HV Analysis, the horizontal-vertical method, researches a subject along two lines. The vertical line tells its story from origin to today with causes for each turn. The horizontal line compares it with current competitors or peers, using real user voices.
The two lines then cross in a section that explains how history shaped today’s position and sets out three scenarios. The default delivery is a report of ten to thirty thousand characters as PDF plus a Markdown source, with every key fact numbered against a source list.
What You Get
- A long-form report with a one-line definition, vertical analysis, horizontal analysis and a crossing section
- Numbered citations that tie each key fact to a source list marked first-hand, second-hand or the party’s own claim
- A PDF with cover, headers and Chinese fonts, plus the Markdown source
- Flags in the text for single-source facts, conflicting accounts and missing information
Common Use Cases
- Researching a competitor or a whole competitive field before a decision
- Preparing source material before writing an article
- Learning a new technology concept or company history from scratch
- Profiling a person’s career against peers in the same field
What Makes It Unique
The method forces a verdict from the crossing of two views, so a timeline and a comparison table alone do not count as finished. The evidence rules are strict: current facts need current sources, a ledger records each fact’s source, event date and publication date, the agent searches for evidence against its own emerging judgement, and it states gaps and never fills them from memory. It is also explicit that it will not claim a PDF exists when the converter could not run.
Under The Hood
The agent searches the web and reads pages with whatever search and fetch tools the host provides, optionally splitting the three research lines across subagents, and it may query the arXiv API for papers. It writes the report as Markdown in your working folder. To make a PDF it runs a bundled Python script through the shell; for that it creates or reuses a virtual environment in your user cache folder, installs the markdown and weasyprint packages with pip, and writes HTML and PDF files. It can also save the Markdown into an Obsidian vault path you name.