SPY 708.45 -0.39% QQQ 651.42 -0.56% VIX 19.31 +2.06% CAT 835.24 +8.3% 5D · BUY 74 BA 234.15 +7.0% 5D · BUY 72 JPM 311.69 +0.6% 5D · BUY 61 GE 282.34 -5.3% 5D · PASS REGIME CHOP FIVE HARD RULES ACTIVE SPY 708.45 -0.39% QQQ 651.42 -0.56% VIX 19.31 +2.06% CAT 835.24 +8.3% 5D · BUY 74 BA 234.15 +7.0% 5D · BUY 72 JPM 311.69 +0.6% 5D · BUY 61 GE 282.34 -5.3% 5D · PASS REGIME CHOP FIVE HARD RULES ACTIVE
SKU #08 · live now

The AI trader that never sleeps.

Sentinel reads insider Form 4s, earnings-drift windows, and live tape. Four agents debate every ticker before a single share is bought. Five hard rules cap your worst day. Ships as one folder. Runs on Alpaca paper. Your journal writes itself.

4agents debate every pick
5rules · regime-gated
-10.7%max DD (v2 backtest crisis slice)
$0monthly infra · paper-first
SENTINEL
2026-04-23 · REGIME CHOP · ● LIVE PAPER
Equity
$100,382
+0.38% today
P&L
+$382
3 open
Win Rate
58%
12/21 last 30d
Sharpe
1.42
rolling 30d
Rules
OK
0 red days
Regime
CHOP
VIX 19.3
Cash
$42,110
42% buffer
Next
BUY CAT
74 conf

Four agents. One debate. Zero fake confidence.

Every candidate ticker goes through a deterministic debate before it can be bought. Each agent votes BUY, HOLD, PASS, or VETO — and any single VETO kills the trade. It's not an LLM jury. It's four opinionated rules with accountability logged to your journal.

01 · TECHNICAL

Is the tape rising?

Price above 10-EMA, 5d positive, 1d not a crash. If the trend is broken, the agent PASSes. If it's clean and accelerating, BUY with high confidence.

02 · MACRO

Is the regime safe?

Reads SPY, VIX, sector tape. VETOes on SPY ≤ -1.5% intraday or VIX ≥ 25. Neutral tape = HOLD, not BUY. The agent that can kill the trade.

03 · RISK

Is the ATR in range?

Daily ATR > 5% or today < -3% = VETO. In tolerance = BUY with full size. Tight = BUY but size-sensitive. No trade ever ships without this check.

04 · SENTIMENT

Is the crowd waking up?

Insider-flagged + 5d momentum = BUY. Insider-flagged but tape disagrees = PASS (contradiction). Tepid = HOLD. Protects against one-sided signals.

Your worst day is capped before it happens.

Most traders don't die from bad picks. They die from bad days. Sentinel enforces five rules taken straight from professional desk risk playbooks — hard-coded, not suggestions. You can't override them during a losing streak.

RULE 01
Daily loss limit — halt at −2R
Down 2R ($200 on a $100k paper account)? New buys stop. Sells still run. Come back tomorrow.
Risk Halt
RULE 02
No adds to losers — pyramid winners at +1R
You can only scale into a position once it's already +1 ATR above entry. Losers don't get fed.
Entries
RULE 03
Position caps — 3 per sector, 6 total
Nobody gets over-concentrated in Tech or Banks. Hard cap, not a suggestion.
Concentration
RULE 04
De-gross on streaks — 3 of 10 red days
Three red closes in the last ten days? Size drops 50% automatically until the streak breaks.
Streak Shield
RULE 05
First-15-min half-size
The open is where retail gets slaughtered. Any entry in the first 15 minutes is half-size by default.
Open Guard

One folder. One command. One trader.

No cloud. No subscription to a signals service. No "AI trading bot" SaaS with 90% churn. This is the full paper-trading OS I run on my own account — packaged, documented, yours to keep.

→ CODE

Full Python engine

live_engine.py, ai_trader.py, all signal generators for insider Form 4, PEAD, ML baseline. ~3,000 lines, commented.

→ HUD

Sentinel dashboard

Single-file HTML/CSS/JS dashboard in the biskin.studio palette. Equity sparkline, debate chips, live rule feed, portfolio marketplace.

→ RULES

Five-rule risk layer

Every rule wired into the buy path. Daily reset, pyramid scaler, sector caps, de-gross streak logic, open-guard sizing.

→ JOURNAL

Auto-written trading journal

Every decision logged as dated Markdown in data/ai_trader_journal/. Debate votes, rationale, P&L, regime. Feeds Obsidian or Claude directly.

→ BACKTEST

Historical rule validator

Run the rules against 2+ years of daily CSVs. See exactly what they would have saved you in March 2020, Aug 2024, Apr 2025.

→ SETUP

20-min video + README

Alpaca paper keys, Python env, first run, HUD on localhost. From zip to live tape in under half an hour.

One price. Three levels of serious.

Solo
Sentinel Solo
$79
Everything to run it yourself.
  • Full Python trading engine
  • Sentinel HUD dashboard
  • Five-rule risk layer
  • Four-agent debate system
  • Insider Form 4 + PEAD signals
  • Auto-journal (Markdown)
  • Historical rule backtester
  • 20-min setup video
Buy Solo — $79
Most Popular
Sentinel Kit
$149
For the trader who wants the whole playbook.
  • Everything in Solo
  • 60-min deep walkthrough video
  • Pre-configured Alpaca keys guide
  • Rule-tuning cheat sheet (1R, sector map, halts)
  • Sentinel Portfolios marketplace template
  • Private Discord invite
  • 1 × 60-min onboarding call
  • Free lifetime updates
Buy Kit — $149
Desk
Sentinel Desk
$299
Trader stack + every biskin agent pack.
  • Everything in Kit
  • All 7 Biskin Studio agent packs
  • Trading Team pack ($99 value)
  • Marketing + Engineering + Strategy + Design + Life Ops
  • Claude Desktop MCP config for your journal
  • "Your AI's trading desk" positioning deck
  • Priority support
  • First access to v2 features
Buy Desk — $299

Things people actually ask.

Is this a get-rich-quick bot?

No. It's a disciplined paper-trading OS. It removes the four worst habits most traders have — overtrading, adding to losers, over-concentration, trading after losses — and writes a journal while it does it. Edge comes from discipline + signal, not magic.

Does it trade with real money out of the box?

No. Default is Alpaca paper (free). You can flip the API key to a live account once you've watched it run for 30+ days and backtested it against your style. I don't recommend live until you've seen it handle a red week.

What data feeds does it need?

Free: Alpaca paper API, Yahoo Finance (yfinance), SEC EDGAR for Form 4, optional Finnhub free tier. No paid data required to start. Upgrade paths documented.

What's the edge vs. buying an index fund?

The honest answer: probably nothing, over 30 years, net of taxes. The useful answer: this teaches you how insiders, analysts, and desks actually think, with a written record of every decision. It's a training machine as much as a trading one.

Do I need to know Python?

To install: no — the setup guide is zip-to-running in 20 minutes. To modify signals or tune rules: yes, a little. Every file is commented. Claude Code handles the rest.

What about the backtest numbers?

Real v2 backtest, three arms (baseline / rules_on / rules_gated), SPY 60-day regime proxy. Crisis slice: baseline -6.6%, rules-gated -1.9% return, DD -12.7% → -10.7%. Trend slice: baseline +9.5% Sharpe 1.30, rules-gated +5.4% Sharpe 0.82 — gate beats naive rules (+3.4% Sharpe 0.57) in the regime where caps hurt. Honest caveat: 221 trading days, no 2022-style bear in the data yet. The backtester ships with the product — run it on your own window, I don't post cherry-picked screenshots.

Refunds?

Gumroad default: 30-day refund, no questions. If the setup guide doesn't get you to a running HUD in an hour, you didn't get what you paid for. Email team@biskin.studio.

Why $79 and not $1,000?

Because I'd rather have 500 paying users sharpening the tool than 10 "platinum" ones paying for nothing. The model ships.

Your next trade gets a debate.
Your worst day gets a ceiling.

Get Sentinel — $79 Kit — $149 Desk — $299