Trust is not a promise. It is a record.
Every tool call, argument, result, revision and retry stays on the record — traceable, replayable, and owned by you.
Illustrative excerpt. Fictional calls, with identifiers and decoded arguments shortened for display. Each call has its own durable identity and receipt reference. receipted means the result was recorded; a receipt can contain a tool error, and a retry is a separate call. Full results live in the referenced receipt objects. All ledger data is encrypted at rest and in transit.
Traceable.
“Why did the agent do that at 10:02 on March 14?” is one lookup — the tool call, its arguments and what came back. An answer, not an investigation.
Replayable.
Saved inputs, tool arguments, receipts and checkpoints preserve the evidence needed to inspect a run and evaluate changes against recorded work.
Versioned.
What was approved, what changed afterward, who changed it — every artifact answers all three.
Operator owned.
The ledger lives in your database — your schema, your keys, your region. Retention, redaction and hard-delete are your controls, not vendor tickets.
Exportable.
Plain SQL rows and artifacts you can query, dump and take with you. Compliance evidence is a query you run, not an export you request.
One context.
Every possibility.
Your team and AI, creating together — from first idea to finished work.