FinMRI: the flagship project of Rainbow After Storm
An MRI for any US stock.
FinMRI assembles a virtual hedge-fund team of AI agents that turns market, news, sentiment and fundamental data into a full-picture risk read. It's a diagnostic scan for what you hold, not a buy/sell signal machine.
How the agent team works
- 1
Analysts
Gather market, news, social-sentiment and fundamental data for the stock you ask about.
- 2
Bull vs. bear debate
Opposing analyst theses argue over several structured rounds, then a consolidation pass weighs both sides.
- 3
Trader
The consolidated view is translated into concrete execution planning.
- 4
Risk team
Aggressive, conservative and neutral risk perspectives each review the plan independently.
- 5
Portfolio manager
A final decision layer produces the comprehensive, attributable risk read.
Built for understanding what you hold, not chasing signals
Most quant tools emit buy/sell signals. FinMRI is for medium- and long-term investors asking a different question: where does this stock stand right now, and what are the honest arguments on both sides?
Forcing explicit bull and bear theses before consolidation produces materially more honest output than asking one model for "an analysis." The result is attributable: you can see which agent said what, and why.
FinMRI's output is model analysis for reference only. It is not investment advice, and it says so prominently in the product.
Every stage is visible while it runs
Eleven agents report in turn, each one ticking over as it finishes. You can see how far along the analysis is and which stage produced which part of it.
Nothing arrives as a black-box score, and nothing is hidden behind a spinner.
Want a walkthrough, or this approach applied to your domain?
The same multi-agent architecture behind FinMRI (structured debate, risk review, attributable output) transfers to other analysis-heavy domains. Tell me what you're thinking.
Or just go poke at it. It's live.
Open FinMRI ↗