FOR AGENTIC AI

The white box behind the black box.

LLM wrappers, deep RL agents, autonomous research crawlers, and execution bots all share the same upstream dependency: statistically validated signal parameters. None of them solve discovery. We do. Enumerated. Deterministic. Explainable. The statistical infrastructure your agents can rely on.

Forex·Equities·Crypto·Commodities
01LLM AND LLM WRAPPERS

Your models are brilliant at forming strategy. Let us be the calculator.

Large language models excel at helping users articulate research questions, reason about asset behavior, and assemble strategy logic. What they cannot do is run walk-forward survival tests, permutation null distributions with FDR correction, SPA bootstrap, or probability of backtest overfitting checks at scale. Not for a single permutation. Certainly not for millions in under a minute.

Allow S1 to become the white-label compute layer behind your conversational interface. Your model handles the reasoning. Our API handles the enumeration. The user receives statistically validated outputs that your platform can explain, cite, and audit. Beyond the signal itself, you can prove data destruction to both users and their regulators: ephemeral compute, ingress and egress certificates, cryptographic verification that raw data was purged after delivery.

Your LLM Wrapper
Crude Oil × ETH patterns
BTC momentum analysis
Portfolio risk assessment
U

Hey, can you show me some interesting statistical patterns between crude oil and Ethereum over the last 120 days that I could build a strategy on?

AI

Certainly. I can pull up mean-reversion and convergence/divergence statistics between CL (WTI Crude) and ETH/USDT. Let me run an exhaustive cross-asset enumeration through Student One's Gemina engine.

Sending request to /gemina — CL × ETH/USDT, 90-day window, 1-min resolution, full indicator lattice...

AI

Gemina found a persistent divergence pattern. At minutes 192 to 206 of the session, when CL gains +0.2% while ETH loses −0.2% in the same minute, the spread between them closes within 3 hours on 76%, 82%, 71%, and 88% of the past 30, 60, 90, and 120 days respectively. For full context, click to view the complete minute-wise heatmap across all session windows.

● S1 Gemina API · 1.2s● 1,000,000+ configs tested
Ask about any asset pair...
02DEEP REINFORCEMENT LEARNING

Your PPO agent overfits because the feature space is wrong.

Standard deep RL pipelines feed raw calculated indicators into the observation space: RSI(14), MACD(12,26,9), Bollinger(20,2). These are arbitrary defaults. The agent learns to exploit statistical artifacts of those specific parameter choices rather than structural properties of the underlying price process.

S1 outputs are the result of exhaustive statistical tests performed on indicators, not the indicator values themselves. Each event row in the output is a fully labelled feature vector in Croissant ML format:

regime_labelHMM or PELT-detected market regime: low_vol, high_vol, trend, mean_reverting
directionLong or short, determined by indicator crossover direction
day_of_weekISO day (Mon-Sun) derived from entry bar timestamp, used as a statistical gate
time_of_day30-minute UTC bucket (48 bins) at entry, used as a statistical gate
third_indicatorConditional filter: a second indicator value at entry must satisfy a threshold predicate
mfe / maeMaximum favorable and adverse excursion per event, stored as returns
conformal_intervalSplit-conformal prediction bounds with target coverage
breakeven_frictionPer-event breakeven cost in basis points

These are fully labelled, structured datasets. Every event carries its regime context, temporal metadata, and statistical measurements. Feed them directly into any architecture.

TransformersLSTMCNNRNNGANPPO / A3CHuman analyst

Any system that consumes tabular feature vectors can ingest S1 outputs without transformation. The statistical substrate is architecture-agnostic.

Typical deep RL observation space

RSI(14), MACD(12,26,9), BB(20,2)
Arbitrary defaults from textbooks
Agent learns parameter artifacts

With S1 enumeration outputs

Statistically validated configurations
Exhaustive sweep, not sampled
Agent learns structural behavior
03AUTONOMOUS RESEARCH AGENTS

Clawbots, copilots, swarm agents, and research orchestrators.

Autonomous research agents operate on your own infrastructure. They ingest data, form hypotheses, test conditions, and compile reports without manual intervention. The constraint is that quantitative math at enumeration scale requires purpose-built compute. These agents can call the Dojo API for on-demand enumeration without provisioning their own statistical engine.

The interaction pattern is API-to-API. The research agent decides which assets, families, and period bands to enumerate. S1 returns the complete solution set. The agent interprets, filters, or feeds results downstream. No human in the loop at the computation layer.

Clawbots

Autonomous scraping and research agents that continuously scan asset universes. Submit enumeration jobs per asset on a schedule. Flag regime changes when previously stable configurations break. Transact with metered compute plans so your bots pay per call without manual intervention.

Research Copilots

Assist human analysts by pre-computing enumeration across watchlists. Surface configurations that warrant further investigation.

Swarm Agents and Multi-Agent Systems

Coordinated agent fleets where each node handles a different asset class or research family. Distribute enumeration jobs across the swarm. Aggregate results centrally.

Strategy Orchestrators

Multi-step agentic workflows that discover signals, validate them, assemble candidate strategies, and pass them to separate backtesting or execution layers.

AutoGPT / BabyAGI / Task-Driven Agents

Self-directed planning agents that decompose research goals into subtasks. Call S1 as a tool within their action space for quantitative validation at each step.

Data Pipeline Agents

Airflow DAGs, cron-triggered notebooks, and scheduled compute jobs that integrate enumeration into existing quantitative infrastructure.

04EXECUTION BOTS AND TRADING SYSTEMS

MT4, MT5, and autonomous execution systems.

Automated trading systems on MetaTrader 4, MetaTrader 5, and proprietary execution frameworks handle order routing, position management, and risk controls. They are built to execute. They are not built to discover which signal parameters are statistically valid across time.

These systems typically operate with hard-coded indicator settings chosen during initial development or manual optimization. When market regimes shift, the parameters may no longer reflect the statistical properties of the current price process. Periodic re-enumeration provides an updated parameter landscape that execution systems can reference.

S1 does not execute trades, manage positions, or provide timing signals. We provide the statistical substrate: which configurations satisfy specified constraints on a given asset at a given point in time. What the execution system does with that information is outside our scope. All services are non-discretionary.

MetaTrader 4 / MQL4REST API integration via DLL or web request
MetaTrader 5 / MQL5Native HTTP support, JSON parsing
Custom execution enginesREST or Arrow IPC for direct binary ingestion
Cloud-hosted botsWebhook callbacks, scheduled polling

THE STRUCTURAL GAP

None of these systems solve statistical discovery.

LLM wrappers retrieve information. Deep RL agents optimize policies. Research crawlers automate workflows. Execution bots route orders. Each operates within its own domain. None of them enumerate the full parameter space of technical indicators against empirical price data to determine which configurations exhibit statistically stable behavior.

This is the layer we occupy. Downstream of raw OHLCV data, upstream of any strategy, model, or trading decision. We compute across periods 1 to 14,000 on a one-minute canonical axis. Users select their own period bands, allowing weekly and fortnightly anomalies that influence intraday behavior to surface within a single enumeration run. The output is deterministic, explainable, and reproducible.

Enumeration Spec

Period range1 to 14,000 (configurable bands)
Canonical axis1-minute OHLCV
ProtocolMCP, REST, OpenAPI 3.1
Output formatJSON or Arrow IPC
BillingPer-call metered
AuthAPI key + HMAC signing

Integrate enumeration into your agent stack.

Request API credentials. Inspect the engine in Dojo before committing.