Novel Agentic LLM Framework for Startup Intelligence through Web and API Integration

Read full text Summarise with VIRAT
Authors: J. UmaMaheswari, P. Abinayajothi, C. Abarna
Cited by: 0
References: 5

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper presents an automated pipeline that uses large language models (LLMs) to simplify startup discovery and intelligence gathering. The system generates targeted search queries, retrieves relevant web data, and extracts structured information from third-party APIs, reducing the manual effort needed for research. Supporting tools handle tasks like entity resolution, data parsing, and ranking, ensuring accurate and reliable results. The pipeline does not require custom model training. Instead, it uses prompt-based agents to manage all stages, including searching, scraping, enriching, and summarizing data. By producing concise, decision-ready insights, the framework helps venture capital firms, startup scouts, and innovation teams make faster, better-informed decisions. Its modular design makes it easy to replicate and scale, offering an efficient and practical solution for startup intelligence workflows.

Fields of Study & Subjects

Topic Modeling Information Retrieval and Search Behavior Web Data Mining and Analysis

Publication details

Journal / source
International Explore Journal of Computer Science and Applications
Volume
4
Issue
1
Pages
1–7
Publication date
28 February 2026
Language
EN