Framework
Decision Infrastructure Framework
The canonical architecture for systems that transform exploration into qualified execution.
Overview
Most decision systems are built as monoliths — generation and execution live in the same layer, validated by the same logic, governed by the same feedback loops. This works until the cost of a bad decision exceeds the cost of building infrastructure to prevent it.
Decision Infrastructure separates the pipeline into distinct architectural layers, each with its own responsibility, evidence requirements, and failure modes. The framework makes visible the structural arrangement that determines whether intelligence earns trust, resources, and action.
This framework is spatial, not temporal. The layers exist simultaneously and continuously. A decision does not "pass through" the framework once — it lives within it, accumulating evidence, responding to environmental change, and earning or losing trust over time.
Design Principles
These are governing constraints, not guidelines. Every architectural decision in the framework must be traceable to one of these principles.
Separation of Generation and Qualification
The system that generates possibilities must be architecturally separate from the system that evaluates them.
When generation and evaluation share infrastructure, the generator optimizes for passing evaluation rather than producing genuine diversity. Architectural separation prevents this collapse.
Evidence Before Allocation
No resource flows to a decision until evidence justifies the allocation.
Confidence without evidence is opinion. The framework gates every resource transition on accumulated, structured evidence — not conviction, narrative, or recency.
Continuous Qualification
Trust is not a one-time grant. Every qualified decision must continuously re-earn its position through ongoing evidence.
Environmental conditions change. A decision that was optimal yesterday may be harmful today. Qualification must be a living process, not a historical credential.
Failure Isolation
The failure of any individual decision must not compromise the infrastructure that evaluates all decisions.
Individual decisions fail. That is expected. The system fails when a single failure cascades into infrastructure damage — corrupting evaluation criteria, qualification thresholds, or resource allocation logic.
System Map
Five architectural layers, each with distinct responsibilities. Intelligence flows downward through increasingly rigorous gates. Evidence flows upward, informing every layer above.
Layers & Components
Each layer has distinct responsibilities, inputs, outputs, and ownership. No component spans multiple layers.
Generation Layer
Produces candidate decisions with maximum structural diversity. Optimized for exploration, not quality.
Template Engine
Deterministic candidate generation with diversity constraints
AI Generator
LLM-based candidate generation for structural patterns beyond templates
Foundry
Automated research pipeline — mutations, cross-asset transfer, inverse mining
Validation Layer
Tests candidates against historical evidence. Produces structured confidence assessments, not pass/fail verdicts.
Backtest Engine
In-sample and out-of-sample statistical validation
Regime-Aware Scoring
Evaluates performance within specific market conditions
Qualification Layer
Gates resource allocation on accumulated evidence. The critical boundary between exploration and deployment.
Paper Trading Simulation
Forward-testing in live market conditions without capital risk
Qualification Engine
Multi-dimensional qualification assessment
Execution Layer
Manages resource deployment for qualified decisions. Enforces safety invariants.
Live Execution Engine
Translates qualified decisions into market actions
Risk Guard
Circuit breakers and exposure limits
Learning Layer
Transforms outcomes into institutional knowledge. Feeds evidence back to every layer above.
Outcome Attribution
Decomposes results into parameter-level evidence
Intelligence Aggregation
Synthesizes evidence across strategies, regimes, and time
States & Transitions
A decision moves through these states as it accumulates evidence. Each transition is gated — there are no free promotions.
Candidate
Generated but not yet validated. May be structurally invalid.
Entry: Produced by any generation source
Exits: Passes pre-validation → Draft · Fails pre-validation → Rejected
Draft
Structurally valid, awaiting historical validation.
Entry: Passes spec validation and diversity checks
Exits: Passes backtest → Validated · Fails backtest → Failed
Validated
Historical evidence supports the strategy. Ready for forward testing.
Entry: Backtest results meet minimum thresholds
Exits: Approved for paper trading → Active (Paper)
Active (Paper)
Running in live market conditions without capital risk.
Entry: Admitted to portfolio with paper capital allocation
Exits: Qualifies → Qualified · Retires → Retired · Paused → Paused
Qualified
Evidence supports live deployment. Eligible for capital allocation.
Entry: Meets qualification criteria with regime proof
Exits: Promoted → Active (Live) · Disqualified → Paused
Active (Live)
Deployed with real capital. Subject to continuous qualification.
Entry: User promotes with capital allocation
Exits: Killed → Killed · Regime transition → Paused
| From | To | Trigger | Guard |
|---|---|---|---|
| Candidate | Draft | Pre-validation pass | Valid spec structure |
| Draft | Validated | Backtest completion | Composite score ≥ threshold, IS/OOS coherent |
| Validated | Active (Paper) | Portfolio admission | Diversity constraints met, bot capacity available |
| Active (Paper) | Qualified | Qualification engine | Cohort divergence, regime proof, minimum duration |
| Qualified | Active (Live) | User promotion | Exchange connection, capital available, fee status clear |
| Active (Live) | Paused | Regime transition or kill | Toxic transition detected or user request |
Boundary Rules
Boundaries define what crosses between layers and what does not. Every boundary has an explicit failure mode.
Generation → Validation
StrategySpec (canonical format with indicators, risk parameters, exit profile)
Generation confidence, template source, AI model identity
Invalid spec structure → rejected at pre-validation. Duplicate fingerprint → deduped.
Validation → Qualification
Validation results with confidence intervals, regime-conditional scores
Raw backtest trades, intermediate calculations, engine internals
Failed validation → terminal state. No retry without spec modification.
Qualification → Execution
Qualified strategy with evidence trail, regime proof, capital allocation
Qualification scores, internal rankings, paper account details
Disqualification during live → position closed, capital returned. No silent degradation.
Execution → Learning
Closed position outcomes with entry conditions, exit mechanics, regime context
Open position state, unrealized PnL, real-time market data
Missing attribution → exit logged without enrichment. Learning degrades gracefully.
Operational Semantics
How this framework operates in practice — cadence, consumers, and staleness rules.
| Dimension | Value | Rationale |
|---|---|---|
| Generation cadence | On-demand (user) + 3x/day (foundry) | User generation is interactive. Foundry sweeps run autonomously to maintain pipeline diversity. |
| Validation latency | 30-90 seconds per strategy | Backtests run against 90-day rolling windows with IS/OOS split. |
| Qualification assessment | Every 6 hours (batch) | Balances evidence freshness against compute cost. Batch includes qualification, evaluation, and intelligence scoring. |
| Paper tick cadence | 1 minute | Evaluates all paper positions against live market data. Event-driven with polling fallback. |
| Live tick cadence | 1 minute | Matches paper cadence. Exchange orders placed on signal. |
| Learning aggregation | Weekly | Learning summaries aggregate across all outcomes. Feeds back into generation prompts and template parameters. |
| Regime classification | Hourly (snapshot) + weekly (catalog rebuild) | Hourly snapshots capture current conditions. Weekly rebuild derives regime_periods from snapshot history. |
Knowledge Lineage
Introduced In
Operationalized By
Investigated In
Depends On
Influences
Related Research
Methodologies
See this framework implemented in Orqis