Enterprise AI Architecture

Enforcing Contextual Admissibility

How Exogram synchronizes state tombstones with ledger events to prevent agents from executing against deprecated facts.

01. The Architectural Threat

  • In standard AI systems, when an operational fact is updated (e.g., "User is activated" to "User is banned"), the old state often remains in the unstructured context store.
  • These lingering, obsolete connections are called "Phantom State".
  • During retrieval, the agent fetches both the new state and the Phantom State, leading to execution failures and contradictory decisions.
  • Standard context layers have no native relationship to relational source-of-truth tables.

02. The Exogram Resolution

  • Exogram implements synchronized, instantaneous metadata archival across the execution state layer.
  • When a fact is updated in the primary Supabase ledger, the old ledger entry is marked `is_active=false`.
  • Simultaneously, Exogram reaches into the contextual structure and severs the bounding edges by injecting an `{"archived": true}` tombstone onto the obsolete node.
  • The policy engine actively tracks strict traversal constraints, meaning Phantom State vanishes from the execution view immediately.

Technical Implementation Blueprint

// Exogram Synchronized State Tombstoning:

def update_fact(self, fact_id: str, new_content: str):
    # 1. Write new fact to Supabase
    new_id = self.supabase.insert(new_content)
    
    # 2. Archive old fact in Supabase
    self.supabase.update(fact_id, {"is_active": False})
    
    # 3. Tombstone the Node in the execution context
    state_engine.update_node(
        node_id=fact_id, 
        set_metadata={"archived": True}
    )
    
    # The phantom node is instantly eliminated from traversal bounds.

Frequently Asked Questions

Why not just delete the node entirely?

Because Exogram is an immutable auditing system. We never delete data. We tombstone it. This preserves the historical audit trail while preventing it from polluting active agent context.

Can an agent retrieve archived facts if it needs to?

Yes, but only via explicit historical query endpoints. Standard operational traversal filters them out automatically.

Explore Other Blueprints