Constitutional substrate
The constitutional substrate is the lowest layer of AIEP. It defines what a valid instruction is, how alternatives are generated, how they are selected, and how every decision in the system is made tamper-evidently traceable. Every higher layer in the AIEP stack depends on the constitutional substrate being present and intact.
The core patent is GB2519711.2, filed 20 November 2025.
The instruction object
An AIEP instruction is not a natural language string. It is a structured machine-readable object with the following required fields:
| Field | Purpose |
|---|---|
intention | The canonical statement of what the instruction is trying to achieve |
parameters | Scoped, typed parameters that bind the instruction to its context |
context | The evidence context in which the instruction is valid |
safetyEnvelope | An identifier referencing the safety constraints that bound execution |
protocolVersion | A reference to the public protocol registry version in force at time of publication |
divergenceGraph | The embedded graph of alternative canonical interpretations |
The object is hash-bound at publication. Any alteration to any field produces a different hash — making tampering detectable by any retrieval agent.
The DivergenceGraph
The DivergenceGraph is the constitutional substrate’s core innovation. It embeds alternative interpretations of an instruction directly within the instruction object — not as ambiguity, but as structured, auditable alternatives.
Structure:
| Element | Description |
|---|---|
| Primary canonical instruction | The current empirical consensus interpretation |
| Alternative instructions (2–8) | Generated exclusively using the defined divergence operators |
| Parent-hash chain | Each alternative is cryptographically chained to its parent |
| Weighted scoring | Registry-retrieved coefficients determine which alternative is selected under any given context |
The DivergenceGraph does not allow arbitrary alternatives. Alternatives may only be generated using the defined operator set — this is what makes the graph bounded and reproducible.
Divergence operators
Nine operators are defined. Each transforms the primary instruction in a specific, bounded way:
| Operator | Transformation |
|---|---|
| D1 | Synonym substitution — replace a term with a semantically equivalent term |
| D2 | Parameter relaxation — widen a constraint |
| D3 | Parameter tightening — narrow a constraint |
| D4 | Context promotion — elevate a contextual condition to a primary condition |
| D5 | Context demotion — reduce a primary condition to contextual |
| D6 | Evidence substitution — replace the supporting evidence reference |
| D7 | Scope expansion — extend the domain of applicability |
| D8 | Scope contraction — restrict the domain of applicability |
| D9 | Temporal shift — shift the validity window of the instruction |
These nine operators, applied to any valid instruction, produce the complete bounded space of alternative interpretations. No alternative outside this space is valid under the constitutional substrate.
Deterministic selection
When an AI agent retrieves an instruction, it must select from among the primary and alternative interpretations. This selection is deterministic — given the same context, schema version, and registry coefficients, every agent produces the same selection.
The selection algorithm:
- Retrieve the instruction object from the Mirror endpoint
- Retrieve weighted scoring coefficients from the protocol registry for the current
protocolVersion - Evaluate each alternative against the agent’s context parameters
- Compute a deterministic score for each alternative under the retrieved coefficients
- Select the highest-scoring alternative — or the primary if no alternative exceeds it
- Record the selection as a signed artefact in the evidence ledger
This is not ranking by probability. It is selection by deterministic evaluation against a declared, retrievable scoring function.
Canonical primitives R1–R8
The GENOME kernel defines eight canonical primitives that form the frozen core of the constitutional substrate. Every component at every layer of AIEP is built from these primitives:
| Primitive | Function |
|---|---|
| R1 | Canonical serialisation — deterministic encoding of any artefact to a stable byte representation |
| R2 | Hash binding — SHA-256 of the canonical form, producing the artefact’s unique identifier |
| R3 | Provenance declaration — issuer identity, timestamp, and schema version bound to every artefact |
| R4 | Schema pinning — artefacts reference the exact schema version they were validated against |
| R5 | Divergence operator application — bounded transformation of instructions using D1–D9 |
| R6 | Registry retrieval — deterministic fetch of scoring coefficients and schema definitions |
| R7 | Ledger append — tamper-evident appending of artefacts to the evidence ledger |
| R8 | Fail-closed gating — suppression of execution when any invariant is not satisfied |
These primitives are frozen. A new version of the GENOME kernel does not alter R1–R8 — it only adds above them. This is what makes artefacts produced under different kernel versions interoperable.
GENOME_LOCKFILE.json
Every GENOME-compliant deployment commits to the kernel version at build time via GENOME_LOCKFILE.json. This file declares:
- The kernel version in force (
kernelVersion) - The canonical primitive set bound to that version (
primitiveSet) - The schema versions the deployment accepts (
schemaVersions) - A hash of the lockfile itself, signed by the deployer
A deployment that alters its lockfile after build produces a different hash — and any artefact it subsequently produces is traceable to the post-alteration state. This makes configuration drift detectable.
Why this matters
Most AI systems have no substrate. Instructions are text. Alternatives are probabilistic. Selection is opaque. The constitutional substrate replaces this with:
- Instructions that are structured objects, not strings
- Alternatives that are bounded and auditable, not sampled
- Selection that is deterministic and retrievable, not probabilistic
- Every decision traceable to the kernel version and registry state in force at the time
An AI system reasoning against the constitutional substrate is not a better language model. It is a different kind of system — one whose decisions can be investigated after the fact.
Architecture · GENOME SDK · Protocol · Patents — GB2519711.2