v6.5 RELEASE · INSTITUTIONAL DECISION ARCHITECTURE FOR INDIVIDUAL INVESTORS

Your portfolio doesn't need more research. It needs an operating system.

FOUNDING-MEMBER PRICING — $247 (reg. $497) · first 100 licenses

Most investors have the same information. The difference isn't insight—it's infrastructure. HARVEST PROTOCOL is a complete investment operating system with quantitative scoring, deployment gates, and behavioral circuit breakers that run on Claude's free tier.

$4,375 avg behavior-gap loss/yr
45 min monthly cycle
9 exit triggers
13% EV hurdle
monthly_buy_session --deploy $9,200
 
SESSION: 2026-04 · PORTFOLIO: $312,400
MACRO: VIX 14.2 · CAPE 32.1 · GATE OPEN
 
DEPLOYMENT QUEUE — 3 PASSES, 2 REJECTS
 
COST composite 82 · EV 16.1% · size $3,800
VEEV composite 79 · EV 14.4% · size $2,600
VOO composite 78 · EV 14.3% · size $2,800
SMCI composite 64 · EV 2.8% · EV_REJECT
PFE composite 58 · EPS↓ · QUALITY_REJECT
 
ALLOCATION: Roth 401k $3,800 · Taxable $5,400
EXITS ARMED: 9 triggers per position
 
→ DEPLOY $9,200 · 2 NAMES BLOCKED · 38 MIN ELAPSED
THE COST OF NO SYSTEM

$4,375 a year. Vanishing quietly.

Behavioral finance research documents an average 1.5–2% annual return loss from preventable decision errors — selling at panic lows, deploying at FOMO peaks, holding positions whose thesis broke months ago.

Morningstar Mind the Gap 2024; DALBAR QAIB 2024 — investor returns lagged fund returns by 1.68% annualized over 10 years.

On a $250,000 portfolio, that is $4,375 per year. Over 10 years compounded: over $60,000 in avoidable wealth destruction. Not from bad picks. From bad process.

PANIC EXIT — MARCH 2020
Sold VOO at −32% drawdown. Bought back 4 months later at +18% recovery. Net behavioral cost on a $100K position.
−$12,500
FOMO ENTRY — NOVEMBER 2021
Deployed $15,000 into high-growth names at CAPE 38. Deployment Gate would have returned INDEX ONLY. Portfolio down 31% over 14 months.
−$4,650
WITH HARVEST PROTOCOL
Gate fires. Capital holds. Process executes. The system's value isn't what it tells you to buy — it's what it tells you not to do.
+$17,150
THE REJECTION PROOF

Not what we bought. What we didn't.

5 names the Deployment Gate rejected in the last 18 months. Average 12-month outcome: −58%. If a $250K portfolio had taken 5% positions in each: $72,500 of avoided loss.

REJECTED MAR 2024
SMCI
Super Micro Computer
REJECTION TRIGGERS
• RSI: 86 → overbought flag (−2 pts)
• EV%: 2.8% vs 13% hurdle → EV_REJECT
• Beneish M-Score: −1.38 → quality flag (−5 pts)
12-MONTH OUTCOME
−72%
REJECTED JAN 2024
LULU
Lululemon Athletica
REJECTION TRIGGERS
• Expectation Gap: UNFAVORABLE → EXPGAP_REJECT
• EV%: 3.1% vs 13% hurdle → EV_REJECT
• Estimate revision cut: −11% in 60 days (−3 pts)
12-MONTH OUTCOME
−43%
REJECTED JAN 2024
PFE
Pfizer Inc.
REJECTION TRIGGERS
• EPS declining YoY: −77% FY23 vs FY22 (−5 pts)
• Earnings miss + guidance cut × 3 qtrs (−5 pts)
• Piotroski F-Score: 3/9 → flagged (−3 pts)
12-MONTH OUTCOME
−37%
REJECTED Q1 2024
WBD
Warner Bros. Discovery
REJECTION TRIGGERS
• Altman Z-Score: 0.94 → distress zone (−5 pts)
• EPS declining YoY — losses widening (−5 pts)
• U/D ratio: 1.1 with VP < 2 → UD_REJECT
12-MONTH OUTCOME
−43%
REJECTED JAN 2024
NKLA
Nikola Corporation
REJECTION TRIGGERS
• Altman Z-Score: −4.2 → pre-filter rejection
• EV%: negative — no FCF path → EV_REJECT
• Short interest: 28% of float (−2 pts)
12-MONTH OUTCOME
−99%
Chapter 11 filed Jun 2024
The Ledger · Cumulative
5 / 5
Rejections that aged well
+$72,500
WHAT THE GATE SAVED
5% positions across a $250K portfolio, avoided across 18 months of Deployment Gate activity.

"The most valuable thing the system does is tell me to hold back. Not because the company is bad—but because the math doesn't justify the risk at this price, in this environment."

— Early Access User · $480K Portfolio · Software Engineering Director

THE QUESTION WE GET MOST

"Why not just ask Claude directly?"

THE AI IS THE REASONING ENGINE. THE PROTOCOL IS THE PRODUCT.

HARVEST PROTOCOL gives Claude a 500-page protocol—with a Deployment Gate, 10-factor scoring, Expected Value Framework, and 9 exit triggers—that converts analysis into a sized, routed, behaviorally-enforced decision. The AI is the reasoning engine. The protocol is the product.

CAPABILITY AI ALONE WITH PROTOCOL
Analysis quality High—but unfocused 40+ quantitative checks, structured
Position sizing None EV-weighted, risk-adjusted
Market timing gate None VIX/CAPE/sentiment deployment gate
Exit criteria None 9 pre-committed triggers
Behavioral circuit breakers None VP disconfirmation, EV decay
THE HONEST COMPARISON

How it stacks up.

FEATURE HARVEST Robo-Advisors Stock Pick Services Asking Claude/GPT Directly
Deployment Gate (VIX/CAPE)
9 pre-committed exit triggers Auto rebal only
EV-weighted position sizing Fixed %
40+ quantitative checks Varies Unstructured
Behavioral circuit breakers
FIRE / tax routing integration
Local — your data stays yours Full account access Cloud Cloud
Cost $247 once 0.25% AUM/yr $99–299/yr $0–20/mo
Decisions or just analysis? Sized + routed Decisions Ideas only Essays only
You stay the operator Partial
FOUR LAYERS

The complete investment operating system.

HARVEST PROTOCOL isn't a stock picker or a newsletter. It's a complete investment operating system with four integrated components that work together to convert research into repeatable, behaviorally-enforced decisions.

LAYER 01

Investor Playbook

30 chapters. Knowledge layer spanning Graham to Dalio. Compiled mental models, frameworks, and decision heuristics from 8 decades of investment literature.

LAYER 02

Analysis Engine

10-sweep BEST protocol with 40+ quantitative checks. Composite scoring, expectation gap analysis, Beneish M-Score, Piotroski F-Score, and VP modeling.

LAYER 03

FinPlan Framework

FIRE planning integration, buy cycle management, tax-advantaged routing, and market-condition deployment gates that prevent bad timing.

LAYER 04

engine.js

Node.js automation layer (Complete System only). Scheduled cycles, batch processing, watchlist monitoring, and automated gate checks.

WHAT'S NEW IN v6.5

Tightened gates. Sharper exits. Better calibration.

📈 DYNAMIC EV HURDLE RATEAuto-adjusts with rates — MAX(13%, Treasury + 8%).
🔍 EXPECTATION GAP ANALYSISReverse-engineers market-implied assumptions from price.
🚪 TIGHTENING TRAILING STOP20% → 15% → trim at +50%. No more round-tripping winners.
🏛️ INSIDER & SUPERINVESTOR SWEEPSEC Form 4 + 13F signals before the press covers them.
⚖️ HALF-KELLY POSITION SIZINGHard caps by score × horizon. Over-concentration becomes impossible.

Get a free Quick Score for any ticker

See the scoring engine in action. 3 free analyses per day. No account required.

TRANSFORMATION

Before / After

BEFORE PROTOCOL

Spends 4–6 hours/month on research
Sells on fear, buys on momentum
No idea if beating VOO after fees
Deploys capital when market is overvalued
Can't weight conflicting analyst opinions
Averages down on broken thesis
Exit decisions driven by P&L anxiety

AFTER PROTOCOL

45–90 minute single monthly session
Pre-committed exit criteria, emotion-independent
Calibration log vs VOO with attribution
Deployment Gate stops bad timing
Composite formula with source weighting
VP disconfirmation trigger fires automatically
Exit triggers independent of price movement
ILLUSTRATIVE SCENARIOS · REPLACE WITH BETA TESTIMONIALS BEFORE LAUNCH

What changes after 90 days.

Placeholder scenarios — illustrate realistic system outcomes. Replace with 3+ real beta testimonials (name, role, portfolio size, concrete outcome) before opening cart. Individual results vary. Not financial advice.

In March I was 20 minutes from buying NVDA at $950 on momentum. The Expectation Gap came back unfavorable. I passed. One pass paid for the system 50x over.

Software Engineer, 34, $340K portfolio

Composite 81—but EV came back at 7%. Passed. It dropped 28% two quarters later.

Finance Professional, 41, $680K portfolio

They all give you ideas. None of them give you a process. This is the first thing that tells me not just what to buy but when NOT to.

Physician, 38, $220K portfolio

THE MATH

The math is simple. The discipline isn't.

Behavioral finance research documents an average 1.5–2% annual return loss from preventable decision errors. On a $250K portfolio, eliminating that gap is worth $3,750–$5,000 per year. The system costs $247 once.

One avoided panic-exit on a 15% decline in a $10,000 position pays for 4 years of the system.

ONE-TIME INVESTMENT
▸ HARVEST PROTOCOL bundle $247 (once)
▸ Claude Pro (optional upgrade) $240/yr if upgraded
ANNUAL BENEFITS
▸ Behavior gap eliminated +$4,375/yr avg
▸ Tax optimization / routing +$750–$1,750/yr
▸ Time reclaimed (13 hrs/mo) 156 hrs/yr
NET ANNUAL BENEFIT $4,000–$6,000/yr

Behavior gap estimate from Morningstar Mind the Gap 2024 and DALBAR QAIB 2024. Individual results vary.

THREE PATHS IN

Choose your system.

Buy-side research desk: $2,400+/mo · Seeking Alpha Premium: $299/yr · Robo-advisor on $250K: $625/yr · HARVEST PROTOCOL: $247 once

STARTER
$127
one-time payment
  • Investment Analysis Engine v6.5
  • FinPlan Framework
  • Investor Playbook (30 chapters)
  • Setup Guide (all 4 workflow tiers)
  • Sample output walkthrough
  • All future v6.x updates
  • engine.js automation layer
  • Community Discord access
5 SPOTS / MONTH
PRO + COACHING
$897
one-time payment
  • Everything in Complete System, plus:
  • 3 × 60-min private sessions
  • Methodology configuration for your setup
  • Custom FIRE projection setup
  • First BEST cycle together
  • Priority email support
  • 12-month accountability check-in
🔒 YOUR DATA IS ALWAYS YOURS

HARVEST PROTOCOL runs on your machine, in your AI account. We never see your portfolio, income, or net worth. Zero data sent to us. Ever.

No Claude subscription required to start. Begin with a free Claude account. Upgrade to Pro ($20/month) when your workflow demands it.

30-day money-back guarantee on all tiers · Personal use license · Not financial advice

QUESTIONS

Everything you need to know.

No. Tier 1 of the workflow requires only a Claude Pro account and ~20 minutes of one-time setup — paste the protocol files into a Claude Project and run the prompts. The Complete System adds engine.js, an optional Node.js reference implementation that batch-processes watchlists; setup instructions walk you through it line by line. If you can install an app, you can run it.
Hallucination risk is real, and the system is designed around it — not in spite of it. Quantitative inputs come from the Alpha Vantage API as the primary source; every fallback (free tier limits, missing fields) is disclosed inline in the output. Every numerical claim is cited. The protocol’s job is to structure Claude’s reasoning around verified data and force it to flag what it doesn’t know. You are still the final auditor against primary sources (10-K, 10-Q, earnings transcripts).
Because unstructured AI gives you a balanced essay that decides nothing. The protocol gives Claude a 500-page system — Deployment Gate, 10-factor composite scoring, Expected Value Framework with a dynamic hurdle rate, Half-Kelly position sizing, and 9 pre-committed exit triggers. The output is not “here are some things to consider.” It is “deploy 8.5% of portfolio in this account, with these nine exit triggers armed.” The AI is the reasoning engine; the protocol is the product.
The protocol works at any portfolio size. The dollar value of behavioral guardrails scales with your account, but the habit value is largest when the portfolio is small — you build the discipline before your decisions involve six figures of capital. The same Deployment Gate, the same EV check, the same exit triggers fire on a $20K position as on a $200K position.
Meaningful calibration data — the kind that lets you say “my decisions outperformed VOO by X over Y months” — requires roughly 10–15 picks with 12-month outcomes. Plan on 12–15 months for that. Before then, the value shows up in two places: (1) process discipline — you stop making panic exits and FOMO entries, and (2) time — a 45-minute monthly cycle replaces 4–6 hours of unstructured research.
Completely. HARVEST PROTOCOL is a local operating system. Your portfolio data, positions, and analysis history live in your Claude Project and on your own machine. We have zero visibility into any of it. We do not see your trades, your net worth, or your tickers. There is no telemetry, no analytics, no “anonymized usage” feedback loop.
The protocol is model-agnostic by design. The reasoning system is documented in plain markdown and runs at ~85% fidelity on any frontier model — Claude, GPT-4/5, or successor systems. engine.js runs locally and is decoupled from any particular vendor. If Anthropic deprecates a model or shifts pricing, your purchased copy of the protocol keeps running on whatever capable model exists at the time. Buyers receive free updates within v6.x; v7.0+ may require a paid upgrade with a guaranteed 18-month backward-compatibility window.

The next market drop will reveal whether you have a system.

When markets fall 25%, most investors panic. The ones with a Deployment Gate, pre-committed sell criteria, and a VP disconfirmation trigger don't panic—they execute.

THE GUARANTEE

Run one full monthly BEST cycle. If it doesn't change how you make your next investment decision — full refund, no questions, you keep the Playbook.

That's the deal. We don't promise returns. We promise the protocol will change how you decide — or we don't keep your money.

Install the System — $247 →

30-day money-back · Personal use license · All future updates included · Not financial advice. All investments involve risk.