Publicação
Agents at work: utilizing design patterns for AI - agent workflow automation
| datacite.subject.fos | Ciências Sociais::Economia e Gestão | |
| dc.contributor.advisor | Obermeier, Daniel | |
| dc.contributor.advisor | Batikas, Michail | |
| dc.contributor.author | Veltrup, Leon | |
| dc.date.accessioned | 2026-05-27T15:22:45Z | |
| dc.date.available | 2026-05-27T15:22:45Z | |
| dc.date.issued | 2026-01-28 | |
| dc.date.submitted | 2025-12-17 | |
| dc.description.abstract | This thesis evaluates the automation potential of knowledge work tasks using multi-agent AI frameworks. A structured scorecard assesses task suitability across project roles. Selected tasks are implemented with distinct agent design patterns in CrewAI, using GPT-4o. Performance is evaluated via workflow-level metrics, including Task Success Rate and Effective Task Success Rate. Findings reveal that pattern-specific configurations significantly influence agent success, robustness, and resource efficiency. The study provides empirically grounded guidance onorchestrating design patterns for agents with varying task complexity in business analytics workflows. | eng |
| dc.identifier.tid | 204242380 | |
| dc.identifier.uri | http://hdl.handle.net/10362/203507 | |
| dc.language.iso | eng | |
| dc.relation | UID/00124/2025 | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | AI agents | |
| dc.subject | Workflow automation | |
| dc.subject | Model evaluation | |
| dc.subject | Task selection | |
| dc.subject | Agent performance | |
| dc.title | Agents at work: utilizing design patterns for AI - agent workflow automation | eng |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| thesis.degree.name | A Work Project, presented as part of the requirements for the Award of a Master’s degree in Business Analytics from the Nova School of Business and Economics |