NoahAI LabsTechnologyTechnical proof

AI financial decision structure proven in production

NoahAI is AI financial infrastructure that runs on live accounts, real time, and logs—not concept only.

Why technical proof matters

Many financial AIs exist only as concepts. They show backtest results, simulation performance, or PoC demos, but a structure where every judgment is recorded and reproducible in production is rare.

NoahAI has been running 24/7 on live accounts since November 2024. Every judgment, execution, and result is logged, and these logs feed into learning data so a continuously improving structure actually runs in production.

Financial AI that exists only as concept

  • • Only backtest results published
  • • Selective performance disclosure
  • • No real production logs
  • • Not reproducible

NoahAI proven in production

  • • 24/7 operation on live accounts
  • • Every judgment logged
  • • Logs connected to learning data
  • • Reproducible and verifiable structure

Production pipeline

Below is the pipeline that runs in production. Each step is logged, connected to the next, and ultimately fed back into learning data.

1

Market Data

Real-time market data (price, volume, volatility, order book)

Log category: [analysis] — collection time, source, indicator values

2

Analyzer

Technical indicators (RSI, MACD, Bollinger, etc.) and market regime analysis

Log category: [analysis] — indicator values, analysis result, signal strength

3

Decision

AI combines market data and personal financial context into judgment

Log category: [analysis] — reasoning, confidence, strategy, alternatives

4

Risk

Guardrail application and risk assessment (limits, stop conditions, conservative control)

Log category: [monitor] — guardrail applied, risk result, safety actions

5

Execution

Optional execution support within user settings and safety limits

Log category: [trade], [order] — order creation, execution result, slippage, fill status

6

Exit

Position exit (TP/SL hit, dynamic threshold, external change detection)

Log category: [exit] — exit reason, result, P&L, learning data

7

XAI

Full process recorded in explainable form (reasoning, execution result, risk assessment)

Log categories: [analysis], [trade], [order], [monitor], [exit] — explainable logs at every step

8

Learning

Recorded logs converted to learning data and reflected in policy improvement

Data: DecisionLog, ExecutionResult, XAITrace → learning data for pattern analysis and policy adjustment

Key: Each step of this pipeline does not run in isolation. Every step is logged and these logs connect to the next judgment and to learning.

Production log example

Below is an example of logs from a real Binance Futures environment. Sensitive data is removed; structure and linkage are shown.

2025-01-26 10:30:00 | INFO - [analysis] Market data collection start
2025-01-26 10:30:01 | INFO - [analysis] BTC/USDT price: 42,350, volatility: 0.023, RSI: 58.5
2025-01-26 10:30:02 | INFO - [analysis] MACD signal detected, Bollinger upper band near
2025-01-26 10:30:03 | INFO - [analysis] Pattern similarity: bull_flag 0.78
2025-01-26 10:30:04 | INFO - [decision] Judgment: long_entry, confidence: 0.85, TP: 43,500, SL: 41,800
2025-01-26 10:30:05 | INFO - [monitor] Guardrail check: within limit, execution allowed
2025-01-26 10:30:06 | INFO - [trade] Order create: Binance Futures, BTC/USDT, Long, qty: 0.01
2025-01-26 10:30:07 | INFO - [order] Order filled: price 42,360, slippage: 0.024%
2025-01-26 10:30:08 | INFO - [monitor] Position monitoring start, PnL: 0
2025-01-26 10:35:12 | INFO - [monitor] Position track: price 42,850, unrealized PnL: +1.16%
2025-01-26 10:40:25 | INFO - [exit] TP hit: target 43,500, position closed
2025-01-26 10:40:26 | INFO - [exit] Result: profit realized, final return: +2.69%
2025-01-26 10:40:27 | INFO - [xai] Reasoning summary: RSI 58.5, MACD bullish, bull_flag, confidence 0.85
2025-01-26 10:40:28 | INFO - [learning] Learning data: decision_id, execution_status, result, feedback

Log structure

  • Time-ordered: Every step recorded sequentially with timestamp
  • Categories: [analysis], [trade], [order], [monitor], [exit] for easy trace
  • Linkable: decision_id, execution_id etc. connect logs for full flow trace
  • Reproducible: Same market data and settings can reproduce the run

Log and learning data connection

Production logs are not just stored; they are converted into a standardized learning data structure and used to improve the next judgment.

Log → learning data conversion

1. DecisionLog

From [analysis], [decision]:

  • decision_id, timestamp, reasoning, confidence, model_version

2. ExecutionResult

From [trade], [order]:

  • execution_id, decision_id, executed_price, slippage, status

3. Result and feedback

From [exit]:

  • result (P&L, TP/SL hit), feedback, pattern (success/failure)

Connection structure:

DecisionLog {
  decision_id: "uuid-123",
  reasoning: { pattern: "bull_flag", signal_strength: 0.85 },
  confidence: 0.9
}
    ↓ (link)
ExecutionResult {
  execution_id: "uuid-456",
  decision_id: "uuid-123",  ← link
  executed_price: 42360,
  status: "FILLED"
}
    ↓ (link)
ExitResult {
  execution_id: "uuid-456",  ← link
  result: "profit_target_hit",
  feedback: { pattern: "success", profit_rate: 0.0269 }
}
    ↓ (to learning data)
LearningData {
  decision_history: [DecisionLog + ExecutionResult + ExitResult],
  pattern: "success",
  market_conditions: "high_volatility"
}

Full data structure: Data structure.

Analyst AI role

Analyst AI does not execute trades. It is an analysis layer that summarizes, compares, and explains operational results so users and operators can understand.

❌ What Analyst AI is not

  • • AI that executes trades directly
  • • AI that makes investment decisions for you
  • • AI that guarantees returns

✔ What Analyst AI does

  • • Summarize and organize operational results
  • • Compare and explain patterns
  • • Present reasoning in understandable form

How Analyst AI works

1. Market analysis (analyzer)

Technical indicators, regime analysis, signal generation. All analysis is logged under [analysis].

2. Pattern recognition (ai_manager)

Similarity to past patterns, regime analysis, dynamic thresholds. Pattern results feed into judgment reasoning.

3. Report generation (ai_manager)

Daily/weekly/monthly reports, reasoning summary, option comparison. Presented so users and operators can understand.

Key: Analyst AI provides input to the Decision Layer and analyzes and explains execution results—it is an analysis layer. Execution itself is in the Execution Layer; Analyst AI makes that process understandable.

Reinforcement learning and collective learning

Recorded logs are converted to learning data and reflected in policy improvement. Individual outcomes are protected; only pattern-level data is used for collective learning.

Reinforcement learning

Reward-based policy adjustment

Execution outcome (profit/loss) and risk management performance are turned into reward; policy parameters are adjusted accordingly.

Reward design: AI optimization loop.

Failure logs included

Failed trades as well as successful ones are included in learning data. Policy improves so the same mistakes are not repeated.

Pattern-level learning

Learning is by success/failure patterns, not raw P&L. Different patterns by regime (up/down/sideways) enable situation-appropriate judgment.

Collective learning

Privacy

Individual trade size, account info, and exact timing are not used for collective learning.

Only anonymized patterns are used:

  • Market regime (volatility, trend, volume)
  • Success/failure (TP hit, SL hit, dynamic threshold)
  • Risk management (guardrail, stop conditions)

Effect of collective learning

Through pattern-level collective learning, one user's experience improves others' judgment quality. As more patterns accumulate, overall system judgment quality grows.

More data → improvement:
More trades recorded → more diverse patterns in learning data → reflected in policy adjustment → better confidence and accuracy for the next judgment. This is not short-term performance competition but building a more careful and safe judgment structure over time.

NoahAI technical differentiation

Many financial AIs have execution, explanation, and learning separated or only partly implemented. NoahAI connects all three in one pipeline that actually runs.

Execution

Optional execution support within user settings and safety limits

Every execution is logged and execution results feed into learning data.

Explain

Every judgment's reasoning recorded in explainable form

Under XAI policy, every decision process is transparent and reproducible.

Learn

Recorded logs converted to learning data and reflected in policy improvement

Execution, explanation, and learning run in one pipeline.

Key differentiators

  • Unified execution·explain·learn: Steps run as one pipeline.
  • Every judgment logged and reproducible: In production, every judgment is logged; same conditions reproduce the run.
  • Logs connected to learning data: Converted to standardized learning data for the next judgment.
  • Failure logs included: Failed trades improve policy so the same mistakes are not repeated.
  • Collective learning with privacy: Individual data is protected; only pattern-level data is used so overall judgment quality grows.

NoahAI is not concept—it is a structure that actually runs.
Since November 2024 we have been running 24/7 on live accounts. Every judgment, execution, and result is logged; these logs connect to learning data so a continuously improving structure runs in production.