A master thesis from Aalborg University
Leveraging LLMs to Generate Business Plans
Author(s)
Term
4. semester
Publication year
2025
Submitted on
2025-06-02
Pages
74 pages
Abstract
In today's competitive business environment, well-structured business plans are essential for startups to be successful and secure funding, yet many small businesses lack the resources to create them effectively. To provide a convenient solution for the stated problem, this research investigates how Large Language Models (LLMs) can be utilized to generate business plans and examines the benefits and limitations compared to traditional planning methods. A multi-agent system was developed using the CrewAI framework, employing six specialized agents for different business plan sections, with Google's Gemini 2.5 Pro for content generation and Meta's Llama 3.3 70B for initial evaluation. The system was tested using both expert-provided fictional company data and synthetic data generated from existing business plans using GPT 4.1. Evaluation employed both human expert judgment and LLM-as-a-Judge techniques across five metrics including relevance, completeness, correctness, consistency, and clarity. Results demonstrate that LLMs can generate structurally coherent business plans with relevant content across all sections, offering significant advantages in speed, cost-effectiveness, and accessibility for startups. However, the generated plans can be utilized as drafts only, since limitations include hallucination tendencies, inconsistencies between sections, and lack of deep business insights that human expertise provides. The research concludes that AI-generated business plans serve best as starting points and still requires human review and refinement, representing a complementary tool rather than a complete replacement for traditional business planning methods.
Keywords
Documents
Colophon: This page is part of the AAU Student Projects portal, which is run by Aalborg University. Here, you can find and download publicly available bachelor's theses and master's projects from across the university dating from 2008 onwards. Student projects from before 2008 are available in printed form at Aalborg University Library.
If you have any questions about AAU Student Projects or the research registration, dissemination and analysis at Aalborg University, please feel free to contact the VBN team. You can also find more information in the AAU Student Projects FAQs.