EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Driven Software Pricing: An Integrated Approach with Prompt Engineering for Market Analysis

Gregory Fernandes Muniz, Joelcio de Carvalho Tonera, Rodrigo Perozzo Noll, Genizia Islabão de Islabão

Journal of the Brazilian Computer Society · 05.06.2026 · 32 (1) · 1486-1505

DOI: 10.5753/jbcs.2026.6572 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 05.06.2026. Verfasst von Gregory Fernandes Muniz und 3 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Software pricing based on valuation still represents a significant challenge due to its intangibility, variety of business models, and market volatility. This article discusses a pricing protocol by analogy mediated by language models (LLMs) and based on prompt engineering that explores public evidence (sitemaps, functional documentation, and competitor pricing pages). An experimental study was conducted with six software programs applying the same structured prompt in three LLMs, totaling 18 executions with standardized informational scope. The sample software consisted of 5 Innovation Management systems: INTEGRA, HYPE Innovation, IdeaScale, Viima/HYPE Boards, and Qmarkets, and one Customer Relationship Management (CRM) system: Salesforce. The 3 LLMs were: ChatGPT 5.1 Thinking, Gemini 3 Pro, and DeepSeek-V3.2. The LLMs extracted functionalities from sitemaps, mapped competitors, synthesized price benchmarks, and suggested market value ranges. The consolidated orders of magnitude converge, for example, to US$ 8,000–25,000/year in INTEGRA (per-instance license), ∼US$ 1,200–3,600 per user/year in Salesforce (per-seat model), and US$ 50,000–100,000/year in HYPE Innovation (enterprise license), with intermediate levels for IdeaScale (∼US$ 15,000–70,000/year), Viima HYPE Boards (∼US$ 6,000–18,000/year), and Qmarkets (∼US$ 30,000–55,000/year), in line with the functional depth and complexity of integrations observed. As a validation step, the estimates from the three LLMs were compared to actual quotations obtained from reference prices from public sources, after standardization (midpoint when a range existed; periodicity conversion to an annual basis and currency conversions when applicable). The evaluation of the results was done by verifying whether the annual market price was within the range estimated by each LLM (inside/outside the interval) and calculating the quotation (market price ÷ midpoint), as a percentage, as a measure of proximity to the midpoint. Under the interval coverage criterion, ChatGPT showed superiority (5/6), followed by Gemini (4/6) and DeepSeek (2/6), suggesting greater consistency of the first in proposing intervals compatible with the observed prices. Taken together, the results indicate convergence of orders of magnitude, albeit with occasional discrepancies, suggesting that the protocol is more suitable as an exploratory price screening tool, complementary to traditional methods. The main contribution lies in a reproducible and innovative protocol in which, from a single prompt applied in isolated conversations by software and by model, one obtains the functionalities extracted from the sitemap, the competitive benchmarking, the comparative table of functionalities, and the estimation of the market value, enabling a search and price analysis approach based on LLMs.

Zitieren

APA

Muniz, G. F., Tonera, J. D. C., Noll, R. P., & Islabão, G. I. D. (2026). AI-Driven Software Pricing: An Integrated Approach with Prompt Engineering for Market Analysis. Journal of the Brazilian Computer Society, 32(1), 1486-1505. https://doi.org/10.5753/jbcs.2026.6572

Vancouver

Muniz GF, Tonera JDC, Noll RP, Islabão GID. AI-Driven Software Pricing: An Integrated Approach with Prompt Engineering for Market Analysis. Journal of the Brazilian Computer Society. 2026;32(1):1486-1505. doi:10.5753/jbcs.2026.6572

BibTeX
@article{Muniz2026,
  author = {Muniz, Gregory Fernandes and Tonera, Joelcio de Carvalho and Noll, Rodrigo Perozzo and Islabão, Genizia Islabão de},
  title = {AI-Driven Software Pricing: An Integrated Approach with Prompt Engineering for Market Analysis},
  journal = {Journal of the Brazilian Computer Society},
  year = {2026},
  volume = {32},
  number = {1},
  pages = {1486--1505},
  doi = {10.5753/jbcs.2026.6572}
}
Kostenlos starten →