The University of Southampton
University of Southampton Institutional Repository

Exploring GenAI in software development: insights from a case study in a large Brazilian company

Exploring GenAI in software development: insights from a case study in a large Brazilian company
Exploring GenAI in software development: insights from a case study in a large Brazilian company

Recent progress in Generative AI (GenAI) impacts different software engineering (ES) tasks in software development cycle, e.g., from code generation to program repair, and presents a promising avenue for enhancing the productivity of development teams. GenAI based tools have the potential to change the way we develop software and have received attention from industry and academia. However, although some studies have been addressing the adoption of these tools in the software industry, little is known about what are developers' real experiences in a professional software development context, aside the hype. In this paper, we explore the use of GenAI tools by a large Brazilian media company that has teams developing software in-house. We observed practitioners for six weeks and used online surveys at different time points to understand their expectations, perceptions, and concerns about these tools in their daily work. In addition, we automatically collected quantitative data from the company's development systems, aiming at getting insights about how GenAI impacts the development process during the period. Our results provide insights into how practitioners perceive and utilize GenAI in their daily work in software development.

AI for SE, Generative AI, Industry Case Study, Software Development
330-341
IEEE Computer Society
Pereira, Guilherme Vaz
1a429598-2c6b-4bbb-9678-de050521bb5a
Jackson, Victoria
28beab06-6fae-46d3-ad73-1d29897680db
Prikladnicki, Rafael
7139f69b-6fba-4a68-b602-bb94ec835714
van der Hoek, André
4c4cdeed-2314-47ad-ab7f-ae14026a028c
Fortes, Luciane
779015f7-1907-464d-bfda-295eeee52fe5
Araújo, Carolina
160be6d6-d6d8-41fb-9ec1-6a39ec8362e5
Coelho, André
eeba84be-464c-4831-9fe8-74c2a186da03
Chelli, Ligia
df2f40e8-bdfe-4391-85eb-3a7c10bf79f9
Ramos, Diego
7a2f5292-7a3c-433e-9bb4-5cdd684d625f
Pereira, Guilherme Vaz
1a429598-2c6b-4bbb-9678-de050521bb5a
Jackson, Victoria
28beab06-6fae-46d3-ad73-1d29897680db
Prikladnicki, Rafael
7139f69b-6fba-4a68-b602-bb94ec835714
van der Hoek, André
4c4cdeed-2314-47ad-ab7f-ae14026a028c
Fortes, Luciane
779015f7-1907-464d-bfda-295eeee52fe5
Araújo, Carolina
160be6d6-d6d8-41fb-9ec1-6a39ec8362e5
Coelho, André
eeba84be-464c-4831-9fe8-74c2a186da03
Chelli, Ligia
df2f40e8-bdfe-4391-85eb-3a7c10bf79f9
Ramos, Diego
7a2f5292-7a3c-433e-9bb4-5cdd684d625f

Pereira, Guilherme Vaz, Jackson, Victoria, Prikladnicki, Rafael, van der Hoek, André, Fortes, Luciane, Araújo, Carolina, Coelho, André, Chelli, Ligia and Ramos, Diego (2025) Exploring GenAI in software development: insights from a case study in a large Brazilian company. In Proceedings - 2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice, ICSE-SEIP 2025. IEEE Computer Society. pp. 330-341 . (doi:10.1109/ICSE-SEIP66354.2025.00035).

Record type: Conference or Workshop Item (Paper)

Abstract

Recent progress in Generative AI (GenAI) impacts different software engineering (ES) tasks in software development cycle, e.g., from code generation to program repair, and presents a promising avenue for enhancing the productivity of development teams. GenAI based tools have the potential to change the way we develop software and have received attention from industry and academia. However, although some studies have been addressing the adoption of these tools in the software industry, little is known about what are developers' real experiences in a professional software development context, aside the hype. In this paper, we explore the use of GenAI tools by a large Brazilian media company that has teams developing software in-house. We observed practitioners for six weeks and used online surveys at different time points to understand their expectations, perceptions, and concerns about these tools in their daily work. In addition, we automatically collected quantitative data from the company's development systems, aiming at getting insights about how GenAI impacts the development process during the period. Our results provide insights into how practitioners perceive and utilize GenAI in their daily work in software development.

This record has no associated files available for download.

More information

Published date: 20 August 2025
Venue - Dates: 47th IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice, ICSE-SEIP 2025, , Ottawa, Canada, 2025-04-27 - 2025-05-03
Keywords: AI for SE, Generative AI, Industry Case Study, Software Development

Identifiers

Local EPrints ID: 506939
URI: http://eprints.soton.ac.uk/id/eprint/506939
PURE UUID: e14f16aa-8a90-41d5-b354-ad5c29384839
ORCID for Victoria Jackson: ORCID iD orcid.org/0000-0002-6326-931X

Catalogue record

Date deposited: 21 Nov 2025 17:44
Last modified: 22 Nov 2025 03:18

Export record

Altmetrics

Contributors

Author: Guilherme Vaz Pereira
Author: Victoria Jackson ORCID iD
Author: Rafael Prikladnicki
Author: André van der Hoek
Author: Luciane Fortes
Author: Carolina Araújo
Author: André Coelho
Author: Ligia Chelli
Author: Diego Ramos

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×