product-research

Automated Amazon product research uses LLM agents and Sorftime MCP to execute data collection, attribute tagging, and competitor reviews analysis. It coordinates VOC extraction and decision scoring across multiple sites to deliver end-to-end product deep-dives.

VOC extraction analyzes customer voice from competitor reviews to inform Amazon category selection. This process uses LLM-driven cross-analysis to identify pain points and market barriers, generating decision scoring that outputs Markdown reports and visual dashboards.

End-to-end product research for Amazon US and JP marketplaces is initiated via a command like /product-research "bluetooth speaker" US. The LLM agent executes stepwise data collection and barrier assessment, allowing mid-course interventions to generate visual dashboard insights.

Yes, Amazon product analysis requires Sorftime MCP API access and a Bash-enabled environment. This setup allows the provided scripts to perform automated data collection and LLM-driven analysis, which are essential for executing cross-analysis and barrier assessment.

This LLM agent workflow integrates cross-skill with category-selection, amazon-analyse, review-analysis, and sif-amazon-research. This interoperability provides a holistic view of product research, combining competitor reviews and deep-dive study outputs.

Limitations for Amazon product barrier assessment include strict dependencies on Sorftime MCP API availability and a Bash environment. Without these, automated data collection and LLM-driven cross-analysis cannot execute, halting the decision scoring process.