Mapping user-centred interfaces

All images in the pitch presentation have been generated using OpenAI/Dall-E or are icons from Microsoft PowerPoint.
Voice-over: generated using elevenlabs.io. The recordings are authorised for non-commercial use.

Workshop on identifying the disclosures regarding AI systems that are necessary to ensure reliable and trustworthy collaboration with AI.

Development status

Ready for practical use

Scientific basis

Development and implementation

Initial field trials

Evaluation and optimisation

Ready for practical use

What problem do many companies face?

AI is often implemented without taking the needs and expectations of end users into account, which frequently leads to a lack of understanding and trust in AI systems and, consequently, to reduced efficiency and acceptance. This results in a low level of transparency for users. Collaboration between humans and AI must be taken into account in order to ensure effective cooperation.

How does the tool help to solve the problem?

The tool offers a structured process for identifying user requirements at an early stage and incorporating them into the design process. This is achieved through an interactive workshop and direct dialogue with users. The tool promotes the development of AI interfaces that are intuitive to use.

How is the tool used within the company?

AI experts implement the tool through a workshop involving subject-matter experts and the workers who are to use the AI. The user requirements gathered are then analysed and mapped onto methods for ensuring the explainability of AI. These findings can then be incorporated into the development of the AI and its interfaces.

What is the time commitment involved for the company in raising this objection?

To ensure the workshop is a success, a 3-hour session with the relevant AI users and domain or process experts is sufficient to explain the pitfalls of AI software and to identify what information and explanations are needed regarding how AI works. The subsequent analysis of the results may take 3–4 working days.

What added value does the tool bring to the company?

Staff are informed about the specific features, requirements and pitfalls of AI software, which forms the basis for the responsible use of AI and the development of the right level of trust in AI. The design outcomes resulting from the workshop make it possible to provide users with the information they need to trust AI and use it effectively.

Scientific publications

[1] Liao, Q. Vera, Daniel Gruen, and Sarah Miller. 2020. “Questioning the AI: Informing Design Practices for Explainable AI User Experiences.” In Conference on Human Factors in Computing Systems – Proceedings. Association for Computing Machinery. https://doi.org/10.1145/3313831.3376590.

[2] Liao, Q. Vera, Milena Pribić, Jaesik Han, Sarah Miller, and Daby Sow. 2021. “Question-Driven Design Process for Explainable AI User Experiences,” April. https://arxiv.org/abs/2104.03483v3.

[3] Lim, Brian Y., and Anind K. Dey. 2009. “Assessing Demand for Intelligibility in Context-Aware Applications.” In Proceedings of the 11th International Conference on Ubiquitous Computing, 195–204. UbiComp ’09. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/1620545.1620576.

[4] Ehsan, Upol, Q. Vera Liao, Michael Muller, Mark O. Riedl, and Justin D. Weisz. 2021. “Expanding Explainability: Towards Social Transparency in AI Systems.” Conference on Human Factors in Computing Systems – Proceedings, January. https://doi.org/10.1145/3411764.3445188.

Practice validation within the KI-FIT network satellite (2026)

The tool was successfully tested in practice as part of the HUMAINE network satellite project KI-FIT. In a two-part series of workshops (30 January and 6 February 2026), the tool was used in collaboration with spexa GmbH (Essen) and BO-I-T to test three identified AI solution approaches: (1) a chatbot as an intelligent form-filling aid for questionnaires, (2) real-time free-text anonymisation, and (3) a motivator to increase user interaction. The workshops were rated as enriching by the participants and contributed to the planning of the project’s next steps; the application of the HUMAINE tool was successfully validated.

Contact persons
Pavlos-Rath Manakidis
Pavlos-Rath Manakidis
Institute for Neuroinformatics