Mercodia AB aims to transition from manual procedures to a more automated workflow and
to explore the potential role of digital tools and artificial intelligence (AI) in their operations.
As part of this process, the workflows of the Bio-Analysis and the research and development
departments were mapped to identify key bottlenecks.
In the Bio-Analysis department, the primary challenges were mainly the manual and time-
consuming creation of correctly formatted output files for their customers and quality control
of the data. To address these issues, a software application was developed with the following
tools: LIMS Converter and Quality Check. When testing the speed of these functionalities, the
times were evaluated to be 3 minutes and 1 minute respectively. This represents a significant
improvement in time efficiency compared to the current manual processes at Mercodia, which
are estimated to take between 1.5 to 3 hours for file generation and 1 hour for quality control.
In contrast, the research and development department, with its more variable workflows,
requires more flexible tools such as AI. A literature review was conducted to investigate how
AI could be integrated into their workflow. Based on the results of this study, prompt testing
was performed using two different large language models. These tests highlighted that prompt
engineering together with structured data submission are critical factors affecting AI
performance.
These findings suggest that automation and AI have the potential to reduce the manual
workload at Mercodia AB. Further development and testing are recommended to validate
these tools in industry environments.
2025. , s. 79