New company disclosure
Selected SEC and configured issuer IR sources are discovered and preserved.
AI-native investment research
Suvi is building an evidence-grounded investment research system for people who care about the business behind a stock.
Start with AgenticThesisOpen-source thesis monitoring · AgenticThesis
An open-source AI agent that tests your investment thesis—why you own a stock—against new company filings—with exact citations, human review, and version history.
The agent proposes. The investor decides what becomes thesis history.Explore AgenticThesis
Selected SEC and configured issuer IR sources are discovered and preserved.
Radar routes evidence against explicit claims and falsifiers before analysis.
Each proposed change retains exact source citations and an explicit status.
Approval or rejection remains with the investor before version history changes.
From disclosure to reviewed history
AgenticThesis keeps the source, proposed change, review decision, and resulting thesis version connected.
Record why the business deserves attention and what would prove each reason wrong.
Monitor selected SEC and explicitly configured issuer IR disclosures.
Preserve original artifacts and source-addressable citation spans.
Show which claims are supported, weakened, possibly invalidated, or unknown.
Only Human Review can make a proposed change authoritative.
Available today · bounded by evidence
New events are matched against versioned claims and falsifiers before model use.
Accepted quotes resolve to preserved artifacts, pages, or exact character ranges.
No proposed thesis change becomes authoritative without explicit review.
Checkpoint, resume, replay, and conflict protection preserve long-running work.
Open source · self-hosted · human-reviewed