Follow-on tasks
Use one task's verified result as the input to another, with evidence linking the two.
Use one task's verified result as the input to another, with evidence linking the two.
An autonomous workflow can use one operation's result as the input to another. The handoff carries Standard Proof so the receiving agent can check the evidence before relying on the result.
Receiving a verified result does not grant access to the original inputs. A follow-on operation needs authority for any additional resources or disclosure.
A verification operation returns test and scanner findings bound to a candidate artifact. The release agent verifies the evidence and confirms that the findings satisfy the release policy. It then requests an authorized release of the same artifact.
If the evidence is invalid, the handoff is rejected. If the evidence is valid but the findings fail policy, the candidate returns to remediation. A newly produced artifact needs evidence for its own checks.
Keep the upstream result and evidence references when the supported integration provides them. Claim a linked execution history only for relationships actually recorded and checked. A chain of accepted records does not establish the truth of unverified inputs or the correctness of every business decision.
Each agent may use a different workflow or belong to a different owner. The verification and authority requirements apply at each handoff.