The Otarix Pipeline

Full-market analysis every minute. 16 steps. 13 agents.

How It Works

Every run travels through the complete decision lifecycle — from raw data to executed trade to post-trade learning.

Data 8 feeds, 42 symbols
Integration Normalize & dedupe
Analysis 3 agents in parallel
Research Dual thesis
Validation Fact-check + evidence
Trade Plan Entry/SL/TP/Leverage
Risk 7 gates + sizing
Deep Think Opus — adversarial
Approve Opus — signed
Execute Deterministic
Monitor PnL + learning

Cost by Run Type

Most runs exit early. The system is designed to be cheap to scan and expensive to decide.

Run Type Stops At Steps Tokens/Run Cost/Run % of Runs
NO SIGNAL Researcher Team 6 / 16 5,180,000 $18.90 93%
REJECTED Fact-check 7 / 16 5,465,000 $20.17 3.5%
NO TRADE Trader Agent 9 / 16 5,815,000 $21.82 2.7%
FULL RUN Monitoring 16 / 16 6,942,000 $28.48 0.6%

Annual Budget

The compute cost of a 24/7 AI trading desk.

$10M
Per Year
$27,500
Per Day
2.74T
Tokens / Year
1,440
Runs / Day
12
Executed Trades / Day
$19.10
Avg Cost / Run

Key Design Rules

Adversarial by Design

The Researcher must write both PUMP and DUMP theses. Deep Thinking actively argues against the trade. No one-sided decisions are possible.

Deterministic Execution

The execution layer is pure code — idempotent, retried, logged. The LLM's role ends at approval. AI thinks, code executes.

Two-Tier Compute

Sonnet (12 agents) carries 91% of tokens. Opus (2 agents) handles only adversarial review and final approval — reasoning complexity determines the model.

Early Exit Architecture

93% of runs stop at the Researcher (NO SIGNAL) — $18.90 instead of $28.48. The system saves budget by deciding not to trade as cheaply as possible.

Math Outside the LLM

Backtest statistics, position sizing calculations, and execution run on numerical engines. The LLM reads summaries — never computes.

Signed & Auditable

Every decision is digitally signed with a unique decision_id. Full token transparency: per agent, per run, per dollar.

See the pipeline in action.

Request a live console walkthrough and see every agent, every token, every decision in real time.

Request a Demo