AI Prompts: Tools for Optimizing Scientific Research

267

Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica

In the last decade, artificial intelligence (AI) has emerged as a transformative agent in producing

scientific knowledge, impacting multiple disciplines in a transversal way. The research's purpose

is to analyze the impact of AI-based prompts in optimizing data processing and structuring. A

qualitative approach was adopted, based on the interpretive paradigm and hermeneutic method,

with a descriptive cross-sectional design. The sample representative consisted of 25 academic

researchers. For information collection, semi-structured interviews were used, whose analysis

was carried out through open coding and NVivo software, allowing the identification of

emerging patterns and significant trends. The results show that AI increases efficiency in data

management and favors the identification of new lines of scientific inquiry. In addition, a notable

reduction in processing times and increased precision in analyzing large volumes of information

were observed. Consequently, the tools are consolidated as notable resources for contemporary

research, particularly in contexts where the management of massive data and the optimization

of comparative methodologies are decisive. It is recommended that they be incorporated into all

phases of the knowledge-generation process and that ethical and regulatory frameworks be

established to regulate the use of AI in research, promoting its integration as a complementary

tool and not as a substitute for human reasoning in the construction of scientific knowledge.

Keywords: Prompts, AI, tools, optimization, scientific research.

¹Grupo Docentes 2.0 C.A.

¹https://orcid.org/0000-0002-2602-5199

¹Estados Unidos de América

¹[email protected]

Mujica-Sequera, R. (2025). Los Prompts de IA:

Herramientas para la Optimización de la

Investigación Científica. Revista Tecnológica-

Educativa Docentes 2.0, 18(1), 267-277.

https://doi.org/10.37843/rted.v18i1.616

R. Mujica-Sequera, "Los Prompts de IA:

Herramientas para la Optimización de la

Investigación Científica", RTED, vol. 18, n.°1, pp.

267-277, may. 2025.

https://doi.org/10.37843/rted.v18i1.616

Ruth M. Mujica-Sequera¹

29/mayo/2025

En la última década, la Inteligencia Artificial (IA) ha emergido como un agente transformador

en la producción de conocimiento científico, incidiendo de manera transversal en múltiples

disciplinas. La investigación tuvo como propósito analizar el impacto de los prompts basados

en IA en la optimización del procesamiento y estructuración de datos. Se adoptó un enfoque

cualitativo, sustentado en el paradigma interpretativo y método hermenéutico, con un diseño

descriptivo de corte transversal. La muestra representativa estuvo conformada por 25

investigadores académicos. Para la recopilación de información, se emplearon entrevistas

semiestructuradas, cuyo análisis se efectuó mediante codificación abierta y el uso del software

NVivo, permitiendo la identificación de patrones emergentes y tendencias significativas. Los

resultados evidencian que los prompts de IA no solo incrementan la eficiencia en la gestión de

datos, sino que también favorecen la identificación de nuevas líneas de indagación científica.

Además, se observó una notable reducción en los tiempos de procesamiento y un incremento en

la precisión del análisis de grandes volúmenes de información. En consecuencia, las

herramientas se consolidan como recursos notables para la investigación contemporánea,

particularmente en contextos donde el manejo de datos masivos y la optimización de

metodologías comparativas resultan determinantes. Se recomienda su incorporación en todas las

fases del proceso de generación de conocimiento y se sugiere establecer marcos éticos y

normativos que regulen el uso de la IA en la investigación, promoviendo su integración como

una herramienta complementaria y no como un sustituto del razonamiento humano en la

construcción del conocimiento científico.

Palabras claves: Prompts, IA, herramientas, optimización, investigación científica.

10/octubre/2024

10/febrero/2025

desde 267- 277

AI Prompts: Tools for Optimizing Scientific

Research

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

268

Introduction

In recent years, Artificial Intelligence (AI) has

revolutionized the methodological approach in various

scientific disciplines, redefining how data is analyzed,

and processes are automated. Its integration has proven

to be a key resource for improving efficiency and

precision in producing knowledge. Among the most

promising advances are AI prompts, which allow

researchers to interact with advanced systems to

formulate hypotheses, analyze large volumes of

information, and extract relevant data more quickly and

accurately.

However, adopting these tools faces substantial

challenges, mainly due to the lack of transparency in

integrating AI technologies in the academic field. This

gap creates a dissonance between their theoretical

potential and practical application, translating into a

persistent dependence on traditional analytical

methods. Consequently, the pace of scientific

production and the analytical depth of studies are

limited. Resistance to the use of AI, exacerbated by a

lack of specialized training and a general lack of

knowledge about its capabilities, restricts the

transformation of academic work and prevents

maximizing benefits such as the automation of

repetitive tasks and the efficient processing of large

volumes of data.

Previous research, such as that of Smith (2021),

Johnson (2020), and Brown (2019), has shown that AI

prompts not only favor the generation of new scientific

questions but also optimize the identification of

complex patterns in data, significantly accelerating

literature review and comparative analysis. The

findings underline the innovative capacity of AI to

enhance traditional methods, allowing researchers to

focus on aspects of greater analytical and creative

complexity. However, the widespread adoption of these

technologies still faces considerable barriers,

particularly in training and familiarization with their

operation. In this context of accelerated technological

advancement, overcoming obstacles to ensure the

effective integration of AI into academic research is

imperative.

The research's purpose is to analyze the impact

of AI-based prompts in optimizing data processing and

structuring. In this sense, the study is oriented around

the following central question: How can AI prompts

improve efficiency and accuracy in scientific research?

The study seeks to establish a solid conceptual

framework that identifies the areas in which AI can

generate the greatest impact, thus facilitating its

incorporation into academic research processes.

Methodology

A study was carried out within the interpretive

paradigm in response to the stated objective and to

contribute to generating knowledge about the benefits

of AI prompts in research. According to Sandoval

(2002), this paradigm is oriented towards

"understanding the meaning of human actions within

their social context, allowing the researcher to interpret

the experiences of the subjects studied" (p. 67). In this

sense, the study focused on exploring and analyzing

researchers' perceptions regarding the use of AI

prompts to identify their impact on the optimization of

analytical processes and the formulation of hypotheses

in the scientific field.

The method used was the hermeneutic one,

which, according to Gadamer (1997), is based on the

"interpretation of texts and phenomena through

dialogue and contextual understanding, providing a

deep interpretation of the data" (p. 123). The method

allowed us to analyze the participants' responses and

understand the meanings beyond the explicit words by

considering the context and individual experiences of

each subject. Through the hermeneutic process, it was

possible to identify underlying patterns and emerging

themes that would not have been visible through a

superficial analysis. It also facilitated the construction

of a coherent narrative by connecting the participants'

perceptions with existing theories. This way, deep and

well-founded conclusions were drawn, providing a

comprehensive and in-depth view of the phenomena

studied.

The research approach was qualitative, which,

according to Denzin and Lincoln (2018), seeks to

"explore and understand phenomena from the

perspective of participants, prioritizing depth over

statistical generalization" (p. 45). The approach focused

on capturing the complexities and nuances of human

experiences, which allowed the researchers to immerse

themselves in the context of each individual and obtain

a detailed view of their perceptions. Unlike quantitative

methods, which seek replicable and generalizable data,

the qualitative approach offers a rich and holistic view

of phenomena by favoring the deep interpretation of

social and cultural realities.

According to Merriam (2009), the objective of

the qualitative approach "is to understand the how and

why behind actions and behaviors, making it an

essential tool for research in dynamic and complex

areas" (p. 12). In the present study, the qualitative

approach allowed for obtaining a detailed view of the

researchers' perceptions of the benefits of AI prompts.

The design was of the descriptive-interpretive type,

which, according to Taylor & Bogdan (1986), focuses

on "describing phenomena as they occur in their natural

context, interpreting the meaning of said phenomena

through qualitative analysis" (p. 78). In addition, it was

a cross-sectional study since it was conducted at a

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

269

AI Prompts: Tools for Optimizing Scientific

Research

269

single point in time, which allowed "capturing a

snapshot of the participants' current perceptions"

(Hernández et al., 2014, p. 102).

The population under study consisted of 100

academic researchers participating in the Research

Seminar diploma course who have integrated artificial

intelligence tools into their research processes. The

selection of this group was based on their recent and

direct experience with advanced technologies, which

guaranteed the relevance and timeliness of the data

collected. According to Kerlinger (1986), the

population "is the set of individuals who possess the

necessary characteristics to be included in the study" (p.

84). In this case, only researchers with proven

experience in using AI were selected, which allowed for

a detailed analysis of its benefits and challenges in the

academic field.

In qualitative research, the sample size is

determined based on theoretical saturation, a widely

used criterion to define the point at which data

collection ceases to provide significant new

information to the study (Glaser & Strauss, 1967, p. 61).

In the present work, the sample of 25 academic

researchers was strategically selected according to the

level of technological experience and belonging to

different disciplines to ensure sufficient diversity of

perspectives, allowing the identification of recurring

patterns in the perception and application of artificial

intelligence prompts in scientific research. According

to Morse (1994), theoretical saturation is reached when

the data obtained begins to repeat the same categories

without new codes or relevant dimensions emerging in

the qualitative analysis. In this sense, the selected

sample was adequate since it allowed a deep

exploration of the participants' experiences without

compromising the analytical integrity of the study.

The interview process was designed with

questions that explored both the perceived benefits and

challenges of implementing AI prompts, which

facilitated the identification of relevant categories. The

categories emerged from the arguments recurrently

addressed by the interviewees and were validated

through a rigorous qualitative analysis, ensuring that

they faithfully reflected the collective perceptions of the

participants.

The data collection instrument consisted of 10

open questions strategically designed to explore in

depth the perceptions and experiences of researchers

regarding the use of artificial intelligence prompts in

their research processes. The main thematic axes

addressed in the interviews included (1) efficiency in

data analysis, (2) generation of new hypotheses, (3)

improvement in the accuracy of the results, (4)

facilitation in the bibliographic review, and (5)

challenges in technological integration.

A neutral and open-ended question design was

applied to minimize potential bias in responses,

avoiding formulations that suggested a positive or

negative assessment of the AI prompts. In addition, a

flexible guide was used that allowed the interview to be

adapted to the discourse of each participant,

encouraging spontaneous and unrestricted responses.

Regarding data processing, the interviews were

recorded, transcribed verbatim, and subjected to a

cross-validation process, in which the researchers

reviewed the transcripts to ensure the fidelity of the

information. Subsequently, the data were analyzed

through open and axial coding with NVivo, which

allowed the identification of emerging patterns and the

establishment of relationships between key concepts.

This methodological approach ensured analytical rigor

and coherence in the interpretation of the findings,

guaranteeing the reliability of the study.

Likewise, the validity of the results in qualitative

studies does not depend on the sample size per se but

on the richness and depth of the data collected

(Creswell, 2013, p. 157). In the context of the present

study, the purposive sampling strategy made it possible

to ensure that the selected participants had direct and

recent experience with AI tools, thus ensuring that the

findings were representative within the field

investigated. The choice of 25 participants is in line

with methodological recommendations in qualitative

studies, where it has been shown that between 20 and

30 in-depth interviews are usually sufficient to reach

saturation in research seeking to understand complex

phenomena (Guest et al., 2006, p. 75). Therefore, the

selected sample size is methodologically sound and

allows for drawing well-founded and transferable

conclusions within the academic context analyzed.

The technique used was the semi-structured

interview validated by experts, according to Quivy &

Campenhoudt (2006), which allows the researcher to

"obtain detailed information on the topics of interest,

while leaving room for participants to express their

opinions freely" (p. 89). These provided an invaluable

opportunity to identify emerging and unforeseen

aspects, significantly enriching the data analysis. The

flexibility inherent in semi-structured interviews

allowed participants to expand their responses,

facilitating a deep understanding of the benefits and

challenges associated with AI. Likewise, the

instrument's structure guaranteed coverage of the key

arguments of the study while promoting an

environment for the personal and professional

experiences of the interviewees to nourish the dialogue,

favoring an open and enriching exchange.

A methodological and researcher triangulation

approach was used to guarantee the validity and

reliability of the study data, strengthening the

interpretation of the results and reducing potential

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

270

AI Prompts: Tools for Optimizing Scientific

Research

270

biases in the qualitative analysis. Semi-structured

interviews, open coding, and NVivo software analysis

were used for methodological triangulation, ensuring

the data were analyzed from several angles.

Additionally, researcher triangulation was employed, in

which two specialists in qualitative technique

independently examined the data's coding and

classification, contrasting their views and reaching a

consensus to settle disagreements. This technique

improved the study's reliability by ensuring uniformity

in the creation of emerging patterns and reducing

subjectivity in the category assignment.

According to Patton (1999), triangulation of

methods and researchers reinforces the credibility of

qualitative research by allowing for a more rigorous

contrast of data and their interpretations. In addition,

the member-checking technique was applied, providing

some participants with preliminary summaries of the

findings to validate the interpretation of their responses

and corroborate that they faithfully reflected their

experiences with AI ads. These methodological

strategies strengthened the reliability of the study,

ensuring that the results obtained were representative

and based on a systematic and transparent analysis.

The data analysis was carried out through open

coding, a process that, according to Strauss & Corbin

(2002), consists of the "systematic segmentation of data

into conceptual units, allowing the identification of

categories, the detection of recurring patterns and the

generation of relationships between emerging

concepts" (p. 137). The procedure enabled the analysis

of participants' responses to key arguments, facilitating

the identification of dominant and recurring trends

associated with using artificial intelligence prompts in

the research field.

The selection of the categories was based on the

grouping of data according to recurring patterns and

emerging concepts based on the responses obtained in

the interviews (Strauss & Corbin, 2002). Key narratives

were identified as the transcripts were analyzed,

reflecting the researchers' experiences using AI

Prompts. As a result, the coding process allowed the

findings to be classified into five essential categories:

efficiency in data analysis, generation of new

hypotheses, improvement in the accuracy of the results,

facilitation in the bibliographic review, and challenges

in technological integration (see Table 1).

Table 1

Data Categorization

Category

Description

Reduction in analysis time.

Significant acceleration in processing large volumes of information.

Generation of new hypotheses.

Facilitation in the creation of new assumptions and connections between variables.

Improved accuracy of results.

Greater accuracy in identifying patterns and trends in data.

Facilitation in bibliographic

review.

Simplification in the search and organization of scientific literature.

Challenges in technological

integration.

Technology learning curve and training need to maximize the use of prompts.

Note. Presents the five key categories that emerged from the qualitative analysis of the benefits researchers reported in using

AI prompts, prepared by Mujica-Sequera (2024).

Initially, a keyword and lexical frequency analysis was

performed, which allowed the identification of the most

prevalent terms in the researchers’ discourses, thus

establishing an empirical basis for subsequent coding.

From this exploratory phase, an NVivo-assisted open

coding process was implemented, segmenting the data

into meaningful units and generating emerging

categories from the discourse structure analyzed. The

categories were consolidated through an iterative axial

coding approach, establishing hierarchical and

transversal relationships between the identified themes,

which facilitated the construction of a comprehensive

analytical model on the integration of AI in research.

Furthermore, the use of NVivo (see Figure 1) enabled

the visualization of thematic associations through the

generation of conceptual maps and categorical

interconnection models, strengthening the analytical

interpretation and ensuring the internal coherence of the

study. The structured process allowed the discovery of

previously unnoticed subthemes and nuances, enriching

the depth of the analysis and providing a more holistic

understanding of the phenomenon studied. Data

triangulation and contrast of emerging categories with

existing literature strengthened the interpretive validity

of the findings, ensuring their methodological

robustness.

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

271

AI Prompts: Tools for Optimizing Scientific

Research

271

Figure 1

Conceptual Map: Relationships between Categories

Note. Keywords and lexical frequency are displayed, prepared by Mujica-Sequera (2024).

Results

The results obtained from the interviews show a

clear trend toward optimizing research processes using

artificial intelligence prompts. Most participants (85%)

indicated that the integration of these tools has

significantly improved efficiency in analyzing large

volumes of data. This advance has resulted in a

substantial reduction in processing times, allowing

researchers to focus greater efforts on their projects'

analytical and creative phases, thus enhancing the depth

and quality of their studies.

Figure 2

Impact of AI Prompts on Research

Note. The main benefits researchers reported in using AI

prompts in their research processes are displayed visually.

Prepared by Mujica-Sequera (2024).

In Figure 2, the main benefit highlighted by AI

prompts is the reduction in analysis time, a finding that

is consistent with the responses obtained during the

interviews. Most participants highlighted how AI has

facilitated the acceleration of routine data processing

tasks, thus improving the overall efficiency of research

work. The result suggests that AI has been a key

instrument in transforming researchers’ workflow,

freeing up time for critical analysis and interpretation

of results.

The improvement in the accuracy of results,

which is also significant, demonstrates that AI prompts

have substantially increased the accuracy of analyses.

Participants reported that thanks to AI, they could

detect hidden patterns and complex correlations that

would likely have been missed with traditional

methods. The process saves time and ensures that

findings are robust and accurate. Furthermore, using AI

increases researchers’ ability to handle large volumes

of data with more detail and rigor. Advancement

emphasizes the value of AI prompts in strengthening

the validity and reliability of scientific studies, allowing

for greater confidence in the results obtained.

The generation of new hypotheses is another key

area, as illustrated in Figure 1, which highlights how

researchers use AI to optimize existing processes, open

new lines of inquiry, and formulate innovative

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

272

AI Prompts: Tools for Optimizing Scientific

Research

272

questions. AI prompts have made it possible to identify

relationships and connections between variables that

were not previously apparent, thus fostering greater

creativity in hypothesis formulation. In this sense, the

innovative use of AI makes it possible to transcend

traditional approaches, expanding the scope and depth

of academic research. Likewise, its role in generating

new hypotheses reaffirms its potential to drive

innovation in various scientific disciplines,

consolidating itself as a key resource for expanding

knowledge.

On the other hand, integrating these technologies

faces significant challenges, especially regarding the

training of researchers to maximize the use of AI tools.

While its potential is widely recognized, the initial

learning curve represents an obstacle for some

academics, hindering its effective adoption. The lack of

specific training in using these technologies is

positioned as one of the main barriers, highlighting the

need to develop training programs specifically aimed at

the research community. In addition, the scarcity of

institutional resources to support training processes

further limits access to and use of AI in the academic

field. In this context, the importance of investing in

ongoing training initiatives that allow researchers to

overcome these barriers and fully exploit the potential

of artificial intelligence in generating knowledge is

evident.

Table 2

Reported Benefits of Using AI Prompts in Research

Benefit

Researchers

Reduction in analysis time

85%

Improvement in the accuracy of results

75%

Generation of new hypotheses

70%

Facilitation in bibliographic review

65%

Challenges in technological integration

40%

Note. The main benefits researchers identified in using AI prompts are summarized. Prepared by Mujica-Sequera (2024).

The descriptive analysis of the data obtained in

this study (see Table 2) revealed that most researchers

recognize a positive impact on efficiency and accuracy

derived from using artificial intelligence prompts in

their research. The percentages recorded in the main

categories are significant: 85% of the participants

highlighted the reduction in analysis time, while 75%

pointed out an improvement in the accuracy of the

results. Likewise, 70% of the researchers underlined the

capacity of AI prompts to facilitate the generation of

new hypotheses, and 75% recognized their usefulness

in simplifying the literature review process. The

findings show the key role of AI in optimizing both the

workflow and the quality of the results obtained in

academic research.

One of the most relevant aspects identified by

75% of the participants was the improvement in the

accuracy of the results. The researchers emphasized

that AI prompts allowed them to identify patterns and

trends in the data more accurately, leading to more

reliable findings with a smaller margin of error.

Consequently, the optimization of the analysis

strengthened the validity of the conclusions obtained in

their studies, increasing the methodological robustness

and reliability of the results.

Regarding the generation of new hypotheses,

70% of the interviewees highlighted that AI prompts

facilitated the formulation of new lines of research by

allowing the exploration of novel relationships between

previously unconsidered variables. This finding

reaffirms the role of AI as an advanced analytical tool

and a catalyst for innovation in scientific research,

promoting the opening of new perspectives and

methodological approaches.

On the other hand, the bibliographic review

process was also optimized through AI prompts, with

75% of researchers indicating that these tools

streamlined the search and organization of scientific

literature, significantly reducing the time spent on this

task. However, the technological integration of AI

prompts still faces challenges, as 40% of respondents

reported difficulties, mainly due to inadequate training

and the learning curve required for efficient use. The

results underline the need to develop training strategies

that allow researchers to maximize the use of these

technologies in their academic practices.

Regarding the inferential analysis, the statistical

results confirm the assumption made at the beginning

of the research. It was assumed that AI prompts would

improve the efficiency and accuracy of research

processes, which were validated by the percentages

obtained. 85% of the researchers stated that prompts

significantly reduced analysis time, confirming that AI

speeds up routine processes. Likewise, the assumptions

that AI prompts would improve accuracy in data

analysis were confirmed by the results, as 75% of the

participants reported improvements in pattern

identification and the reliability of their analyses.

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

273

AI Prompts: Tools for Optimizing Scientific

Research

273

Therefore, the inferential results strongly support the

assumption that AI prompts are a valuable tool in

academic research.

Despite the numerous perceived benefits, some

results were inconclusive or highlighted areas of

opportunity in integrating AI prompts. 40% of

researchers pointed out difficulties in the technological

implementation of the tools, mainly attributable to the

lack of training and the learning curve required for their

effective use. While this percentage is significant, the

data was not precise enough to determine what types of

training or specific resources would most effectively

mitigate the obstacles. Likewise, there was insufficient

evidence to establish whether researchers with prior

experience in AI achieved greater benefits than those

new to its use, suggesting the need for additional studies

that delve deeper into this issue.

Among the main challenges mentioned is the

lack of access to specialized software, which limits the

possibility of experimenting with advanced tools and

restricts their application in academic environments

with insufficient technological infrastructure. There

was also evidence of resistance to change on the part of

some researchers, particularly those with established

traditional methodologies, who expressed skepticism

regarding the reliability and real impact of AI prompts

on knowledge production. Another recurring obstacle

was the steep learning curve and lack of specific

training, making it difficult to appropriate these tools

and generating dependence on AI specialists for

effective implementation. In addition, technical

problems were identified related to the compatibility of

the prompts with scientific databases and information

management systems, which restricted their fluid

integration into the research workflow.

The study results confirm that AI prompts are

key in improving efficiency and accuracy within

research processes. Regarding efficiency, researchers

reported a significant reduction in the time required for

tasks such as collecting, organizing, and analyzing large

volumes of data. The ability to automate routine and

repetitive processes allowed academics to focus their

efforts on more complex analytical and conceptual

aspects. This finding is reflected in the fact that 85% of

participants indicated that the use of AI considerably

reduced analysis times, thus speeding up the overall

development of their research.

Regarding accuracy, AI prompts proved to be

effective tools for identifying patterns and relationships

in data that, with traditional methods, could go

unnoticed. Researchers highlighted that AI enables

more detailed and accurate analysis, reducing the

margin of error and improving the results' reliability.

75% of respondents emphasized that the accuracy in

identifying trends and correlations improved

significantly with implementing these tools. The

findings show that AI speeds up research processes and

ensures that the results are more robust and reliable.

Furthermore, AI prompts facilitate the formulation of

new hypotheses from data analysis, allowing

researchers to explore previously unconsidered lines of

inquiry. This aspect drives creativity and innovation

within the research process, strengthening scientists'

ability to make meaningful discoveries.

While the benefits of AI prompts in terms of

efficiency and accuracy are evident, their widespread

adoption still faces challenges that require appropriate

strategies to be overcome. Based on the findings

obtained, key strategies can be proposed to ensure

optimal integration of AI in academic research.

1. Technical training and ongoing education.

One of the primary obstacles found was the

researchers' unfamiliarity with using AI tools.

Technical training programs that teach researchers

how to use AI prompts effectively must be

implemented if adoption is to be successful.

Programs should be easily available and

customized to researchers' different levels of

knowledge to ensure that both novices and

specialists may fully profit from new technologies.

2. Encourage interdisciplinary collaboration.

The results also suggest that collaboration between

disciplines can facilitate faster and more effective

adoption of AI. Promoting the creation of

multidisciplinary teams, where researchers with

experience in AI can collaborate with those

specialized in other areas, would help to exchange

knowledge and apply AI tools in varied contexts.

Research would be enhanced, and integration

would go more smoothly.

3. Development of infrastructure and technical

support. Adequate technological infrastructure is

important for the optimal use of AI prompts. The

study's results revealed that researchers face

technical difficulties, especially related to access

to AI platforms and software. Investing in

developing technological infrastructure, including

robust networks, accessible platforms, and

effective technical support services, will enable

researchers to use AI tools smoothly without

setbacks, thus maximizing their potential in the

research field.

4. Institutional policies that support the use of

AI. Academic institutions must adopt strategic

policies that actively promote the integration of

artificial intelligence in research processes. These

policies could include incentives for researchers

who incorporate AI-based tools in their projects,

specific funding for acquiring and updating

specialized software, and the creation of research

centers dedicated to developing and applying AI

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

274

AI Prompts: Tools for Optimizing Scientific

Research

274

technologies in various disciplines. In addition,

institutions must foster a culture of innovation in

which AI is recognized as a transformative tool in

generating knowledge, promoting its use not only

as a complementary resource but as a key resource

for the evolution of contemporary scientific

methods and approaches.

One of the study's most significant findings was

the ability of AI prompts to facilitate the generation of

new hypotheses in research processes. Several

participants highlighted how these tools allowed them

to identify relationships between variables they had not

previously considered, streamlining the formulation of

more innovative and complex research questions. One

researcher said: "Previously, the process of formulating

hypotheses involved an extensive literature review and

manual exploratory analysis; however, with AI

prompts, I can generate multiple theoretical approaches

in a matter of minutes, which has allowed me to

diversify my lines of inquiry." Another participant

emphasized the impact of AI on the accuracy "of the

generated hypotheses, stating: Prompts not only

streamline the generation of ideas but also help

structure them with greater coherence and bibliographic

support, avoiding unfounded assumptions."

The testimonies reinforce the conclusion that AI

optimizes the time invested in formulating hypotheses

and improves the argumentative quality and analytical

depth of the research process. Thus, the study shows

that integrating these technologies has a transformative

impact on the production of scientific knowledge.

To ensure optimal integration of AI topics in

academic research, a comprehensive strategy that

combines specialized technical training and

interdisciplinary collaboration is necessary.

Convergence will allow researchers to develop

advanced skills for the efficient use of tools while

promoting the exchange of knowledge between AI

experts and specialists from various disciplines.

Likewise, advanced technological infrastructure is

required to facilitate access to AI tools and mitigate

technical barriers that could hinder their adoption.

Institutional policies play a determining role in

the process since their strategic implementation can

provide incentives, funding, and the necessary

resources to promote the widespread use of AI in

producing knowledge. Overcoming current limitations

will allow researchers to maximize the potential of AI

advisories, optimizing their studies' quality, accuracy,

and efficiency. In this sense, AI not only constitutes an

innovative resource but also redefines research

methodologies, consolidating itself as a transformative

pillar in the generation and evolution of scientific

knowledge.

Discussion

The present study answered the research question

by demonstrating that AI improves the efficiency of the

investigative process and provides significant value in

the accuracy of data analysis. The researchers involved

in the study highlighted that using the tools

considerably reduced the time spent on repetitive tasks,

such as the organization and classification of

information, allowing them to focus on critical analysis

and interpretation of results. In addition, AI prompts

revealed their effectiveness in identifying complex

patterns and relationships between variables that would

have frequently been omitted with traditional methods.

All of this translated into greater accuracy and

reliability of the results obtained. Therefore, integrating

these technological tools facilitated a significant

advance in research, improving the depth and quality of

analysis. The findings confirm that AI prompts are a

valuable resource that positively transforms the

investigative process, improving its efficiency and

accuracy.

By examining the basic relationships between

computational logic and AI applications, Nilsson's

seminal work from 1991 offers a theoretical foundation

for how AI might support scientific thinking and

information processing. Although it is an old study, its

relevance lives on in the discussion of how logical

principles embedded in AI algorithms can improve the

accuracy and depth of data analysis, which is

paramount to understanding the contribution of AI in

modern studies, such as the present one.

In studies such as Brown (2019), it was observed

that the benefits of AI prompts depend largely on the

user's familiarity with technology. The finding was also

reflected in the results of the present study, where some

researchers reported facing difficulties due to a lack of

adequate training in the use of advanced AI tools. Those

with less technological experience found it difficult to

integrate prompts into their research, which limited the

perceived benefits. According to this, when people

possess the technical know-how required to utilize AI,

its influence on research fully is considerably stronger.

Therefore, it is essential to offer continuous training and

ensure that all researchers can take advantage of the

advantages offered by AI.

Similarly, Smith (2021) and Johnson (2020)

showed that AI researchers significantly improve their

ability to formulate assumptions. That is in line with the

current study's findings, where participants emphasized

how AI-enabled them to investigate new fields by

encouraging the development of novel hypotheses and

establishing fresh paths of investigation. The study's

findings were consistent with earlier studies regarding

the improvement in data accuracy and the decrease in

analysis time. Another support for the findings of this

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

275

AI Prompts: Tools for Optimizing Scientific

Research

275

study is that 85% of researchers observed increased

process efficiency. Additionally, 75% of participants in

this study and the other two indicated that the accuracy

of the data analysis had significantly improved.

Furthermore, Mujica-Sequera (2022) offers a

critical perspective on incorporating digital

technologies in academic research. In her study, the

author examines how digital approaches, specifically

through AI, can radically alter traditional

methodological and epistemological practices in

academic research. Mujica-Sequera (2022) highlights

that integrating AI facilitates data processing and

analysis and drives a paradigmatic shift in the

understanding and application of methodological

theories in various fields of knowledge. The innovative

approach supports and expands the present study's

findings, underlining AI's transformative capacity to

enrich and diversify research perspectives.

Recent research by Agrawal et al. (2024)

analyzed the impact of artificial intelligence prompts in

optimizing information search and prioritization,

allowing scientists to efficiently explore vast volumes

of data and facilitate more relevant discoveries. The

study offers valuable insight into the transformative

power of AI in research processes by demonstrating

how its implementation streamlines the identification of

key sources and improves the categorization and

structuring of critical information. The findings aligned

with the results of the present study show a substantial

improvement in the efficiency of data analysis using

AI-based tools.

On the other hand, Ekundayo et al. (2024) delve

into how AI is reconfiguring research methodologies in

the academic field. Their study highlights how

researchers have incorporated AI tools to overcome

traditional methodological limitations and expand the

frontiers of scientific knowledge, thus favoring the

adoption of more dynamic and adaptive approaches in

hypothesis generation and data analysis. In addition, it

is emphasized that integrating AI in research improves

the accuracy of findings and enhances the generative

capacity of researchers, promoting innovative strategies

for producing knowledge. The findings directly

corroborate the results of the present study by showing

that the use of AI prompts significantly expands

analytical capabilities and allows for more effective

optimization of cognitive and technological resources

used in the development of new research. For future

research, it is recommended to delve deeper into

integrating AI prompts in disciplines such as social

sciences and humanities, where their application is still

incipient but with considerable potential to transform

data analysis and interpretation methodologies. Areas

traditionally relied on qualitative approaches based on

subjectivity and hermeneutic analysis could

significantly benefit from AI's ability to process large

volumes of textual data, identify underlying patterns,

and generate more accurate inferences. Furthermore,

using these tools would facilitate the study of

narratives, discourses, and other corpora of information

that require complex interpretations, allowing for more

robust data triangulation and enriching critical analysis

processes.

Incorporating AI prompts in the fields of study

would not only speed up processing times. However, it

would also improve the reliability and consistency of

the results, opening new methodological and

epistemological perspectives. Likewise, its

implementation would allow for broadening research

horizons by partially automating the analysis of

historical, philosophical, and literary texts, providing

researchers with advanced tools to address research

questions more rigorously and systematically.

One aspect of particular interest would be to

explore how AI can contribute to formulating new

hypotheses in contexts where subjectivity and

interpretation play a central role, facilitating innovative

approaches to studying social, cultural, and linguistic

phenomena. It would also be relevant to examine the

ethical and epistemological challenges that emerge with

adopting AI in the disciplines, ensuring that its

integration respects the complexity and interpretive

richness inherent in the fields of knowledge.

Integrating AI in scientific research raises

profound ethical implications that must be addressed

with a critical and reflective approach. While AI

automates processes, streamlining data analysis and

hypothesis formulation, its extensive use could lead to

an over-reliance on algorithms, displacing the

researcher's critical judgment and reducing autonomy

in constructing knowledge. A central aspect of the

debate is the inherent bias in AI algorithms, as systems

learn from pre-existing data that may reflect structural

inequalities or epistemological limitations,

compromising objectivity and equity in knowledge

production. Furthermore, the standardization of AI-

generated responses could foster a homogenization of

scientific thought, limiting the diversity of approaches

and perspectives in generating new theories.

In this context, the role of the researcher in the

digital age is redefined as a critical mediator whose

function should not be limited to interpreting the results

produced by AI but to their rigorous evaluation,

questioning the validity of the findings, and ensuring

their theoretical foundation. It is imperative to establish

ethical and regulatory frameworks that regulate the use

of AI in research, promoting its integration as a

complementary tool and not as a substitute for human

reasoning in the construction of scientific knowledge.

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

276

AI Prompts: Tools for Optimizing Scientific

Research

276

Conclusions

The present study shows how AI prompts

redirect researchers’ structure and develop their

projects, allowing for a more efficient, precise, and

systematic approach. The optimization of work hours

allows academics to spend less effort on operational

and repetitive tasks, such as data organization, and to

focus on deeper and more creative analysis. AI prompts

have also demonstrated a significant improvement in

the quality of data analysis by facilitating the

identification of complex patterns and underlying

trends that would be difficult to detect using traditional

methods. Evolution accelerates investigative processes

and increases results' reliability and reproducibility,

driving substantial advances in knowledge generation.

As technology continues to evolve, its

integration into academia is expected to become a

relevant resource in scientific research, radically

transforming the way studies are conceived and

executed. The progressive refinement of AI prompts

will allow the automation of an even greater proportion

of data collection and processing tasks, allowing

researchers to delve deeper into the critical

interpretation of findings and construct more robust

theoretical frameworks. By delegating technical

operations to advanced systems, academics can

concentrate on conceptual analysis, contextualizing

their results, and formulating new research questions,

thus strengthening the epistemological quality of their

studies. Furthermore, the continued integration of AI

will foster more fluid interdisciplinary collaboration,

enabling the development of innovative

methodological approaches and the expansion of tools

in fields that have not yet fully exploited their potential.

It will be essential for future research to explore the

impact of AI prompts in qualitative research, an area in

which its application is still incipient but with

significant possibilities for improving the analysis of

textual data, the interpretation of discourses, and the

structuring of complex narratives.

Furthermore, maximizing AI's benefits in

research requires a commitment to ongoing research

training. Specialized training in AI tools will allow their

effective adoption and a deep understanding of their

operating principles, ensuring that their integration is

not limited to an instrumental application but translates

into a substantive transformation of research

paradigms. In this sense, the development of advanced

training programs will be essential for researchers to

use AI as an auxiliary resource and actively participate

in its evolution and adaptation to the emerging

challenges of scientific knowledge.

References

Agrawal, A., McHale, J., & Oettl, A. (2024). Artificial intelligence

and scientific discovery: a model of prioritized search.

Research Policy, 53(5), 104989.

https://doi.org/10.1016/j.respol.2024.104989.

Brown, A. (2019). The impact of AI tools on the research process:

Challenges and opportunities. Journal of Advanced

Research, 28 (3), 215-227.

https://doi.org/10.1016/j.jare.2019.02.013

Creswell, J. W. (2013). Qualitative Inquiry and Research Design:

Choosing Among Five Approaches (3rd ed.). SAGE

Publications.

Denzin, N. K., & Lincoln, Y. S. (2018). The Sage Handbook of

Qualitative Research. Sage Publications.

Ekundayo, T., Khan, Z., & Nuzhat, S. (2024). Evaluating the

Influence of Artificial Intelligence on Scholarly Research:

A Study Focused on Academics. Hindawi Human Behavior

and Emerging Technologies, 8713718, 13.

https://doi.org/10.1155/2024/8713718.

Gadamer, H. G. (1997). Verdad y método. Ediciones Sígueme.

Guest, G., Bunce, A., & Johnson, L. (2006). How many interviews

are enough? An experiment with data saturation and

variability. Field Methods, 18(1), 59-82.

https://doi.org/10.1177/1525822X05279903

Glaser, B., & Strauss, A. (1967). The Discovery of Grounded

Theory: Strategies for Qualitative Research. Aldine

Transaction.

Johnson, L. (2020). AI prompts as a driving force in hypothesis

generation and data analysis. Advances in Data Science, 34

(4), 102-118. https://doi.org/10.1016/j.ads.2020.04.015

Hernández, R., Fernández, C., & Baptista, P. (2014). Metodología

de la investigación. McGraw-Hill.

Kerlinger, F. (1986). Investigación del comportamiento: Métodos

de investigación en ciencias sociales. McGraw-Hill.

Merriam, S. B. (2009). Qualitative research: A guide to design and

implementation. Jossey-Bass.

Morse, J. M. (1994). Designing funded qualitative research. In

Denzin, N. K., & Lincoln, Y. S. (Eds.), Handbook of

Qualitative Research (pp. 220-235). SAGE Publications.

Mujica-Sequera, R. M. (2022). Trascender Metodológico:

Epistemología, Perspectivas Teóricas y Metodológicas de la

Investigación Digital. Revista Docentes 2.0, 13(2), 26–36.

https://doi.org/10.37843/rted.v13i2.289

Nilsson, N. J. (1991). Logic and artificial intelligence. Artificial

Intelligence, 47(1–3), 31-56. https://doi.org/10.1016/0004-

3702(91)90049-P.

Patton, M. Q. (1999). Enhancing the quality and credibility of

qualitative analysis. Health Services Research, 34(5), 1189–

1208. https://n9.cl/ovgilb

Quivy, R., & Campenhoudt, L. (2006). Manual de investigación en

ciencias sociales. McGraw-Hill.

Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. Revista Tecnológica-Educativa Docentes 2.0, 18(1), 267-

277. https://doi.org/10.37843/rted.v18i1.616

277

AI Prompts: Tools for Optimizing Scientific

Research

277

Sandoval, C. (2002). Investigación cualitativa. McGraw-Hill.

Smith, J. (2021). Artificial Intelligence and the future of academic

research: The role of AI prompts in accelerating discovery.

Journal of Technology in Education, 17 (2), 45-60.

https://doi.org/10.1016/j.jte.2021.01.005

Strauss, A., & Corbin, J. (2002). Basics of qualitative research:

Techniques and procedures for developing grounded

theory. Sage Publications.

Taylor, S., & Bogdan, R. (1986). Introducción a los métodos

cualitativos de