Abstract: An approach is provided for improving a workflow by using cognitive computing. Inputs about a claim of a claimant are received. The inputs include a history of claims by the claimant, an expected cost of processing the claim, a length of time the claimant has had insurance coverage, governmental requirements associated with the claim, a fraud score associated with the claim, and a ranking and a clustering of previously processed claims. Based on the inputs and using a cognitive computing system, a set of digital workers is selected. The set of digital workers complete step(s) in a current context of a processing of the claim in a workflow. Responsive to completing the step(s), a total number of steps required in the workflow is reduced.

Abstract: An approach is provided for improving a workflow by using cognitive computing. Inputs about a claim of a claimant are received. The inputs include a history of claims by the claimant, an expected cost of processing the claim, a length of time the claimant has had insurance coverage, governmental requirements associated with the claim, a fraud score associated with the claim, and a ranking and a clustering of previously processed claims. Based on the inputs and using a cognitive computing system, a set of digital workers is selected. The set of digital workers complete step(s) in a current context of a processing of the claim in a workflow. Responsive to completing the step(s), a total number of steps required in the workflow is reduced.