Agent responsibility
Retrieve runbook context
Retrieve the relevant procedure and prepare a source-linked checklist without executing system changes.
Referenced next steps
IT & operations / IT service management / Solution blueprint
Runbook knowledge assistance
Help operators find the procedure that fits the incident.
Business problem & expected outcomes
The challenge behind
runbook knowledge assistance.
Operators search multiple knowledge stores while responding to an issue.
What this workflow is designed to deliver
Referenced next steps
Retrieve the relevant procedure and prepare a source-linked checklist without executing system changes.
How to measure the improvementCorrect runbook retrieval; unsupported recommendations; time to a useful checklist.
Start with the right information.
Approved runbooks, service identifiers, and incident symptoms.
Interactive workflow diagram
From operational question
to a clear next step.
Retrieve the relevant procedure and prepare a source-linked checklist without executing system changes.
IT & operationsSelect a stage to explore
Context
Operational question
Approved runbooks, service identifiers, and incident symptoms.
Prepared outputReferenced next steps
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.
Knowledge Base
Project & environment scopeRetrieve approved guidance and attach source references to the prepared answer.
Connectors & MCP
Scoped read accessRead the source records needed for runbook knowledge assistance. Pass record identifiers and retrieved evidence to the agent.
The decision boundary
Keep the initial scope read-only; operators decide and perform remediation.
ART product mapping
Components used.
Chosen for this case.
Agent Lab prepares the work described below. These are the capabilities that support this workflow.
Agent Lab
Knowledge Base
Retrieve approved guidance and attach source references to the prepared answer.
Agent Lab
Connectors & MCP
Retrieve the required records through scoped tools; begin with read-only access.
The implementation, step by step
From source context
to a reviewed result.
- 01
Operational question
Approved runbooks, service identifiers, and incident symptoms.
Agree the trigger or manual request, record identifiers, and the process owner. - 02
Retrieve runbook context
Retrieve the relevant procedure and prepare a source-linked checklist without executing system changes.
Define instructions, permitted tools, and the expected output. Keep missing information explicit. - 03
Operator decision
Keep the initial scope read-only; operators decide and perform remediation.
Keep the pilot in preparation mode and use the team’s existing review process. - 04
Referenced next steps
Correct runbook retrieval; unsupported recommendations; time to a useful checklist.
Compare outputs with reviewed examples and test incomplete, conflicting, and unauthorized inputs.
Before you build
What this implementation needs.
Knowledge Base
An approved document set, content owners, and retrieval access boundaries.
Connectors & MCP
Source-system APIs or MCP tools, scoped credentials, and an integration owner.
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.
Keep the initial scope read-only; operators decide and perform remediation.
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
Correct runbook retrieval; unsupported recommendations; time to a useful checklist.
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 operational question. 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 IT & operations
IT & operationsWorkflow design
- ContextIncident signal
- Agent LabRetrieve the runbook
- Your teamResponder review
Prepared outputResponse brief
Solution blueprint
Incident response coordination
Turn an alert into a contextual handoff for the operator.
Used in this case
Explore the implementation - Multi-agent orchestration
- Events & triggers
- Connectors & MCP
- Knowledge Base
- Human approvals
IT & operationsWorkflow design
- ContextAccess request
- Agent LabCheck role & purpose
- Your teamAccess-owner review
Prepared outputDecision-ready request
Solution blueprint
Access request triage
Prepare complete access requests for the people who authorize them.
Used in this case
Explore the implementation - Agent Skills
- Execution governance
- Human approvals
IT & operationsWorkflow design
- ContextChange request
- Agent LabAssemble impact evidence
- Your teamChange-owner review
Prepared outputChange review pack
Solution blueprint
Change request evidence preparation
Make change requests easier for the review board to assess.
Used in this case
Explore the implementation - Agent Skills
- Execution governance
- Human approvals
- File storage
IT & operations / 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.
