Agent responsibility
Check supporting evidence
Identify missing evidence and prepare a complete packet for the returns team.
Return evidence pack
Retail & commerce / Customer service / Solution blueprint
Returns evidence collection
Prepare a return review with the supporting records attached.
Business problem & expected outcomes
The challenge behind
returns evidence collection.
Return requests arrive without the order references or evidence needed for review.
What this workflow is designed to deliver
Return evidence pack
Identify missing evidence and prepare a complete packet for the returns team.
How to measure the improvementEvidence completeness; repeated evidence requests.
Start with the right information.
Order references, return policy, submitted evidence, and item details.
Interactive workflow diagram
From return request
to a clear next step.
Identify missing evidence and prepare a complete packet for the returns team.
Retail & commerceSelect a stage to explore
Context
Return request
Order references, return policy, submitted evidence, and item details.
Prepared outputReturn evidence pack
Designed around the work
A focused agent. The right capabilities.
Give the agent the context and tools this process needs, with an explicit output and an accountable owner.
Connected tools & context
Bind only the operations this workflow needs. Keep credentials in ART and choose the permitted tools explicitly.
File storage
Project & environment scopeRetain source references and review state only where this implementation requires persistence.
Dynamic tables
Project & environment scopeRetain source references and review state only where this implementation requires persistence.
Agent Skills
Project & environment scopePackage the checklist, instructions, and expected output as a reusable skill.
The decision boundary
Authorized staff approve refunds or replacements; evidence collection does not authorize them.
ART product mapping
Components used.
Chosen for this case.
Agent Lab prepares the work described below. These are the capabilities that support this workflow.
Datalake
File storage
Keep the supporting files accessible within the review’s project and environment.
Datalake
Dynamic tables
Track the case, owner, source references, and review state as structured records.
Agent Lab
Agent Skills
Package the checklist, instructions, and expected output as a reusable skill.
The implementation, step by step
From source context
to a reviewed result.
- 01
Return request
Order references, return policy, submitted evidence, and item details.
Agree the trigger or manual request, record identifiers, and the process owner. - 02
Check supporting evidence
Identify missing evidence and prepare a complete packet for the returns team.
Define instructions, permitted tools, and the expected output. Keep missing information explicit. - 03
Returns-team handoff
Authorized staff approve refunds or replacements; evidence collection does not authorize them.
Keep the pilot in preparation mode and use the team’s existing review process. - 04
Return evidence pack
Evidence completeness; repeated evidence requests.
Compare outputs with reviewed examples and test incomplete, conflicting, and unauthorized inputs.
Before you build
What this implementation needs.
File storage
A document inventory, resource access scopes, and a file-retention policy.
Dynamic tables
Typed fields, record identifiers, relationships, and a table-retention policy.
Agent Skills
A process checklist, example inputs, and a reviewer-approved output format.
Also prepare an ART project and environment, the model configuration appropriate to your agent, an accountable process owner, and approved sample data.
Authority stays with your team
Define the boundary
before enabling the action.
Authorized staff approve refunds or replacements; evidence collection does not authorize them.
Explore execution governanceConnect deliberately.
Map the source material and responsible owners first. Where the selected components require system access, configure scoped APIs or tools. A document-based pilot can start with approved material already available in the workspace.
Make each handoff inspectable.
Keep source references with the prepared output and review representative results before expanding scope. If the implementation includes executable actions, define their required facts and authority first. Apply retention to any stored records, files, or memory used by the case.
Build evidence from your own work
Start small.
Agree what good looks like.
What to measure for this case
Evidence completeness; repeated evidence requests.
Establish a baseline
Choose a bounded sample of completed cases, record the current process, and agree review criteria with the process owner.
Run in review mode
Use approved sample data and read-only connections. Compare prepared outputs with reviewer expectations, including incomplete and conflicting inputs.
Expand with approval
Enable a limited set of actions only after the team accepts the results. Check approvals, failures, and handoffs before increasing scope.
Make it your workflow
Try this approach
in Agent Lab.
Start with return request. Connect your approved tools, configure the review boundary, and adapt the output to your team's process.
Try Workflow in Agent Lab
Open your ART workspace to configure this use case.
Discuss the setup with usIndustry & department library
Find your next use case.
3 use cases in Retail & commerce
Retail & commerceWorkflow design
- ContextOrder exception
- Agent LabCheck order constraints
- Your teamOperations review
Prepared outputResolution recommendation
Solution blueprint
Order exception resolution
Give support a complete view of an order that needs attention.
Used in this case
Explore the implementation - Connectors & MCP
- Execution governance
- Human approvals
Retail & commerceWorkflow design
- ContextProduct draft
- Agent LabCheck source references
- Your teamContent-owner review
Prepared outputPublication checklist
Solution blueprint
Product content review
Prepare consistent catalogue updates with source evidence attached.
Used in this case
Explore the implementation - Knowledge Base
- File storage
- Agent Skills
- Human approvals
Retail & commerceWorkflow design
- ContextStore question
- Agent LabRetrieve current guidance
- Your teamEscalate exceptions
Prepared outputPolicy-linked answer
Solution blueprint
Store operations guidance
Help store teams find the current operating procedure.
Used in this case
Explore the implementation - Knowledge Base
- Agent Skills
Retail & commerce / Let’s explore the fit
Discuss your
industry use case.
Tell us where work slows down. We’ll discuss how ART could fit your process, your systems, and the decisions your team needs to own.
