A governed knowledge platform that keeps your sovereign substrate private by design — and proves a 4 KB structured capsule gives an agent the same task performance as 154 KB of raw context.
What it is
Most knowledge tools publish everything you give them. CK Knowledge classifies every document deny-by-default: product and narrative content is searchable; your governing substrate — the rules, decisions, and mechanisms that are your competitive moat — is demand-paged to trusted agents and never published.
A deny-by-default classifier + an adversarial review pass keep mechanism out of the public surface. The boundary is enforced in code, re-proven every cycle.
A ~4 KB interpretive capsule matches full-context performance at ~1/25th the tokens — measured across 8 models, not asserted.
Vector search over your product corpus plus the captured development story — the arc, decisions, and lessons, queryable.
The proof
In a pre-registered evaluation (367 cells, 8 models, $7.66), a small structured capsule out-performed every larger-context regime — and collapsed the gap between model tiers (a small model + the capsule matched a frontier model).
Mean task score (1–5). Independent evaluation; the methodology is portable to any long-running project facing context-rot. Tier-collapse measured: Haiku ≈ Opus once the capsule is present.
Sovereignty
The principle: demand-page the moat, don't publish it. Your governing rules are the reason customers choose you — so they belong in a contract zone, never on a public surface.