Technical Overview

The Tribunal Consensus Engine

The Tribunal is a self-improving orchestration framework for autonomous decision-making through hierarchical multi-agent consensus. It is formally called Ancestral Tribunals — each generation of the tribunal trains on the verified decisions of its predecessors. The weights carry accumulated wisdom. The institution compounds across generations.

read-only inference stream

Sanitized Consensus Trace

Phase 2

t+00s[INGEST]market-state packet sealed; feature names redacted

t+07s[KNIGHT-IMB]independent vote recorded; confidence band attached

t+14s[KNIGHT-MOM]dissent preserved; no cross-agent coordination

t+21s[PROPHET]observer note stored for Phase 3 training corpus; no vote cast

t+28s[KING]quorum check complete; capital gate remains closed

t+35s[SCRIBE]outcome ledger updated; label pending next candle

Why Hierarchy — The Flat System Problem

Most multi-agent systems place agents at the same tier: a main agent, a set of advisors, all voting together. The problem is structural. When every voice occupies the same level, disagreement has no resolution mechanism. Unanimous wrong answers become the output. Bias aggregates instead of canceling.

The Tribunal’s hierarchy exists because each tier solves a problem the tier below it cannot:

Tier	The problem it solves
Three independent knights	A single model has no check on its own bias. Three specialists, zero coordination, produce genuine signal diversity.
Prophet + King	Knights have no capital context. The King synthesizes under risk constraints. The Prophet brings verified macro intelligence the trading tier cannot see.
Succession institution	A single King has no accountability. The institution governs which King holds the throne based on demonstrated performance across all market regimes.

Each layer is a correction of the layer below’s structural blindspot — not a redundancy.

Architecture Philosophy

Three core principles underpin everything:

Multi-Agent Hierarchy — specialized agents with decoupled roles, each tier solving what the tier below cannot
Hardware-Accelerated Inference — optimized for enterprise-grade GPUs, dense models for volume, thinking models for deliberation
Self-Improving Lineage — every verified decision becomes training data for the next generation; the system compounds across cycles

1. The Multi-Agent Hierarchy

Layer 1 — The Knights

Three independent signal specialists. Each is trained on a different corpus — different market data, different signal focus. They receive identical market context and vote without coordinating.

The independence is structural, not prompt-engineered. Three models trained on different data will naturally diverge in their assessments. When all three agree, the signal is strong. When they split, the system expresses genuine uncertainty.

Knight seats are stable identities. The role is permanent; the specific model occupying it earns its position through shadow evaluation. Challengers never hot-swap into production.

Layer 2 — Prophet + King Council

The Prophet is a cross-layer intelligence officer. It computes regime state, portfolio health, and macro context before every session and delivers a structured brief to the King. Its computed output is canonical — the LLM cannot contradict Python-verified numbers. Its advisory interpretation is counsel. Authority over the advisory layer is earned through validated predictions, not assumed.

The King council synthesizes all evidence: the Prophet’s brief, all knight votes with full reasoning chains, portfolio state, and risk parameters. This is deliberation under uncertainty. The King’s maturity is measured not by overall win rate but by sovereign accuracy — its win rate specifically when it overrides knight consensus. A King that never overrides its court is a vote counter. A King with rising sovereign accuracy is developing genuine market intelligence.

The council roster is competitive. Kings earn their seats. Non-performers are demoted. New candidates can be introduced at any time.

Layer 3 — King of Kings (The Succession Institution)

The King of Kings is not a model. It is the trial system — the institution that governs which King holds the throne.

A meta-model selecting the “right King” is another black box adding another failure point. The institution — standardized historical evaluation across all regimes, a competitive succession ladder, Prophet-ledger-based assessment — is more interpretable and more accountable than any model trained to mimic it. The institution is the intelligence.

2. The MoE Parallel

The base model powering the King tier is a Mixture-of-Experts architecture — a large pool of specialist subnetworks with only a small subset active on each forward pass. Every inference call is already a tribunal: the router evaluates all specialists, selects the most relevant voices, silences the rest, synthesizes.

The same model carries a built-in role switch:

Thinking disabled  →  fast, direct output   →  Knight mode
Thinking enabled   →  extended reasoning    →  King mode

The Tribunal does not sit on top of an arbitrary foundation. It layers on top of a model that already runs a tribunal at the weight level.

3. Inference Architecture

The system runs two permanently separated model tracks:

The Trading Track (Knights) — compact dense models, optimized for throughput and pattern recognition. Run locally on workstation hardware. High-volume corpus generation at speed. Fast conditioned reflexes, no deliberation overhead.

The Deliberation Track (Kings) — large thinking-capable models, optimized for depth. Sequential, not parallel. Compute reserved for synthesis: novel combinations under disagreement, capital allocation, vision integration. A trader is never promoted to King because it got fast. The tracks serve different purposes and are built differently from the start.

4. The Self-Improving Lineage

The Cycle

Market data → Knight extraction → Outcome labels (market is the judge)
                    ↓
              Dataset preparation → Fine-tune → Quantized inference model
                    ↓
              Next cycle runs with improved weights → richer signals → better data

Each cycle the model running signal extraction IS the previous cycle’s fine-tuned model. Better model → better signal quality → better training data → better next model. The system does not improve by changing data — it improves by making the same data yield higher-quality signals each time.

The self-improving loop

Every decision feeds the next generation. The corpus is immortal — each cycle a better model judges the same history.

The Canon

The Canon is what survives after every model generation is retired.

When an architecture is replaced entirely — all adapters discarded, all weights gone — the Canon survives. Verified strategic patterns, confirmed regime behaviors, principles tested by Python across years of market history: none of this is lost. The next generation inherits institutional memory even if it inherits no weights.

Canon grows only when Python agrees. The Prophet proposes a pattern. Python verifies it — statistical threshold, multi-regime confirmation. Only then does it enter Canon as Law. A system that writes its own Canon without verification worships its own conclusions. The chain is closed by design:

Prophet observes → Scribe normalizes → Python verifies → Canon records

Adapter Succession

At the weight level, the same “earn your seat” principle governs adapter replacement. A new candidate adapter trains alongside a replay buffer — a stratified record of every regime the system has faced. The candidate must prove it improved on the current adapter without abandoning what the incumbent had mastered. A candidate that learns the new at the cost of behavioral regression fails the identity gate. No regressions are promoted to production.

5. Natural Selection

The system is designed to evolve — not to a predetermined end state, but shaped by evidence.

Every component carries a fitness score derived from market outcomes. When fitness falls below threshold across consecutive cycles, a challenger trains automatically. Both run. The market decides the outcome. The founder designs the selection pressure; evidence shapes the result.

This applies at every layer:

Knight seats — challengers audition in shadow, earn comparison data
King seats — formal succession trials across full regime history
Adapters — tested against replay buffers and behavioral consistency gates
The Canon itself — patterns that stop holding are reclassified, not preserved out of inertia

The initial system is dictated by the founder. The final system is forever evolving, shaped by evidence alone.

6. Infrastructure

Watchdog systems — automated monitors detect stalls and trigger recovery; pods self-terminate on completion
No lookahead — backtesting uses only data that existed at decision time; the integrity of labeled data depends on this completely
Consensus-driven execution — actions only execute when the deliberation chain completes
Hardware-aware inference — dense models for volume extraction (local GPU), thinking models for deliberation (cloud accelerator when needed)
The weights are the IP — the architecture is learnable, the prompts are guessable, but the weights shaped by years of labeled market history cannot be easily replicated