Agentic workflows extend Now Assist for CSM beyond human assistance by enabling autonomous execution of multi-step actions directly from the context of a case, conversation, and/or customer intent, independent of where the data resides thanks to AI Agent Fabric and Workflow Data Fabric.
These flows reduce friction for agents and allow the platform to act on their behalf using secure guardrails.
Prebuilt agentic workflows like Triage Cases or AI Agents like Troubleshooting Steps identification leverage the full ServiceNow AI Platform (Flow Designer, Script, Topics, Catalog Items, RAG, Record operations, web search, Generative AI inputs and more) and any existing automation you've build to intelligently guide or execute behind-the-scenes processes while mix and matching solutions for your specific customer facing teams. The combinations are up to your use cases. This allows humans focus on more complex work to increase customer satisfaction and resolution.
Discover more by clicking on each of the CSM Agentic Workflows or AI agents:
In addition the following agentic workflows are also included as part of the ServiceNow AI Platform and can be tailored for CSM:
Classify tasks (Community deep dive)
Generate My Work Plan (Community deep dive)
Generate resolution plans
Process images for tasks
Process emails for tasks
Analyze task trends
Identify ways to improve service
Investigate problems
Propose survey responses
Key Best Practices
- Understanding AI Agents in ServiceNow
-
General guidelines for creating AI agents and agentic workflows
- When to Use AI Agents: Rationalizing Uses Cases for Workflows, GenAI Skills & AI Agents
- Introducing AI Agents and Quick Start Guide
- AI Agent tools – Getting the most out of your agentic workflows
- Create your own AI Agent! A walkthrough on creating an AI Agent using AI Agent Studio
- AI Agents FAQ and Troubleshooting
- AI Agent Practical Implementation: Lessons from the Field
- How Governance can accelerate the adoption of AI Agent
- Finding the Right Jobs for AI Agents: A Strategic Approach to Use Case Identification
- Optimizing AI Agents at Every Step with ServiceNow Process Mining (Recording)
7 Proven Practices for Successful Agentic AI Implementation
-
Design with Structure First
Give each step a single owner (agent) and a single tool. Streamline parallel processes into one clear flow and trigger them in predictable ways to reduce complexity. Reasoning prompting excels at this. -
Prioritize the User Experience
Make interactions seamless by pulling data from existing records, requesting inputs in intuitive ways, and keeping each step focused on one clear tool while allowing AI agents to dynamically choose the right tool at runtime. -
Create Standards You Can Trust
Use consistent naming, formats, and instructions so AI agent behavior is predictable and traceable. Enforce data privacy rigorously, especially when handling sensitive information. -
Don’t Wait for Perfect Data
Launch with out-of-the-box, productivity-focused agents to deliver quick wins and using generative AI to clean and structure key data (Knowledge, resolution notes, CRM Foundation data models, others). Early successes feed better data back into the system, accelerating future improvements. -
Check Readiness Before You Deploy
Use instance readiness tools to detect customization conflicts before rollout. Preventing issues is faster and easier than fixing them post-deployment. -
Know When Agentic AI Isn’t the Answer
Not every task needs full Agentic AI. Reserve it for problems that require reasoning and planning. Keep single-step or simpler tasks in Now Assist skills or Flow Designer to avoid unnecessary complexity.
Measured Success
How do we usually measure success in this set of purpose-driven skills?
| Outcomes | Explanation (with applicable use case) | Success Metric |
|---|---|---|
|
Faster time-to-triage |
Reduce time spent manually classifying or reassigning cases by auto-executing routing flows Use case: Triage Cases |
Avg. time from case creation to routing (seconds) |
|
Reduced agent intervention |
Decrease manual effort by letting agentic flows execute background tasks when conditions are met Use case: Troubleshooting Steps |
% of tasks executed autonomously |
|
Higher accuracy in resolution |
Deliver more consistent troubleshooting flows by embedding decision logic at point of need Use case: Troubleshooting Steps |
% of cases resolved without additional escalation |
|
Increased workflow reuse |
Use modular agentic flows that can be reused across departments or processes with case types Use case: Triage Cases |
Number of flows reused across workflows or LOBs |
|
Reduced mean time to resolve |
Accelerate case resolution by acting on contextual triggers rather than waiting for agent input Use case: Triage Cases + Troubleshooting Steps |
MTTR (minutes) |
Frequently Asked Questions
1. Why is my agentic workflow not finding the task record (case or interaction)?
Make sure you are prompting correctly when executing the plan if not using triggers or just using the test playground. The prompt can be defined within the agentic workflow setup. By default it is:
table=x, record=y where x is the table you are targeting and y is the record you want to do the workflow on.
2. What initial steps can I take to troubleshoot my agentic workflow or AI agent?
Please follow this following Now Support article: https://support.servicenow.com/kb?id=kb_article_view&sysparm_article=KB2507579
