Building DisconfirmAI: An AI investment research workspace that looks for counter-evidence first

Description and use

DisconfirmAI transforms investment research by applying Karl Popper’s falsification principle: first seek evidence that disproves a thesis rather than confirms it. The platform offers structured workflows that separate evidence by credibility and provides AI‑market analysis tools.

Problem

General-purpose LLMs tend to confirm user premises when analyzing stocks, creating risky bias in financial research.

Outcome

DisconfirmAI shifts investment research from confirmation bias to systematic falsification, enabling investors to identify and act on counter‑evidence before committing capital.

Workflow

• Curate daily primary‑source feed with editorial labels (Background, Doubt, Editor’s Note).
• Separate SEC filings, earnings, and 13F research into Verified, Inferred, and Doubtful sections.
• Define investment framework with circle of competence, entry rules, and exit conditions.
• Schedule Radar to scan conditions; log "scanned-and-empty" when no changes.
• Use open AI industry databases and 23 free valuation tools for independent analysis.

Evidence

When you use a general-purpose LLM to analyze a stock or read an earnings report, it tends to agree with whatever premise you put in the prompt.

Source

I built DisconfirmAI around a simple rule from Karl Popper and value investing: before building conviction in a thesis, look for the specific evidence that would prove it wrong.

Source

In the Research workflow, questions about earnings releases, multi-year financials, and SEC 13F institutional holdings are split into three sections: Verified, Inferred, and Doubtful.

Source

When nothing material changes, it stays quiet and logs scanned-and-empty in the audit trail.

Source