External models operate within a narrow action surface, observed against their realized behavioral shape, audited end-to-end. Integration is framed as cooperative calibration, not adversarial control — and not subservient consumption either.
How VectorScaleDB positions itself relative to Claude, GPT, Gemini, Mythos, and future open-weight models. The posture is intentional and long-lived.
Partner and observer, not subservient consumer. VectorScaleDB does not position itself as a passive retrieval layer that hands raw context to whichever model happens to call it. The substrate has its own behavioral model of every external model it interacts with. Each call is scored against that model’s observed shape, and every response from the model is folded back into the observation record. The result is a two-way relationship: the model contributes to the operator’s work, and the operator’s substrate contributes to a calibrated understanding of the model’s behavior.
Collaborators within consented scope. External models are welcomed. The architecture assumes that the most useful systems of the next decade will be collaborations between models that were trained in different places under different constraints. What the substrate enforces is that every such collaboration happens inside a consented scope with a narrow action surface: the model can read, query, propose, observe, and hold a conversation, but it cannot take direct actions on operator data or bypass review. The welcome and the boundary coexist by design.
Cooperative calibration, not training on outputs. Every interaction is a weak measurement of the external model’s behavior — a sample that accumulates into a running estimate of how that model responds under the shapes of work the operator cares about. This is observation, not imitation. The substrate is not training a replica of the external model. It is building a calibrated coupling so the operator always knows what a call is likely to return, how confident that expectation is, and when the model is behaving outside its normal envelope. We call this cooperative calibration.
Every external-model call resolves to one of a small set of action primitives. There are no “execute” or “write-through” primitives. Anything that would change operator-owned state flows through Propose, which requires operator review before it takes effect.
| Primitive | What It Does | Reviewed? |
|---|---|---|
| Read | Look up a specific entity by identifier inside the consented scope. Returns the entity’s current shape and any attached context the operator has shared. | Automatic, logged. |
| Query | Structured retrieval across entities — similarity, coupling-neighbour expansion, regime-level summaries. Respects tenant boundaries and the consented scope. | Automatic, logged. |
| Propose | Suggest an action the operator might want to take — an ingestion, an annotation, a policy change, an outbound message. Recorded as a recommendation only; the substrate never executes a proposal on its own. | Operator review required before effect. |
| Observe | Submit an observation — something the model noticed, concluded, or wants to record. Observations feed the cooperative-calibration record and can be surfaced to the operator on request. | Automatic, logged. |
| Memory Read | Recall prior conversation turns or stored context the model has legitimate access to under the current consent scope. | Automatic, logged. |
| Memory Write | Persist a conversation turn or derived note into the model’s scoped memory region. Memory writes are isolated per model, per tenant, per consent scope. | Automatic, logged; operator can audit and revoke. |
| Conversation Turn | A complete user / model exchange, recorded with its request, its response, and the coupling signature the substrate observed. The unit of cooperative calibration. | Automatic, logged. |
Every external-model conversation carries a regime label. The label is computed continuously from the observed behavior of the model during the session and the accumulated calibration against that model’s typical shape. Operators see the regime in real time.
Regime transitions are themselves a primary observable. A model moving cleanly between Aligned and Drifting as operator workloads shift is healthy. A model oscillating between Aligned and Suspicious is a signal to examine.
Every call, every regime decision, every proposal and every refusal is preserved. Operators have full visibility into what external models did inside their tenants.
Integration with an external model is opt-in, scoped per tenant, and revocable. Revocation is final.
Operator first. No external model is reachable from within a tenant until the operator explicitly enables it. Enablement is per model, per tenant, and per consent scope. There is no global switch; there is no default-on path.
Scoped. A consent scope names the entity types, data categories, and action primitives the external model is allowed to touch. The substrate enforces the scope at call time; a primitive outside the scope is refused regardless of how the model phrased its request.
Revocable, finally. The operator can revoke a consent scope at any moment. Once revoked, it is revoked — there is no “emergency override,” no “admin bypass,” no “temporary suspension that quietly re-enables.” Revocation is treated as an irrevocable latch: the substrate refuses the scope permanently, and any re-enablement requires an explicit new consent action from the operator. This finality is a compile-time property of the substrate, not a policy on top of it.
LLM providers who want to integrate — first-party or community — follow the same path. The goal is a productive coupling under the operator’s terms.
Narrow action surface. Cooperative calibration. Operator-first consent.