights, updates and random rants!

Whenever new content is available or something noteworthy is happening in the industry, we've got you covered.

Follow us on LinkedIn and Twitter to get the news and on YouTube for moving pictures.

Sharing is caring

If you like what we have to contribute, please help us get the word out by activating your own network.

More blog posts


ChatGPT "knows" nothing

Language models are notoriously struggling to recall facts reliably. Unfortunately, they also almost never answer "I don't know". The burden of distinguishing between hallucination and truth is therefore entirely on the user. This effectively means that this user must verify the information from the language model - by simultaneously obtaining the fact they are looking for from another, reliable source. LLMs are therefore more than useless as knowledge repositories.


ChatGPT and the oil spill

Like with deep learning before, data remains important in the context of large language models. But this time around, since somebody else trained the foundation model, it is impossible to tell what data is really in there. Since lack of data causes hallucinations etc. this ignorance has pretty severe consequences.


Meaningful autocomplete still missing

We take a look at major German media portals and how they deal with the issue of search and autocomplete. A spoiler in advance: The situation remains sad.