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

A developer built DisconfirmAI, an AI investment research workspace that applies Karl Popper's falsification principle by seeking counter-evidence before building conviction in a stock thesis. The tool splits research answers into Verified, Inferred, and Doubtful sections, curates a Daily Reading feed from primary sources, and includes a Radar feature that scans user-defined exit conditions on a schedule, logging a 'scanned-and-empty' audit entry when nothing material changes. It outputs no buy/sell recommendations or price targets and is accessible in the browser without registration.

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. If you ask why a company looks undervalued, it will assemble a convincing bull case. In financial research, that habit is risky. I built DisconfirmAI https://disconfirmai.com/en 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. Here is how the workspace is structured: The Daily Reading https://disconfirmai.com/en/reading feed curates AI industry and market developments from primary sources, keeping original links and publication dates. Editorial annotations use three fixed labels: In the Research https://disconfirmai.com/en/features/research workflow, questions about earnings releases, multi-year financials, and SEC 13F institutional holdings calculated strictly by share-count changes rather than market-value fluctuations are split into three sections: Verified , Inferred , and Doubtful . It does not output buy/sell recommendations or price targets. In Investment Framework https://disconfirmai.com/en/features/system , you write down your circle of competence, entry rules, and the exact conditions that would force you to revise or exit a position. Radar https://disconfirmai.com/en/features/radar scans those conditions on a schedule. When nothing material changes, it stays quiet and logs scanned-and-empty in the audit trail. Everything below is open in the browser without registration: If you analyze tech or AI companies or build financial research workflows, I would love your feedback on the tools and the falsification approach: https://disconfirmai.com/en https://disconfirmai.com/en