Computer-Aided Pitch Deck Pro: An Entrepreneurial Intelligence Framework for AI-Assisted Startup Pitch Generation, Investment Readiness Assessment, and Decision Support
Main Article Content
Abstract
The exponential growth of early-stage ventures coupled with the persistent scarcity of rigorous, scalable, and bias-aware investment-readiness assessment tools has produced a structural bottleneck in the global startup ecosystem. Although machine learning models now achieve over 90 % accuracy on retrospective success prediction and large language models can generate plausible business narratives, these capabilities remain siloed: predictive models offer no constructive feedback to founders, and generative models are routinely challenged by hallucination, weak grounding, and absence of structured evaluation rubrics. This paper introduces Computer-Aided Pitch Deck Pro, an integrated Entrepreneurial Intelligence Framework that operationalizes a seven-stage computational pipeline, Extract → Learn → Evaluate → Validate → Augment → Transform → Export, for end-to-end AI-assisted pitch deck generation, investor-readiness scoring, and decision support. Grounded in design-science research and a corpus-level synthesis of more than 120 peer-reviewed studies on venture AI, retrieval-augmented generation, explainable AI, and human-AI collaboration, the framework introduces four original constructs — (i) a Pitch Deck Quality Index, (ii) an Investment Readiness Score based on the validated Critical Factor Assessment rubric, (iii) an Epistemic Confidence Estimator for quantifying LLM output trust, and (iv) a Pitch Optimization Gain Function for refinement under expert constraint. Across an experimental corpus of 612 pitch dock transcripts and an expert panel of 47 venture capitalists, the proposed system achieves a Pearson correlation of r = 0.91 between IRS and human ratings, a 27 % relative improvement in PDQI after one optimization round, and a 5–15-second end-to-end analysis latency, comparable to recent RAG-augmented investor assistants [1], [2]. Seven major contributions are delineated: the Entrepreneurial Intelligence Framework as a foundational paradigm; the ELEVATE pipeline; the PDQI; the IRS; the ECE; a multimodal pitch-deck quality dataset; and a hybrid expert-in-the-loop evaluation protocol. The paper positions Computer-Aided Pitch Deck Pro as the first system to unify generative, evaluative, and decision-support functions for the entrepreneurial domain, opening a new line of research we term Entrepreneurial Intelligence Systems.
Article Details

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
P. Weber, K. V. Carl, and O. Hinz, "Applications of explainable artificial intelligence in finance—a systematic review of finance, information systems, and computer science literature," Manag. Rev. Q., 2023. [Online]. Available: https://doi.org/10.1007/s11301-023-00320-0
F. S. Khan, S. S. Mazhar, K. Mazhar, et al., "Model-agnostic explainable artificial intelligence methods in finance: A systematic review, recent developments, limitations, challenges and future directions," Artif. Intell. Rev., 2025. [Online]. Available: https://doi.org/10.1007/s10462-025-11215-9
S. Kleinert and D. Urbig, "Startup evaluations with generative artificial intelligence: An exploratory study on early-stage investments and survival predictions by large language models," Entrepreneurship Theory Pract., 2026. [Online]. Available: https://doi.org/10.1177/10422587261430320
J. Greer and M. A. Mark, "Evaluation methods for intelligent tutoring systems revisited," Int. J. Artif. Intell. Educ., 2015. [Online]. Available: https://doi.org/10.1007/s40593-015-0043-2
A. R. Hevner and V. C. Storey, "Research challenges for the design of human-artificial intelligence systems," ACM Trans. Manag. Inf. Syst., 2022. [Online]. Available: https://doi.org/10.1145/3549547
S. Nowak and S. Rüger, "How reliable are annotations via crowdsourcing," in Proc. ACM Int. Conf. Multimedia, 2010. [Online]. Available: https://doi.org/10.1145/1743384.1743478
A. Dedase, "Scalable software as a service architecture," arXiv preprint, 2024. [Online]. Available: http://arxiv.org/abs/2403.05377
K. L. Ricker-Pedley, S. Hines, and C. M. Connelly, "Operational human scoring at scale," in Operational Human Scoring at Scale, 2020. [Online]. Available: https://doi.org/10.1201/9781351264808-10
K. Jagadeesh, S. Suman, L. N. Mothieram, and S. Shashankraj, "VCRAFT AI: Automated pitch deck evaluation and investor-ready deck generation using LLMs," Zenodo, 2026. [Online]. Available: https://doi.org/10.5281/zenodo.18875229
T. V. Rolim, "Sisifo: A semantic approach to construct enterprise knowledge graphs," M.S. thesis, Universidade Federal do Ceará, 2020. [Online]. Available: http://www.repositorio.ufc.br/handle/riufc/69116
J. Miwa, D. Li, T. Kumamoto, et al., "FA-RAG: Financial advice system using RAG based on LLMs," in Proc. HICSS-58, 2025. [Online]. Available: https://hdl.handle.net/10125/111602
H. Zhang, H. Song, S. Li, et al., "A survey of controllable text generation using transformer-based pre-trained language models," ACM Comput. Surv., 2023. [Online]. Available: https://doi.org/10.1145/3617680
S. Moore, N. Bier, and J. Stamper, "Assessing educational quality: Comparative analysis of crowdsourced, expert, and AI-driven rubric applications," in Proc. AAAI HCOMP, 2024. [Online]. Available: https://doi.org/10.1609/hcomp.v12i1.31606
V. Boss, L. Dahlander, C. Ihl, et al., "Organizing entrepreneurial teams: A field experiment on autonomy over choosing teams and ideas," 2021. [Online]. Available: https://hdl.handle.net/11420/45116
G. Ross, S. R. Das, D. Sciro, et al., "CapitalVX: A machine learning model for startup selection and exit prediction," J. Financ. Data Sci., 2021. [Online]. Available: https://doi.org/10.1016/j.jfds.2021.04.001
G. Tamašauskaitė and P. Groth, "Defining a knowledge graph development process through a systematic review," ACM Trans. Manag. Inf. Syst., 2022. [Online]. Available: https://doi.org/10.1145/3522586
Y. Katcharovski and A. L. Maxwell, "Predicting business angel early-stage decision making using AI," arXiv preprint, 2025. [Online]. Available: http://arxiv.org/abs/2507.03721
M. Potanin, A. Chertok, K. V. Zorin, et al., "Startup success prediction and VC portfolio simulation using CrunchBase data," arXiv preprint, 2023. [Online]. Available: http://arxiv.org/abs/2309.15552
I. Iaroshev, R. G. Pillai, L. Vaglietti, et al., "Evaluating retrieval-augmented generation models for financial report question and answering," Appl. Sci., 2024. [Online]. Available: https://doi.org/10.3390/app14209318
R. Nadipalli, "Scalable microservices using Java and RESTful APIs on the cloud," Int. J. Comput. Eng., 2020. [Online]. Available: https://doi.org/10.47941/ijce.3240
F. Khalil and G. Pipa, "Transforming the generative pretrained transformer into augmented business text writer," J. Big Data, 2022. [Online]. Available: https://doi.org/10.1186/s40537-022-00663-7
M. Vössing, N. Kühl, M. Lind, et al., "Designing transparency for effective human-AI collaboration," Inf. Syst. Front., 2022. [Online]. Available: https://doi.org/10.1007/s10796-022-10284-3
T. Zhang, V. Kishore, F. Wu, et al., "BERTScore: Evaluating text generation with BERT," in Proc. ICLR, 2020. [Online]. Available: https://arxiv.org/pdf/1904.09675.pdf
Y.-J. Chen, P.-H. Chen, T.-C. Tung, et al., "Integrating retrieval-augmented generation and large language models for financial question answering," in Proc. ICIIBMS, 2025. [Online]. Available: https://doi.org/10.1109/iciibms66230.2025.11316716
C. A. Guzmán Solano, C. J. B. Dela Cruz, and I. Arroyo-Fernández, "Effective pitch decks through user-centered prompts for generative AI," AI Horizons Commun., 2024. [Online]. Available: https://doi.org/10.47756/aihc.y9i1.176
J. Černevičienė and A. Kabašinskas, "Explainable artificial intelligence in finance: A systematic literature review," Artif. Intell. Rev., 2024. [Online]. Available: https://doi.org/10.1007/s10462-024-10854-8
W. J. Yeo, W. van der Heever, R. Mao, et al., "A comprehensive review on financial explainable AI," Artif. Intell. Rev., 2025. [Online]. Available: https://doi.org/10.1007/s10462-024-11077-7
M. Kutlu, T. McDonnell, M. Lease, et al., "Annotator rationales for labeling tasks in crowdsourcing," J. Artif. Intell. Res., 2020. [Online]. Available: https://doi.org/10.1613/jair.1.12012
M. Steyvers and A. Kumar, "Three challenges for AI-assisted decision-making," Perspect. Psychol. Sci., 2023. [Online]. Available: https://doi.org/10.1177/17456916231181102
J. Arroyo, F. Corea, G. Jiménez-Díaz, et al., "Assessment of machine learning performance for decision support in venture capital investments," IEEE Access, 2019. [Online]. Available: https://doi.org/10.1109/access.2019.2938659
Z. Liu, H. Pei, X. Xiao, et al., "LLM agents as VC investors: Predicting startup success via role-play-based collective simulation," arXiv preprint, 2025. [Online]. Available: http://arxiv.org/abs/2512.22608
S. Meckler, "Procedure model for building knowledge graphs for industry applications," arXiv preprint, 2024. [Online]. Available: http://arxiv.org/abs/2409.13425
H. Kang and X.-Y. Liu, "Deficiency of large language models in finance: An empirical examination of hallucination," arXiv preprint, 2023. [Online]. Available: http://arxiv.org/abs/2311.15548
A. Haghani, H. Nur, and S. Pala, "From decks to decisions: An auditable AI framework for venture capital," Research Square preprint, 2025. [Online]. Available: https://doi.org/10.21203/rs.3.rs-7781525/v1
X. Li, S. Wang, S. Zeng, et al., "A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges," Discover Computing, 2024. [Online]. Available: https://doi.org/10.1007/s44336-024-00009-2
S. M. Alwedaei and J. Moosa, "Developing a cloud-based API for adopting SaaS microservice architecture," in Proc. ITIKD, 2025. [Online]. Available: https://doi.org/10.1109/itikd63574.2025.11004997
L. Gautam and N. Wattanapongsakorn, "Machine learning models to investigate startup success in venture capital using Crunchbase dataset," in Proc. JCSSE, 2024. [Online]. Available: https://doi.org/10.1109/jcsse61278.2024.10613650
Y. Shi, E. Eremina, and W. Long, "Machine learning models for early-stage investment decision making in startups," Managerial Decis. Econ., 2023. [Online]. Available: https://doi.org/10.1002/mde.4072
N. Takas, E. Kouloumpris, K. Μουτσιάνας, et al., "Startup sustainability forecasting with artificial intelligence," Appl. Sci., 2024. [Online]. Available: https://doi.org/10.3390/app14198925
Y. K. Dwivedi, L. Hughes, E. Ismagilova, et al., "Artificial intelligence: Multidisciplinary perspectives on emerging challenges, opportunities, and agenda for research, practice and policy," Int. J. Inf. Manage., 2019. [Online]. Available: https://doi.org/10.1016/j.ijinfomgt.2019.08.002
C. Ziems, W. A. Held, O. A. Shaikh, et al., "Can large language models transform computational social science?" Comput. Linguist., 2023. [Online]. Available: https://doi.org/10.1162/coli_a_00502
K. Šutienė, P. Schwendner, C. Șipoș, et al., "Enhancing portfolio management using artificial intelligence: Literature review," Front. Artif. Intell., 2024. [Online]. Available: https://doi.org/10.3389/frai.2024.1371502
C. Pahl, P. Jamshidi, and O. Zimmermann, "Architectural principles for cloud software," ACM Trans. Internet Technol., 2018. [Online]. Available: https://doi.org/10.1145/3104028
O. C. Oyeniran, A. O. Adewusi, A. G. Adeleke, et al., "Microservices architecture in cloud-native applications: Design patterns and scalability," Int. J. Sci. Technol. Res. J., 2024. [Online]. Available: https://doi.org/10.51594/csitrj.v5i9.1554
E. Mollick, L. Mollick, N. Bach, et al., "AI agents and education: Simulated practice at scale," arXiv preprint, 2024. [Online]. Available: http://arxiv.org/abs/2407.12796
D. P. Price, "Introducing university pitch competitions: An analysis of the first five years," J. High. Educ. Theory Pract., 2021. [Online]. Available: https://doi.org/10.33423/jhetp.v21i9.4598
A. Göknil, F. B. Gelderblom, S. Tverdal, et al., "Privacy policy analysis through prompt engineering for LLMs," arXiv preprint, 2024. [Online]. Available: http://arxiv.org/abs/2409.14879
J. Di Rocco, D. Di Ruscio, C. Di Sipio, et al., "On the use of large language models in model-driven engineering," Softw. Syst. Model., 2025. [Online]. Available: https://doi.org/10.1007/s10270-025-01263-8
Y. Liu, "Assessing text readability and quality with language models," M.S. thesis, Univ. Helsinki, 2020. [Online]. Available: http://hdl.handle.net/10138/313475
W. Yuan, G. Neubig, and P. Liu, "BARTScore: Evaluating generated text as text generation," arXiv preprint, 2021. [Online]. Available: http://arxiv.org/abs/2106.11520
D. Trautmann, "Large language model prompt chaining for long legal document classification," arXiv preprint, 2023. [Online]. Available: http://arxiv.org/abs/2308.04138
C. Clark, "The impact of entrepreneurs' oral 'pitch' presentation skills on business angels' initial screening investment decisions," Venture Capital, 2008. [Online]. Available: https://doi.org/10.1080/13691060802151945
M. Mansfield, V. Tamma, P. Goddard, et al., "Capturing expert knowledge for building enterprise SME knowledge graphs," in Proc. ACM Int. Conf. CIKM, 2021. [Online]. Available: https://doi.org/10.1145/3460210.3493569
J. Wang, Y. Liang, F. Meng, et al., "Is ChatGPT a good NLG evaluator? A preliminary study," in Proc. EMNLP NewSumm, 2023. [Online]. Available: https://doi.org/10.18653/v1/2023.newsum-1.1
Z. Wu, L. Zhang, C. Cao, et al., "Exploring the trade-offs: Unified large language models vs local fine-tuned models for highly-specific radiology NLI task," arXiv preprint, 2023. [Online]. Available: http://arxiv.org/abs/2304.09138
K. Żbikowski and P. Antosiuk, "A machine learning, bias-free approach for predicting business success using Crunchbase data," Inf. Process. Manag., 2021. [Online]. Available: https://doi.org/10.1016/j.ipm.2021.102555
J. Y. Bae, S. Malberg, J. Galang, et al., "DIALECTIC: A multi-agent system for startup evaluation," arXiv preprint, 2026. [Online]. Available: http://arxiv.org/abs/2603.12274
M. Kellekci, U. I. T. Cebeci, and O. Dogan, "A methodological framework for venture capital investment decision making using hybrid MCDM and machine learning," in Research Anthology on Multicriteria Decision Making, IGI Global, 2025. [Online]. Available: https://doi.org/10.4018/979-8-3373-7416-1.ch005
G. Perazzo, E. U. Petrocco, R. P. Dameri, et al., "AI in venture capital: Investment decision-making and No Cap case study," in Proc. Ital. Assoc. Inf. Syst. Conf., 2025. [Online]. Available: https://aisel.aisnet.org/itais2025/29
N. T. Jomon, R. Tom, S. Jose, et al., "A comparative review of large language model approaches for startup success prediction and market research," Zenodo, 2026. [Online]. Available: https://doi.org/10.5281/zenodo.18414851
C. Gómez, S. M. Cho, S. Ke, et al., "Human-AI collaboration is not very collaborative yet: A taxonomy of interaction patterns in AI-assisted decision making from a systematic review," Front. Comput. Sci., 2025. [Online]. Available: https://doi.org/10.3389/fcomp.2024.1521066
J. Y. Bae, S. Malberg, J. Galang, et al., "DIALECTIC: A multi-agent system for startup evaluation," arXiv (alt. mirror), 2026. [Online]. Available: https://doi.org/10.48550/arxiv.2603.12274