A five-stage research pipeline.
From raw data to verified recommendation in under a minute. Every stage designed for one thing: eliminating confident-but-wrong answers.
Ingest
Real data. Not training data.
When you ask about a ticker, we don’t query some cached summary. We pull it live: the most recent 10-Q from SEC EDGAR, today’s Treasury yields from FRED, real-time prices from multiple market feeds, the latest employment and inflation prints from BLS, and nine other authoritative sources. Everything fresh. Everything traceable.
Analyze
Three lenses. Same evidence. Independent analysis.
The gathered data is examined in parallel by three investment lenses — Quality, Momentum, and Context. Each applies its own discipline: fundamentals and competitive position (Quality), price action and sentiment (Momentum), and macro/sector context (Context). Under the hood, each lens is backed by a frontier model (Claude, GPT, Gemini) so no single vendor's blind spot becomes yours. Each lens produces a structured analysis: recommendation, confidence, signals with cited data, and explicit risks.
Verify
Every claim, cross-checked against the source data.
A supervisor reviews all three analyses. It compares conclusions and flags genuine disagreements. Then it verifies every factual claim actually appears in the source data block. Any claim that can’t be verified is flagged as a red flag — and the overall confidence is downgraded accordingly.
Calibrate
Consensus strength determines confidence.
Unanimous across all three lenses with verified data → HIGH confidence. Majority (2 of 3) → downgraded one level. Split decision → defaults to HOLD with LOW confidence. Any lens returning INSUFFICIENT_DATA triggers an honest escalation: we tell you what we'd need to produce a more confident call.
Deliver
A brief you can act on. Or show your advisor.
The final output isn’t a paragraph of hedged copy. It’s a structured brief: the recommendation, the consensus strength, the agreed-upon signals, any disagreements between models, any red-flagged claims, and a plain-language summary. Every data point links back to its source.
What a brief looks like.
Five-stage pipeline, rendered as a single structured document — verdict, consensus strength, the three lenses’ signals, disagreements, and every claim citing its source.
Services revenue +16% YoY (10-Q, Q2 FY26); operating margin 31.5%, sector median 14.8%.
50d MA above 200d MA; RSI 58 (neutral-bullish); 20-day volume +12% vs 90-day avg.
Fed funds 5.33% compresses mega-cap multiples; China revenue −9% (10-Q); supply-chain headlines elevated.
Quality and Momentum support a BUY on fundamentals and trend. Context flags macro headwinds (rates, China) that could compress multiples on a 3–6 month horizon.
A BUY call, but downgraded to MEDIUM confidence because the three lenses split 2-to-1. Entry under $180 preferred. Re- evaluate after next FOMC or the FY26 Q3 print, whichever comes first.
What we will never do.
Every number cited traces to a source
If a figure appears in an analysis, you can click through to exactly where it came from — SEC document, Fed series, or market feed.
We tell you when we don’t know
If the data is sparse or the models disagree, you see a LOW-confidence HOLD with an explicit list of what we’d need to be more certain — not a confident guess.
You see disagreement, not hidden consensus
If the Quality lens says BUY but Momentum says SELL, that disagreement shows up in your brief. Other tools hide it. We surface it.
See it on your portfolio.
Free 30-day trial. No credit card. Full access to all three lenses.