Saentinel

Saentinel Trader · Active paper evaluation

Deterministic trading.
Measured intelligence.

A focused intraday trading research system for US stocks and ETFs. Market data ranks the candidates. Transparent deterministic rules select entries. Risk and execution remain deterministic. An optional shadow AI observes the same evidence only for comparison and research.

Explore the system See current research
  • Paper first
  • Long only
  • Flat by close
09:40 ET DECISION CYCLE PAPER
01RankDeterministic
02SelectDeterministic
03ControlRules decide
OUTCOMETrading decisions are deterministic. Shadow AI can compare—but never control.

A clean restart

Built to trade less—and know more.

Saentinel Trader replaces an overbuilt investment-research platform with a deliberately small operating loop. It scans liquid US equities, records the evidence behind every cycle, selects entries with transparent deterministic rules, and keeps position sizing, risk, execution, monitoring and exits deterministic. An optional shadow model evaluates the same evidence independently so its recommendations can be measured without influencing orders.

The operating model

Intelligence where judgment helps.
Code where rules must hold.

MARKET DATA

Observe broadly

Alpaca assets, snapshots, daily history and completed intraday bars create a time-bounded view of tradable US stocks and ETFs.

DETERMINISTIC SCANNER

Reduce the universe

Liquidity, momentum, spread, history and intraday context rank candidates before selection. Missing or invalid inputs are excluded, never invented.

DETERMINISTIC SELECTOR

Select—or abstain

Transparent gates reject entries that are below VWAP, too extended versus VWAP or ATR, too correlated, already occupied, or beyond the cycle cap. The same inputs produce the same decision.

RISK, EXECUTION & SHADOW RESEARCH

Control—and measure

Fresh quotes, market regime, position capacity, allocation ceilings, risk budgets, daily-loss state and ownership checks constrain every paper order. Optional shadow AI runs separately and cannot place, size, block or exit trades.

One bounded cycle

From market scan to a recorded outcome.

Each cycle is claimed once and persisted. Selection is deterministic, stale results cannot enter, and execution rechecks the world before acting. Optional shadow-AI work is recorded independently and never delays entries.

  1. 01

    Scan

    Filter and rank eligible US stocks and ETFs from current market observations.

  2. 02

    Enrich

    Add completed daily and intraday context, with explicit rejection of stale or incomplete evidence.

  3. 03

    Select

    Apply deterministic VWAP, ATR-extension, correlation, occupancy and cycle-cap rules to the ranked shortlist.

  4. 04

    Constrain

    Apply deterministic market-regime, capacity, capital, risk, spread, timing and asset-eligibility rules, then revalidate against fresh quotes before submission.

  5. 05

    Monitor and exit

    Manage owned positions through stop, take-profit, thesis, stagnation, winner-to-loser profit protection, daily-risk and end-of-day rules.

  6. 06

    Journal and compare

    Persist scans, selections, orders, fills, ownership and research outcomes in SQLite. When enabled, shadow-AI recommendations are stored separately for head-to-head evaluation.

Risk before activity

The evidence informs.
The rules decide.

The trading path is explicit, testable and restart-safe. Optional AI is observational: it can be compared with the deterministic selector, but it has no authority over capital, orders, risk or exits.

01

Allocation is a ceiling

The selector assigns a bounded allocation ceiling. Position, capital, risk-mode, buying-power and market-regime controls may reduce it further; none can silently enlarge exposure.

02

Risk reacts without chasing

Recovery mode reduces size, deterministic SPY regime policy can restrict or block new entries, and a hard daily-loss stop blocks new entries and flattens owned exposure.

03

Ownership stays exact

Saentinel monitors and exits only quantities it can prove it owns. Manual positions remain outside its authority.

04

No overnight positions

New entries stop before the close. Entry orders are canceled and owned positions are flattened within a bounded liquidation window.

Current paper research

The system works.
The strategy must still earn trust.

Forward paper runs exposed an important reality: safe software is not the same thing as a successful strategy. Saentinel is now using its own evidence to study where losses occur and improve only through explicit, deterministic changes.

DEPLOYED

Deterministic entry selection

Actual entries now come from a transparent selector over the ranked shortlist. VWAP, ATR extension, correlation, occupancy and cycle caps are explicit and replayable.

DEPLOYED

SPY market-regime control

Deterministic BULLISH, NEUTRAL, BEARISH and STRESSED states now influence new-entry eligibility and risk without changing existing-position exits.

DEPLOYED

Winner-to-loser protection

A restart-safe profit-protection rule can preserve a meaningful intraday winner from reverting into a full loss while leaving higher-priority exits intact.

DEPLOYED

Execution and reconciliation safety

Known Alpaca fill/position propagation races are bounded and audited so temporary broker lag does not contaminate unrelated symbols or ownership decisions.

MEASURING

Shadow AI vs deterministic selection

The optional model now recommends in shadow only. Its picks, confidence and allocation are persisted for independent comparison against deterministic selections and outcomes.

RESEARCH

IEX vs SIP decision replay

Read-only historical replay compares how feed choice could have changed saved scanner and shadow decisions while respecting point-in-time data boundaries.

MEASURING

Does the strategy have an edge?

Ranking power, selection value, trade economics, drawdown and forward paper performance are now measured explicitly. The answer is not assumed—and profitability remains unproven.

What failure changed

No victory lap.
No hidden rewrite.

“A system can execute correctly and still fail its investment objective.”

That is now part of Saentinel’s design discipline.

The original Saentinel became too complex to prove useful. The replacement deliberately narrows the problem, preserves real paper evidence, and treats disappointing outcomes as inputs—not as results to explain away. When forward evidence showed that LLM picks underperformed the candidates they rejected, the model was removed from the trading decision path instead of being defended. Profitability remains unproven.

The honest boundary

A research system.
Not a promise.

Follow the experiment

Built in the open spirit of evidence.

Saentinel Trader is private software under active paper evaluation. Questions about the project are welcome.

contact@saentinel.com