Methodology
WhaleClaw’s methodology is built on one core principle: AI reads the messages, math produces the signal. This separation is what makes the system reliable.
The two-layer architecture
Section titled “The two-layer architecture”Layer 1: AI Extraction (reads language)
Section titled “Layer 1: AI Extraction (reads language)”Each of the 128+ KOL agents is a dedicated state machine powered by GPT-4o-mini. When a KOL posts a message, the agent:
- Parses the natural language — slang, abbreviations, emojis, context from prior messages
- Extracts three fields: directional bias, conviction strength, stance timestamp
- Maintains state — if a KOL said “long BTC” yesterday and hasn’t changed their view, the agent keeps them as “bullish” until they explicitly shift
This layer needs AI because human traders don’t write in structured data. They write “heavy long here, LFG” or “I’m out, this looks toppy.” The AI understands what they mean.
Layer 2: Deterministic Aggregation (produces the number)
Section titled “Layer 2: Deterministic Aggregation (produces the number)”Once every KOL’s stance is extracted, the aggregation is pure math:
Composite Score = Σ (bias × conviction × tier_weight × time_decay)No LLM touches this step. The weighted votes, time decay curves, and conviction multipliers are deterministic calculations. This means:
- The final consensus number cannot hallucinate. It is exactly what the weighted data says.
- The calculation is reproducible. Same inputs always produce the same output.
- Errors are traceable. If the signal seems wrong, you can trace it back to which KOLs drove the score.
State machine design
Section titled “State machine design”Each KOL agent operates as a finite state machine with three states:
| State | Description | Transitions |
|---|---|---|
| Bullish | KOL is directionally long | Explicit bearish/neutral statement |
| Bearish | KOL is directionally short | Explicit bullish/neutral statement |
| Neutral | KOL is flat or undecided | Explicit directional statement |
Key design decisions:
State persists until explicitly changed. Silence doesn’t mean neutral. If a trader said “long BTC” and then went quiet for 12 hours, they’re still long. Only an explicit reversal changes their state.
Time decay handles staleness. A 12-hour-old call still counts, but less than a 2-hour-old call. This is handled by the weighting math, not by changing the state.
Conviction is extracted, not inferred. “I’m all in” maps to strong conviction. “Maybe long here” maps to weak. The AI makes this classification; the math applies the multiplier.
Multi-source synthesis
Section titled “Multi-source synthesis”The Composite Read doesn’t rely on KOL consensus alone. It combines four independent data streams:
| Source | What it captures | Weight in composite |
|---|---|---|
| KOL Consensus | What 128+ traders think | Primary directional signal |
| Orderflow | What the tape shows | Confirmation / divergence |
| Market Structure | What the chart says | Level-based context |
| Macro Context | What’s happening in the world | Risk/catalyst overlay |
When all four agree, confidence is high. When they diverge, the system either reduces confidence or flags specific conflicts.
Why deterministic matters
Section titled “Why deterministic matters”In trading, false precision kills. If your signal source can produce different outputs from the same inputs (as any LLM can), you can’t trust it consistently.
WhaleClaw’s architecture guarantees:
- Consistency — The same market state produces the same signal
- Transparency — Every output can be decomposed into its inputs
- No hallucination — The aggregation layer is pure math
- Traceable errors — When the signal is wrong, you can identify why
The AI layer does what AI is good at (understanding messy human language). The math layer does what math is good at (producing reliable, reproducible numbers).