Stats
Actions
Tags
ServiceNow AI Agent Studio reference for coding agents deploying AI agents on ServiceNow. Data model, entity mapping, URL patterns, tool types, prompting patterns, MCP setup, and browser navigation. Use when building, configuring, or debugging AI agents on ServiceNow (Zurich or later). Triggers: servicenow, AI Agent Studio, agent studio, sn_aia, agentic workflow, now assist agents, servicenow agent deployment.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-blueprint-skills:servicenow-ai-agentsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A community reference for coding agents deploying AI agents on ServiceNow's
A community reference for coding agents deploying AI agents on ServiceNow's AI Agent Studio. Covers the data model, entity relationships, tool types, prompting patterns, and browser navigation.
This skill provides the platform knowledge. For deployment methodology
(phased rollout, test gates, pilot-first approach), load the companion
agent-deployment skill.
For expert-level deployment support with battle-tested patterns, version-specific configuration, and security hardening, see Agent Blueprint.
ServiceNow is a massive platform that changes every release. Do NOT rely on training data for ServiceNow-specific behavior. Search the official docs and community proactively, not just when stuck.
Before creating records: search for current field requirements. Before configuring tools: search for tool type behavior on the target version. Before telling the user to do anything manually: search for a programmatic approach. When something fails: search the community forums for the error message.
When you get instance access, do ALL of these before creating any records:
Confirm the instance version. Query sys_properties for glide.buildtag:
curl -s -u user:pass https://INSTANCE.service-now.com/api/now/table/sys_properties?sysparm_query=name=glide.buildtag&sysparm_fields=value
Confirm with the user: "Connected to [instance] running [version]."
Verify your access works. Try a simple table query to confirm credentials
and permissions. If using MCP tools, test discover_table_schema on a table.
Extract schemas for the tables you'll work with. Query sys_dictionary
or use discover_table_schema on sn_aia_usecase, sn_aia_agent,
sn_aia_tool, and other AI Agent Studio tables. Do not guess field names.
Research the instance version. Search the web for version-specific docs, best practices, and known limitations. Tell the user what you found.
| Table | Entity | Purpose |
|---|---|---|
sn_aia_usecase | Agentic Workflow | Orchestrates worker agents |
sn_aia_agent | AI Agent | Worker with tools and instructions |
sn_aia_team | Team | Groups agents for a workflow |
sn_aia_team_member | Team Member | Links agent to team (junction) |
sn_aia_tool | Tool | Action available to agents |
sn_aia_agent_tool_m2m | Agent-Tool Link | Links tools to agents (junction) |
sn_aia_trigger_configuration | Trigger | Record-based triggers for workflows |
| Table | Entity | Notes |
|---|---|---|
sn_aia_agent_config | Agent Config | Extended config (proficiency, active) |
sn_aia_version | Version | Version management (Australia+) |
sn_aia_execution_plan | Execution Plan | Runtime execution tracking |
sn_aia_execution_task | Execution Task | Individual tool calls and reasoning steps |
sn_aia_strategy | Strategy | Orchestration strategy configuration |
sn_aia_usecase (workflow)
|-- .team --> sn_aia_team
| |-- sn_aia_team_member (junction)
| |-- .agent --> sn_aia_agent
| |-- sn_aia_agent_tool_m2m (junction)
| |-- .tool --> sn_aia_tool
|-- sn_aia_trigger_configuration.usecase --> (triggers)
|-- sn_aia_version.target_id --> (versions, Australia+)
sn_aia_usecase: name, description, base_plan (NOT instructions), team, execution_mode, strategy, record_typesn_aia_agent: name, description, role, instructions, proficiency, compiled_handbook, agent_type, strategysn_aia_tool: name, description, tool_type, script, input_schema, output_schema, execution_modesn_aia_trigger_configuration: usecase, target_table, condition, channel, active, run_as| If you want... | Use this field | On this table | NOT this field |
|---|---|---|---|
| Workflow orchestration instructions | base_plan | sn_aia_usecase | |
| Agent step-by-step logic | instructions | sn_aia_agent | |
| Agent persona/context | role | sn_aia_agent | |
| Agent proficiency description | proficiency | sn_aia_agent |
Always verify field names against the live instance. UI labels don't always match database column names:
instructions (DB field on sn_aia_agent)base_plan (DB field on sn_aia_usecase)When translating an AI agent blueprint to ServiceNow:
| Blueprint Role | ServiceNow Entity | Table |
|---|---|---|
| Manager / Orchestrator | Agentic Workflow | sn_aia_usecase |
| Worker | AI Agent | sn_aia_agent |
The Manager agent IS the agentic workflow. Do not create a separate
sn_aia_agent record for the orchestrator. Its routing logic, escalation
rules, and orchestration instructions go into the workflow's base_plan field.
ServiceNow's ReAct engine handles agent selection, sequencing, and handoff natively.
If the blueprint defines N agents (e.g., "5 agents: 1 manager + 4 workers"),
create N-1 sn_aia_agent records. The manager becomes the workflow record.
| Type | Use Case |
|---|---|
| Record Operation | CRUD on ServiceNow records (built-in) |
| Script | Custom server-side logic |
| Flow/Subflow | Multi-step automation via Flow Designer |
| Search Retrieval | AI Search / RAG against knowledge bases |
| Web Search | External internet search |
| MCP Tool | External tools via MCP servers |
| Catalog Item | Present service catalog items to users |
Script tools use a self-executing function pattern:
(function(inputs) {
// Your logic here
return JSON.stringify(result);
})(inputs);
Use return, not gs.info(). The return value is what the agent receives.
Use Markdown formatting. Write in second person imperative ("Analyze this..."). Be specific with tool names and conditions. Define gates ("Do NOT proceed until...").
# Objectives
"Your objective is to..."
# Validations (before execution)
"First check if..."
# Steps
"1. Use the [Tool Name] tool to..."
# Expected Output
"Present a resolution plan with..."
# Constraints
Do's and don'ts.
Name input parameters explicitly in instructions. The ReAct engine is dramatically more reliable when instructions reference specific parameter names rather than vague descriptions like "query the relevant tables."
The most widely used community MCP server for ServiceNow:
servicenow-mcp-serverProvides: table queries, schema discovery, background script execution, incident management, knowledge base access.
More tools including flow development and diagnostics:
@servicenow/sdkMost ServiceNow work can be done via REST API:
# Query a table
curl -s -u user:pass "https://INSTANCE.service-now.com/api/now/table/sn_aia_agent?sysparm_query=sys_scope=APP_SCOPE_ID&sysparm_fields=name,sys_id"
# Create a record
curl -s -u user:pass -X POST -H "Content-Type: application/json" \
"https://INSTANCE.service-now.com/api/now/table/sn_aia_agent" \
-d '{"name":"My Agent","description":"Agent description"}'
Auth note: Basic auth on every request can trigger CSRF failures on some tables. For multi-request workflows, capture session cookies from the first authenticated request and reuse them.
Create scoped apps on sys_app (the Application table). This gives you a
proper application scope that contains all your AI Agent Studio records.
curl -s -u user:pass -X POST -H "Content-Type: application/json" \
"https://INSTANCE.service-now.com/api/now/table/sys_app" \
-d '{"name":"My AI Agents","scope":"x_myco_ai_agents","version":"1.0.0"}'
After creating, switch to the new scope before creating agent records. Records created in the wrong scope require manual moves.
| Page | URL Pattern |
|---|---|
| Overview | /now/agent-studio/overview |
| Create & Manage | /now/agent-studio/create-manage/ |
| Use Cases tab | /now/agent-studio/create-manage/params/selected-tab/use_cases |
| Playground | /now/agent-studio/playground |
| Test Execution | /now/agent-studio/playground/params/execution-plan/{sys_id} |
| Settings | /now/agent-studio/settings |
| Use Case Setup | /now/agent-studio/usecase-guided-setup/{sys_id}/params/step/details |
| Page | URL Pattern |
|---|---|
| List view | /{table}_list.do (e.g., /sn_aia_agent_list.do) |
| Record view | /{table}.do?sys_id={sys_id} |
| Background Scripts | /sys.scripts.do |
| System Properties | /sys_properties_list.do |
When workspace URLs fail, fall back to classic UI. The *_list.do and
*.do patterns are the most predictable across all ServiceNow versions.
| Page | URL Pattern |
|---|---|
| Home | /now/servicenow-studio/home |
| App Builder | /now/servicenow-studio/builder?table=sys_app&sysId={sys_id} |
Do NOT use $studio.do (legacy Studio). It shows a limited file tree and
misses AI Agent artifacts.
| Scenario | Wait Time |
|---|---|
| After login | 3-5 sec |
| Workspace page load | 5-6 sec |
| Classic UI page load | 2-3 sec |
| After form submission | 2-3 sec |
| Agent test execution | 15+ sec |
Use time-based waits, not text-based waits. ServiceNow's dynamic content makes text-based waits unreliable.
| Element | Selector |
|---|---|
| All menu | menuitem "All" |
| Filter textbox | textbox "Enter search term to filter All menu" |
| Playground: workflow radio | radio "Agentic workflow" |
| Playground: select workflow | combobox "Select one" |
| Playground: task input | textbox "Task" |
| Playground: start | button "Start test" |
f2e prefix./navpage.do. Re-run login flow.menuitem "All", type in the filter textbox, click matching result./now/agent-studio/playgroundradio "Agentic workflow"combobox "Select one"textbox "Task"button "Start test"For repeatable, traceable testing, invoke agents via API rather than UI. See the ServiceNow docs for the Execution Plan API.
For a structured deployment approach with phased rollout, test gates, and
pilot-first methodology, load the agent-deployment skill from this plugin.
The recommended sequence:
Found a missing URL pattern, selector, or useful tip? Contributions welcome at https://github.com/agent-blueprint/agent-blueprint-skills.
Built by Agent Blueprint -- AI advisory for enterprise agent deployment.
npx claudepluginhub agent-blueprint/agent-blueprint-skills --plugin agent-blueprint-skillsBuild, modify, debug, and deploy agents with Agentforce Agent Script — Salesforce's scripting language for AI agents on the Atlas Reasoning Engine. Covers `.agent` files, subagents, actions, validation, CLI commands, and publishing.
Builds, modifies, debugs, and deploys Agentforce agents using Agent Script. Covers .agent files, actions, subagents, flow control, and CLI commands.
Builds, modifies, debugs, and deploys Salesforce Agentforce AI agents using Agent Script, .agent files, aiAuthoringBundle metadata, and sf CLI commands like generate, preview, publish, test.