Multimodal Information Input Processing Prompts In Obsidian

General Input Processing

The prompt's starting point is to address the challenge analysts face in efficiently processing, retaining, and retrieving critical insights from an overwhelming volume of unstructured information (e.g., transcripts, reports, verbal discussions). Its methodology involves a systematic "structured information extraction and synthesis," guiding the AI to act as an intelligent assistant that actively processes, categorizes, and interlinks information based on predefined rules. This is achieved through mechanisms such as logical summarization and hierarchical organization, automatic Wikilinks for key entities, number highlighting for significant data, table summarization for relevant figures, sentiment analysis, and relevant tagging. The primary purpose is to enhance the analyst's ability to rapidly grasp core insights, improve knowledge retention, facilitate analysis and decision-making, and streamline collaboration. The outcome is a highly structured, semantically rich Obsidian Markdown note that is readily searchable, highlights critical information, presents logical flow, and is directly usable for further analysis, significantly reducing the time and effort for manual information structuring.

Verbal Content Processing

This prompt, specifically designed for analytical purposes, originates from the challenge of efficiently processing large volumes of unstructured verbal content such as interview transcripts, earnings calls, or podcasts. Its methodology involves a systematic, multi-faceted approach to transform raw text into a highly structured, analyzable, and archivable Obsidian note. This is achieved through several key mechanisms: first, synthesizing the entire transcript into a concise "Key Logic" summary; second, organizing content hierarchically using headers and multi-level nested bullet points; third, automatically identifying and linking all key entities (companies, products, people, concepts) via Obsidian's wikilink syntax; fourth, highlighting critical numerical data, parameters, and dates for rapid scanning; and finally, generating comprehensive tags for efficient categorization and retrieval. The ultimate purpose of this prompt is to significantly improve the efficiency of information intake and knowledge consolidation, enabling analysts to quickly grasp core messages, identify important entities, extract critical data, and effectively integrate insights into their knowledge base.

Behind the paywall I put my system prompt used in all my usecases and showed in my videos.