This mixed-methods approach study investigates the potential of introducing generative AI (ChatGPT 4 and BARD) as part of a deductive qualitative research design that requires coding, focusing on possible gains in cost-effectiveness, coding throughput time, and inter-coder reliability (Cohen's Kappa). This study involved semi-structured interviews with five domain experts and analyzed a dataset of 122 respondents that required categorization into six predefined categories. The results from using generative AI coders were compared with those from a previous study where human coders carried out the same task. In this comparison, we evaluated the performance of AI-based coders against two groups of human coders, comprising three experts and three non-experts. Our findings support the replacement of human coders with generative AI ones, specifically ChatGPT for deductive qualitative research methods of limited scope. The experimental group, consisting of three independent generative AI coders, outperformed both control groups in coding effort, with a fourfold (4x) efficiency and throughput time (15x) advantage. The latter could be explained by leveraging parallel processing. Concerning expert vs. non-expert coders, minimal evidence suggests a preference for experts. Although experts code slightly faster (17%), their inter-coder reliability showed no substantial advantage. A hybrid approach, combining ChatGPT and domain experts, shows the most promise. This approach reduces costs, shortens project timelines, and enhances inter-coder reliability, as indicated by higher Cohen’s Kappa values. In conclusion, generative AI, exemplified by ChatGPT, offers a viable alternative to human coders, in combination with human research involvement, delivering cost savings and faster research completion without sacrificing notable reliability. These insights, while limited in scope, show potential for further studies with larger datasets, more inductive qualitative research designs, and other research domains. Received: 30 March 2024 | Revised: 17 May 2024 | Accepted: 18 June 2024 Conflicts of Interest The author declares that he has no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are not publicly available due to privacy concerns. However, anonymous data are available on request from the corresponding author upon reasonable request. Author Contribution Statement Frédéric Pattyn: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing - original draft, Writing - review & editing, Visualization, Project administration.

This mixed-methods approach study investigates the potential of introducing generative AI (ChatGPT 4 and Bard) as part of a deductive qualitative research design that requires coding, focusing on possible gains in cost-effectiveness, coding throughput time, and inter-coder reliability (Cohen’s Kappa). This study involved semi-structured interviews with five domain experts and analyzed a dataset of 122 respondents that required categorization into six predefined categories. The results from using generative AI coders were compared with those from a previous study where human coders carried out the same task. In this comparison, we evaluated the performance of AI-based coders against two groups of human coders, comprising three experts and three non-experts. Our findings support the replacement of human coders with generative AI ones, specifically ChatGPT for deductive qualitative research methods of limited scope. The experimental group, consisting of three independent generative AI coders, outperformed both control groups in coding effort, with a fourfold (4x) efficiency and throughput time (15x) advantage. The latter could be explained by leveraging parallel processing. Concerning expert vs. non-expert coders, minimal evidence suggests a preference for experts. Although experts code slightly faster (17%), their inter-coder reliability showed no substantial advantage. A hybrid approach, combining ChatGPT and domain experts, shows the most promise. This approach reduces costs, shortens project timelines, and enhances inter-coder reliability, as indicated by higher Cohen’s Kappa values. In conclusion, generative AI, exemplified by ChatGPT, offers a viable alternative to human coders, in combination with human research involvement, delivering cost savings and faster research completion without sacrificing notable reliability. These insights, while limited in scope, show potential for further studies with larger datasets, more inductive qualitative research designs, and other research domains. Received: 30 March 2024 | Revised: 17 May 2024 | Accepted: 18 June 2024 Conflicts of Interest The author declares that he has no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are not publicly available due to privacy concerns. However, anonymous data are available on request from the corresponding author upon reasonable request. Author Contribution Statement Frédéric Pattyn: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing - original draft, Writing - review & editing, Visualization, Project administration.

In the high-paced, uncertain, and resource-constrained environment of software startups, achieving product–market fit and acquiring initial customers are critical yet challenging tasks. These challenges are often exacerbated by the absence of strategic planning, inefficient requirements selection processes, inadequate resource allocation, and insufficient market research, leading to an alarming 63% failure rate among software startups. The Product Manager (PM), responsible for product strategy, planning, and results monitoring, plays a pivotal role in navigating these complexities; however, the PM role is often undervalued and lacks a universally accepted definition. This study aims to enhance the understanding of the PM's role within software startups by conducting a comprehensive Systematic Literature Review (SLR). Employing a rigorous selection methodology, we reviewed 134 studies and identified 662 distinct PM tasks across 122 activities. Notably, only 7 studies (5.73%) specifically addressed the software startup context, revealing a substantial gap in the literature. Our findings indicate that while product planning and requirements prioritization are dominant topics, many critical activities remain underrepresented, underscoring the need for targeted research in these areas. By addressing the unique challenges faced by software startups, we pave the way for more targeted and effective PM strategies. Future research should consider adopting mixed-method approaches to deepen the understanding of PM practices and investigate underexplored areas such as go-to-market strategies, roadmap creation, and requirements selection within the startup context.

Software startups operate under extreme uncertainty and financial pressure, making Requirements Prioritization (RP) a critical activity for improving survival prospects. This study investigates which prioritization criteria are most relevant to early-stage ventures by conducting a systematic literature review (SLR) of 40 studies and analyzing 358 RP references encompassing 82 distinct criteria across 10 categories. Additionally, we conducted 34 semi-structured interviews with founders from 19 software startups to compare academic insights with real-world practices. The analysis reveals a substantial gap between scholarly emphasis and practitioner needs: while "expected cost" is the most frequently cited criterion in the literature, criteria related to financial impact—such as return on investment, cash flow, and time to value—are underrepresented despite being consistently cited by the most successful startups in our sample. Notably, the criterion "Time to Value," absent from all reviewed literature, emerged as a key factor among practitioners. These findings highlight the need for a more financially grounded and context-sensitive approach to RP in startup environments. The study concludes with a call for greater alignment between academic frameworks and the realities faced by early-stage software ventures, especially in economically challenging conditions.

Startups face critical challenges in prioritizing requirements under severe resource constraints. Although methods such as RICE and ICE are known, prior studies show that decisions often default to ad hoc judgments and stakeholder opinions. This paper introduces and validates VECTR, a lightweight prioritization framework that integrates three criteria highly relevant to startups: return on investment (ROI), Time-to-Value (TtV), and confidence. Rather than presenting these criteria as conceptually new, VECTR’s contribution lies in their explicit operationalization for startup contexts and their integration into a single lightweight visualization. Seventeen practitioners—including founders, product managers, and technical leads—participated in semi-structured interviews. They first described their current prioritization practices and then evaluated VECTR through explanatory material and a proof-of-concept visualization. Results show that ROI, TtV, and confidence are already considered in practice, but inconsistently. Practitioners found VECTR intuitive, visually clear, and useful for structuring discussions, while noting limitations related to estimation effort and subjective assumptions. Most reported that it could support better data-driven decisions, though concerns remained around input estimation and assumptions made by biased humans. This study contributes a financially grounded, software-startup-suitable prioritization method and offers practitioners a practical way to allocate scarce resources toward requirements with the greatest impact, while acknowledging that the validation demonstrates perceived usefulness rather than measurable performance gains.