A1Data Fetcher· institutional APIA2Technical Analyzer· real-time technicalsA3Sentiment Scanner· news & socialA4Risk Calculator· Altman Z · D/E · betaA5Narrative Generator· plain-English explainA6Auditor· cross-checks every claimA7Compliance Monitor· logs the evidence trailVValue Lens· Buffett & MungerGGARP Lens· Peter LynchQQuant Lens· Simons · ShawMMacro Lens· Dalio · SorosXMulti-Strat Lens· Griffin · EnglanderA1Data Fetcher· institutional APIA2Technical Analyzer· real-time technicalsA3Sentiment Scanner· news & socialA4Risk Calculator· Altman Z · D/E · betaA5Narrative Generator· plain-English explainA6Auditor· cross-checks every claimA7Compliance Monitor· logs the evidence trailVValue Lens· Buffett & MungerGGARP Lens· Peter LynchQQuant Lens· Simons · ShawMMacro Lens· Dalio · SorosXMulti-Strat Lens· Griffin · Englander
AI Verification · Not AI Advice

See the math.
Trust the data.

Glass Box shows you exactly why every risk score is what it is — the raw institutional data, the formula, and an independent audit before you see any number. No black box. No hallucinations displayed unchecked.

No credit card required
5 free verifications daily
Research tool, not advice
E&O insured
Live verification — illustrative
A6 Auditor active
8.4
Score
Apple Inc. — AAPL
NASDAQ · Technology✓ A6 Verified · 14:32
Debt / Equity Ratio
1.78
FMP API · 2 hr ago
Altman Z-Score
6.24
FMP API · Very Low Risk
Beta vs S&P 500
1.22
Twelve Data · Live
✓ Auditor A6: narrative matches raw API · 0 discrepancies found
The Strategy Lenses

Eight legendary lenses. One audited score.

Each lens is pretrained on a legendary investor's documented strategy and reads your holdings for growth and risk — every view traces back to the same audited data. Lenses inform; they never advise.

LEAD LENS
The Value Lens
Value & Buy-and-Hold
Pretrained on Buffett & Munger
Berkshire Hathaway · Value / Buy & Hold
📈 ~20% annual, 50+ yrs
Growth70
Risk18
The GARP Lens
Growth at Reasonable Price
Pretrained on Peter Lynch
Fidelity Magellan · GARP
📈 29.2% avg annual (1977–90)
Growth86
Risk34
#1 · ~$74B
LEAD LENS
The Multi-Strat Lens
Multi-Strategy
Pretrained on Ken Griffin
Citadel · Multi-Strategy
📈 ~$74B lifetime net gains
Growth82
Risk40
#2 · ~$58B
The Macro Lens
Global Macro / Risk Parity
Pretrained on Ray Dalio
Bridgewater · Global Macro
📈 ~$58B lifetime net gains
Growth74
Risk44
#3 · ~$51B
The Quant Lens
Quantitative
Pretrained on Jim Simons
Renaissance Tech · Quantitative
📈 ~$51B lifetime net gains
Growth90
Risk28
#4 · ~$50B
The Allocation Lens
Multi-Strat Risk
Pretrained on Izzy Englander
Millennium · Multi-Strategy
📈 ~$50B lifetime net gains
Growth68
Risk22
#5 · ~$43B
The Algo Lens
Quant / Multi-Strategy
Pretrained on David Shaw
D.E. Shaw · Quant
📈 ~$43B lifetime net gains
Growth80
Risk30
#6 · ~$41B
The Reflexive Lens
Global Macro
Pretrained on George Soros
Soros Fund Mgmt · Global Macro
📈 ~$41B lifetime net gains
Growth78
Risk58
V
Buffett & MungerValue & Buy-and-Hold

click a lens to hear its story · drag / arrows to slide · filter to spin the desk

⚠ Important: Glass Box is a financial research and data-verification tool. It does not constitute investment advice; all scores are informational. The Strategy Lenses are original AI archetypes that study the publicly documented philosophies of well-known investors — named as inspiration only. Glass Box is not affiliated with, endorsed by, or representing any named investor or firm, and portraits are original illustrations, not likenesses. Track-record figures are historical facts about each investor's public record, not a promise of Glass Box performance.
0.0%
AI accuracy this week
0
errors caught by A6
0
errors shown to users
0.0
user trust score
View full audit log →
How Glass Box works

Not AI magic.
AI math — audited.

01 — FETCH

Agent A1 pulls institutional data

Debt-to-equity, Altman Z-Score, free cash flow, 30 years of history — directly from Financial Modeling Prep's institutional API. Twelve Data provides real-time technicals. No aggregators, no intermediaries.

A1 Data Fetcher · A2 Technical Analyzer · A3 Sentiment Scanner
02 — EXPLAIN

Agent A5 translates to plain English

A configured narrative agent generates a clear summary from the underlying risk metrics. Every number in the text traces back to its raw data source. Every claim is auditable, not asserted.

A4 Risk Calculator · A5 Narrative Generator
03 — AUDIT

Agent A6 audits before you see it

The Auditor cross-checks the narrative against raw API data. If anything doesn't match, it's flagged and corrected before display. You only see verified output — and we publish the error rate publicly, every week.

A6 Auditor · A7 Compliance Monitor
Trusted Data · Trained Models

What the models learned — and from where

Transparency isn't only about the audit. It's about what went in. Here's the provenance behind every score.

🏛

Institutional sources

FMP + Twelve Data — the same feeds funds pay for, never scraped aggregators.

30 yrs history
🧮

Deterministic core

Risk math (Altman Z, D/E, beta) is formula-based and reproducible — no model guesswork on the numbers.

auditable
🧠

Narrative models

LLMs explain, they don't decide. Trained to summarize the metrics, constrained to cite every claim.

Qwen · Llama · cloud
🛡

Audit layer

A6 checks every narrative against raw data. Weekly error rate published — nothing hidden.

0 shown to users

Was this verification useful?

Your rating helps us track how useful the evidence trail actually is — logged locally in this demo, not yet wired to a live trust-score pipeline.

For Advisors

Built for the conversation with your client, not just the score.

An evidence trail your clients can see

When a client asks "why does it say that?", point to the exact API response and the audit that checked it — not a black-box score.

Compliance-ready by default

Every verification is logged with its source data, its narrative, and its audit result. Export the trail for E&O documentation or a compliance review.

Multi-client, white-label ready

Run verifications across client portfolios and hand back reports branded for your practice, not ours.

★★★★★

Finally — a platform that shows me where the number came from. My clients ask 'why does it say that?' and I can now point to the exact API response. That's career-defining trust-building.

MD
M. Donovan
Fee-only RIA · New Jersey
★★★★★

The Discrepancy Rate widget changed how my clients think about AI. Instead of 'is this reliable?' they now ask 'what's the error rate this week?' That's a fundamentally different — and better — conversation.

PR
P. Ramirez
Independent CFP · California
Pricing

Start free. Upgrade when you trust us.

No dark patterns. All prices visible. Cancel anytime.

Free
$0
forever · no credit card needed

5 stock verifications per day
Full Evidence Path — raw data visible
A6 Auditor confirmation badge
Discrepancy Rate dashboard
Portfolio Glass Box Score
Crisis Alerts
Start Free
Most Popular
Standard
$20
per month · cancel anytime

200 verifications per month
Portfolio Glass Box Score
Crisis Alerts — real-time
Stress Test — historical crisis simulator
Weekly Discrepancy Report email
Broker import via SnapTrade
Start Standard →
Advisor
$150
per month · for independent advisors

Unlimited verifications
White-label Client Reports PDF
API access for custom integrations
Multi-client portfolio management
Compliance audit log export
30-day free trial — no risk
Start 30-day Trial
From the desk

Notes on transparency.

Coming soon

Why we publish our own error rate

Every AI research tool makes mistakes. Most hide them. Here's why showing ours, every week, is the point.

Coming soon

How Agent A6 audits Agent A5

A walkthrough of the verification step that runs before any narrative reaches your screen — and what happens when it disagrees.

ƒ
Coming soon

Reading a Debt/Equity ratio without the jargon

The raw metrics behind a risk score, explained the way we'd explain them to a client.