MétaCan
Menu
Back to cohort
Record W4417036956 · doi:10.5753/sbqs.2025.15010

Automated Test Case Generation in a Real-World System Using a Customized AI Agent: An Experience Report

2025· article· W4417036956 on OpenAlex
Diógenes Henrique de Siqueira‐Silva, Carlos Mar

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicSoftware Testing and Debugging Techniques
Canadian institutionsOptech (Canada)
Fundersnot available
KeywordsContext (archaeology)Component (thermodynamics)Process (computing)Quality (philosophy)Test (biology)Test caseSoftwareKeyword-driven testingTest Management Approach

Abstract

fetched live from OpenAlex

Test case design is an essential activity in software quality assurance. However, when performed manually, it can be time-consuming, error-prone, and require substantial effort, particularly in complex applications. This experience report describes the development and application of an artificial intelligence agent, built using the ChatGPT platform, designed to automate the process of generating test cases for a real-world system and reduce the time required. The agent was configured to simulate the role of a QA analyst, using functional requirements, interface prototypes, and prompt engineering strategies to produce test scenarios with high coverage and accuracy. Experimentswere conducted on one of the modules of a component assembly control system, comparing manually created test cases with those generated by the agent. The results showed a reduction of over 50% in specification time while maintaining the quality and coverage of the scenarios. This paper details the agent’s configuration, the results achieved, the challenges encountered, and the lessons learned, contributing evidence for the practical use of generative AI in the context of software quality assurance.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.955
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.004
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.067
GPT teacher head0.373
Teacher spread0.306 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it