Johannes Stiehler

Cover Image for Johannes Stiehler

About Johannes

Johannes has spent his entire professional career working on software solutions that process, enrich and surface textual information. Until the end of 2020, he served as Chief Executive Officer at ayfie Group AS. In this role, he headed the research and development of the ground-breaking search and text analytics solutions at ayfie. He was focussed on the creation of software that accelerates, improves and scales knowledge-based workflows. Before joining ayfie, he successfully headed software product development projects at Fast Search & Transfer (FAST) and SEARCHTEQ (a business division of German Telekom). He holds a master’s degree in computational linguistics. He is a regular speaker at international conferences.

More articles by the same author


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.


Rundify - read, understand, verify

Digital technology has overloaded people with information, but technology can also help them to turn this flood into a source of knowledge. Large language models can - if used correctly - be a building block for this. Our "rundify" tool shows what something like this could look like.


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.


Compliance Workflows

The various industry regulations, data protection requirements, and other regulations create a complex web of requirements that companies must meet. AI components make this business process more efficient and reliable.


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.


How to "AI" - LLMs as a Commodity

How can companies innovate using AI? How do you go beyond wrapping ChatGPT in a pretty UI?


Man-machine and machine-man

What ticket sellers and Instagrammers have in common, and how AI might cost them both their jobs.


Who reads policies anyway?

The demo of our new product "Quaestio" pits AI and paperwork against each other. It looks like the AI is winning.


5 reasons why ChatGPT is (often) not the solution

The release of GPT-4 is renewing the buzz around Large Language Models. Are these tools ready for prime time now?


Is this the death of all world-changing AI applications?

If an AI sometimes lies to me, is it of any use at all? We examine the areas of application for which lying AI is suitable and where it has no place.

Chat and other GPTs (ChatGPT and its predecessors)

What is ChatGPT capable of? Instead of uncritical applause or doomsday scenarios, a level-headed look at the underlying technologies and the possibilities that arise from them.

Cloud Naive or Cloud Native

We prefer to discuss Text AI and Natural Language Processing, but in this video we'll go over the basics. We talk about scaling, the serverless trend, and cloud-native services - all things you might be interested in.


More value per dollar

We develop products. Whether for ourselves or for customers, we invest the same enthusiasm and have the same quality standards. How we deliver the maximum added value, we describe here.


Helpful at all costs - ChatGPT and the end of the software engineer

ChatGPT may help software developers in some cases, but it won't replace them. It can be helpful to a certain degree, but its eagerness to give wrong answers can be counterproductive. (Automatically generated summary)


Online Education

There is so much information for people with a desire to learn. We help our client help their customers to find the right element of learning at the right time.


May I suggest something?

Web portals should go beyond offering a search function and implement Suggest features to make searching easier, more relevant and more enjoyable. This is possible by providing suggestions in different categories. (Summary generated by NEOMO summarizer)


Procurement System

Electronic bidding and procurement systems are designed to create an ideal fit between buyers and suppliers in professional markets. We helped our client consistently create this fit for its users through an optimal search solution.


To search or not to search

We are still not done with search – although we are at it since 2001.


What’s in a name?

Some may claim that my co-founder Florian and I simply enjoy rebranding companies on a regular basis.


International Text-Analytics Company

Based on the merger of two companies, a new market and geography opened up.


Insurance Company

One of the largest insurers in the world, our client is operation several high stakes search applications.