How AI drives software development

Column

Software Development

Innovation

Technology

May 19, 2025

How AI drives software development

Improper use of technology, without the due technical knowledge, can compromise the quality, security, and sustainability of the developed solutions

Artificial intelligence (AI) has become vital in the world of technology, and this also applies to those who create computer programs and applications. AI is no longer a passing fad but has consolidated itself as a force that enhances the development of software. Through advanced techniques such as machine learning (machine learning), natural language processing (NLP), and computer vision, AI expands the possibilities of innovation, optimizing everything from the conception stage to the maintenance and update phases.

This text explores how the strategic application of AI, made with knowledge grounded, can result in more modern, efficient software aligned with the needs of the contemporary market, which is constantly transforming. Also, the dangers associated with the inadequate use of this type of technology, without proper technical knowledge, will be addressed, as this can compromise the quality, security, and sustainability of the developed solutions.

One of the areas where AI can help the most is in the creation and automatic refinement of code. Programs that learn from many code examples can help developers write repetitive parts, get ideas on how to program better, and even find points where the program might be slow. AI-powered tools can analyze existing code and suggest changes to improve its performance, including security aspects. This frees developers from manual and repetitive work, allowing them to focus on the overall structure of the program.

Another important application of artificial intelligence is in the detection of failures and the automation of tests in software systems. Intelligent algorithms can identify recurring error patterns, allowing for the creation of more comprehensive and efficient tests, including finding problems that might go unnoticed in human-made tests. Furthermore, AI can analyze error logs to quickly detect the cause of issues, optimizing the debugging and failure correction process.

The first phase of software conception — understanding what the client wants and writing down what the program needs to do — can also be improved with AI. Natural language processing techniques can be used to analyze documents with client requests and find ambiguous, contradictory or incomplete passages, ensuring that the demand is clear to all parties involved. Artificial intelligence can also assist the development team in prioritizing activities, considering the potential benefits and risks associated with each initiative.

Furthermore, AI analyzes data from old projects to predict problems, such as delays or extra expenses, and more accurately estimate the time and effort required at each stage of the projects, making planning more assertive and optimizing resources.

Technique

Even with the great potential of artificial intelligence in optimizing software development, it is very important that the developer has experience in code production, as they will need in-depth knowledge to find specific solutions for certain problems or to understand, supervise, and adapt solutions created by AI. Therefore, developers and software engineers need to be able to:

  • Choosing the most appropriate AI tools and application methods: not all software problems are the same, nor do all AI tools help in the same way. Knowing which algorithm, which technique, or which tool to use at each moment is crucial for good results;
  • Prepare and analyze data to “teach” AI: the efficiency of the artificial intelligence tool depends on the quality and relevance of the data used in its training. Professionals with technical knowledge must be able to collect, process, organize, and adequately analyze this data, so that the AI learns correctly and can apply this knowledge in new contexts;
  • Understanding and verifying AI suggestions: AI tools provide various types of information, which must be critically checked according to the project’s objectives. It is necessary to understand how the software works to identify solutions that are effective and safe.
  • Include AI in development: the use of AI does not replace the work that the IT professional was already doing. It is essential that the developer knows how to integrate artificial intelligence tools into their current activities, ensuring efficient synergy with other existing processes and tools.
  • Monitor AI models: artificial intelligence tools can become outdated due to changes in data or demands. Therefore, it is important to constantly monitor their performance and make adjustments or new training when necessary.

Risks

If AI is used in software development by people without technical knowledge, it may harm the quality, security, and efficiency of managing any changes that may be necessary in the future.

AI tools that generate code without the supervision and review of experienced developers can cause the infiltration of errors security flaws into programs and result in code that does not work well or is susceptible to attacks, problems often difficult to trace.

Furthermore, if the development team does not fully understand code generated by artificial intelligence, they may have difficulty both in maintenance and in implementing changes and improvements to the system, increasing costs and development time.

Improvements in one part of the program have the potential to harm others, so if the development team does not understand all aspects and consequences of an improvement in the code suggested by the AI, performance problems and the system’s ability to handle many users in the future may arise, for example.

Regarding security, while AI helps in locating failures, it can cause the paralysis of other important practices. Furthermore, a poorly trained AI can generate code with new security flaws or ignore already established rules.

Finally, it is important to know that AI can contain biases if the data used to train it presents these biases. This can lead to unexpected or unfair behavior in the software. And, as some AI models function as “black boxes”, it can be difficult to understand the reasons for their decisions, which makes it difficult to correct possible biases.

Conclusion

Artificial intelligence is a powerful tool that can change the way software is made, making work faster and programs better, while also facilitating the implementation of innovations. From helping to write and improve code to intelligently testing programs and understanding what customers need, AI has the potential to transform every step of development.

However, it is essential to remember that, to succeed, development teams need to have a lot of technical knowledge and experience. Using AI without care and experience can bring more problems than solutions, harming the quality, security, and adaptability of the software in the future.

Therefore, the best way to make the most of AI in software development is to combine machine intelligence with human knowledge and experience. Investing in the training and development of AI technical skills for IT professionals is fundamental to ensure that this powerful technology is used effectively and responsibly, paving the way for a future with more innovative and high quality software.

This content was produced by:

Cesar Soares Stenico

LinkedIn

Systems developer, graduated in Computer Science and holds an MBA in Digital Business. Works on building web applications, with a strong enthusiasm for new technologies, blockchain systems, and software engineering. With an innovative profile, constantly seeks to apply modern and efficient solutions in systems development.

Who wrote this column

Skylar

"Startup" de tecnologia e legendagem que faz parte das iniciativas do Pecege, utiliza inteligência artificial e técnicas linguísticas para fazer legendagem em tempo real. Atuante nas áreas de educação, eventos, agronegócio, tecnologia, saúde, entretenimento e esportes, entre outras. Acesse o site!

You may also like

November 16, 2026

Exploratory modeling of the effect of preemptive cytomegalovirus treatment in AIDS patients

Cytomegalovirus (CMV) is highly prevalent and causes severe disease in immunocompromised individuals, such as HIV patients. Given the scarcity of robust data on preemptive treatment for this infection, an exploratory model was developed. The objective was to identify potential subgroups that would benefit from this approach. A retrospective observational study was conducted, analyzing 176 medical records of patients admitted to a tertiary hospital between 2017 and 2022. After applying inclusion and exclusion criteria, 116 patients were divided into a preemptive treatment group (19) and a control group (97). Machine learning techniques, such as LinearDML and CausalForestDML, and variable analysis by Feature Importance and SHAP were used. Variable analysis indicated that high CMV viremia was associated with death, with an Odds Ratio of 1.85 (p = 0.004). The model estimated an increase in overall mortality associated with preemptive treatment (ATE of 48%, p = 0.0180), possibly reflecting the greater baseline severity of the treated patients. However, heterogeneity analysis identified that older patients showed a relatively more favorable estimated effect. Limitations included the small sample size and the retrospective and observational nature. Nevertheless, with an expanded evaluation group, the model could serve as a basis for building clinical decision support tools.

Keywords: Machine learning; Double machine learning; Causal inference; Mortality.

November 16, 2026

Regression models for personal hygiene and personal care product expenses in the Southeast region

Regression models were evaluated to correlate expenses with personal hygiene and care products of the population in the Southeast Region of Brazil. Data from the 2017-2018 Family Budgets Survey (POF), conducted by the Brazilian Institute of Geography and Statistics, were used. The models were estimated by ordinary least squares and verified for the assumptions of normality of error terms, multicollinearity, and heteroscedasticity. Linear regression, nonlinear regression with Box-Cox transformation, and linear regression with dummy variables were evaluated. Coefficients statistically different from zero were obtained for all three models, confirmed by the p-values of the F and t tests, and the adherence of residuals to normality was graphically assessed. However, heteroscedasticity problems were observed in all cases, indicating the omission of relevant variables from the model. The low R² values obtained, between 2.19% and 5.56%, suggested that the dependent variable was poorly explained by the models. Despite this, a growing trend in expenses for personal hygiene and care as a function of disposable income per capita was observed. For future studies, it is recommended to evaluate other explanatory variables to improve the model’s adjustment coefficient and eliminate heteroscedasticity.

Keywords: Family expenses; Ordinary least squares; Per capita income; Box-Cox transformation; Dummy variables.

November 16, 2026

Cognitive Accessibility and ASD: Design Guidelines for Augmentative and Alternative Communication Applications

Autism Spectrum Disorder (ASD) imposes specific challenges on the design of digital interfaces, affecting cognitive processing, sensory regulation, and functional communication. In this context, Augmentative and Alternative Communication (AAC) is an essential resource to support individuals with oral language limitations. This study aimed to analyze the usability and accessibility of AAC applications for the neurodivergent public. The research was characterized as descriptive, with a quantitative approach, and was based on the systematic observation of the interfaces of the Brazilian applications Livox, Matraquinha, and Expressia. A structured checklist, developed from the convergence of Human-Computer Interaction (HCI) guidelines, Applied Behavior Analysis (ABA), and the GAIA Guide, was used as a data collection instrument. The results revealed that Livox and Expressia showed greater technical compliance and learning support, while Matraquinha stood out for its semantic literalness, but with limitations in customization and architecture. A generalized critical gap was identified in the proactive detection of frustration, highlighting opportunities for strategic innovation for the digital business market and for the advancement of neuroinclusive design.

Keywords: Neuroinclusive Design; Digital Inclusion; Strategic Innovation; Assistive Technology; Usability.

November 16, 2026

Multidimensional Poverty and Bolsa Família Program: challenges and perspectives of inclusion through public policies

The concept of poverty has evolved over the 20th and 21st centuries, incorporating a more inclusive perspective that transcends monetary income. The Multidimensional Poverty Index (MPI) has emerged as a complementary tool to characterize poverty and guide programs like Bolsa Família, aiming to improve their effectiveness and targeting. The study aimed to create a national MPI using data from the Continuous National Household Sample Survey (PNADC) of 2024, seeking to identify the correlation between receiving the benefit and multidimensional poverty, as well as to detect underserved populations. The Alkire-Foster methodology was used to calculate the MPI, decomposing the results into groups of beneficiaries and non-beneficiaries of PBF. Subsequently, a Generalized Linear Model with a logit function was applied to analyze the correlations. The results revealed that 4.84% of the Brazilian population lived in multidimensional poverty, with an incidence three times higher among Bolsa Família beneficiaries. Two profiles of multidimensional poverty and two potential blind spots in PBF coverage were identified, including 9.0% of non-beneficiary multidimensional poor in extreme monetary poverty and 25.2% in low-income vulnerability. Being a PBF beneficiary was associated with a two-fold higher chance of being classified as multidimensionally poor. It was concluded that the MPI is a valuable tool for designing public policies, increasing targeting capacity and demanding actions to address structural problems that perpetuate poverty.

Keywords: Alkire-Foster; MPI; Public policies.

November 16, 2026

The influence of People Management on the Health and Well-being of collaborators

In a dynamic organizational scenario, understanding the influence of People Management practices on employee health and well-being has become essential. The study aimed to analyze how People Management practices influence employees’ perception of health, well-being, and quality of life in various organizations. The methodology adopted was descriptive, with a quantitative approach, and employed the survey technique. Data were collected through a structured questionnaire with 15 sociodemographic questions and Likert scale items, disseminated for 40 days on social media. The sample consisted of employees from different companies, selected for convenience, with voluntary and anonymous participation. The results revealed that people management practices impacted motivation, engagement, and the perception of quality of work life, but were not consistently perceived by all employees. It was observed that organizational actions focused on health and well-being were recognized in a moderate and non-equivalent manner, with the presence of neutral and dissenting perceptions. It was concluded that, although People Management practices have strategic potential, their effectiveness depends on greater structuring, continuity, and communication. The study contributed to highlighting gaps between the adopted practices and employee perception, providing subsidies for the improvement of organizational strategies and for the production of academic knowledge in the area.

Keywords: Organizational well-being; Organizational climate; Engagement; Motivation; Quality of work life.

November 16, 2026

Optimization of Delivery Logistics Network through Mathematical Modeling and Clustering

Efficiency in distribution logistics constitutes an essential competitive advantage for the reduction of operational costs and the financial sustainability of contemporary organizations. The general objective of this work was to optimize the delivery network of a company, aiming at cost reduction through the decrease of mileage traveled. The methodology employed was based on the principles of Operational Research and was structured in three sequential phases: geographical allocation of clients to depots respecting Federal Unit restrictions, clustering of stores using the K-Means algorithm, and routing of the heterogeneous fleet using the mathematical formulation of the Vehicle Routing Problem. The main results obtained demonstrated a reduction in the total distance traveled, which represented an absolute saving of 5,116 km and a percentage gain of 3.24%. The model validated itself as a robust tool, capable of optimizing vehicle occupancy and eliminating subjectivity in logistical planning. It was concluded that the use of advanced mathematical modeling allowed operational restrictions to be converted into a measurable competitive advantage. The solution validated the viability of data-based decision support systems for the automation and optimization of large-scale logistical flows.

Keywords: Clustering; Logistics optimization; Operational Research; Cost Reduction; Vehicle routing.