Logo: to the web site of Uppsala University

uu.sePublications from Uppsala University
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Enhancing Workflows throughDigitalization and AI: A Case Study at the Bio-Analysis and Research and Development Departments at Mercodia AB
Uppsala University, Disciplinary Domain of Science and Technology, Biology, Biology Education Centre.
Show others and affiliations
2025 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

 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.

Place, publisher, year, edition, pages
2025. , p. 79
National Category
Artificial Intelligence Other Computer and Information Science
Identifiers
URN: urn:nbn:se:uu:diva-560466OAI: oai:DiVA.org:uu-560466DiVA, id: diva2:1971568
Available from: 2025-08-12 Created: 2025-06-17 Last updated: 2025-08-12Bibliographically approved

Open Access in DiVA

The full text will be freely available from 2027-06-17 19:03
Available from 2027-06-17 19:03

By organisation
Biology Education Centre
Artificial IntelligenceOther Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 33 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf