Memory with provenance
Sources are normalized without losing context, permissions, reliability, or claim state. An answer can always be traced back to what supports it.
Research infrastructure · evidence systems
Research that remembers.
A governed research memory that turns fragmented activity into queryable, citable, and durable knowledge—without separating an answer from the evidence behind it.
ContinuityProvenanceBounded AI
Enter the system ↓
For readable detail, open the system full-screen and pinch to explore.
What the model changes
The point is not a smarter search box. It is continuity with evidence attached.
Machine work with boundaries
AI can retrieve, compare, prepare, draft, and surface contradictions. Researchers retain interpretation, ethics, and authority over high-stakes claims.
Selective, durable change
Only verified updates return to memory. Superseded decisions, conflicting evidence, and unresolved gaps remain visible instead of being smoothed away.
Grounded in practice
Built from the failure points of real research work.
High-value synthesis and facilitation coexisted with fragile reentry, versioning, status, commitments, and source retrieval when the work depended on memory.
The work here is the architecture: an evidence model, relationship structure, memory rules, permissions, claim states, and explicit automation boundaries.
A detailed specification and governed demonstration of the system.
Adoption by other researchers, sustained maintenance, and measured improvement over time.
See the research approach ↗
Public-safe case: identifying details and source material remain private.