The query cookbook: every GlideRecord pattern worth memorizing
One page of GlideRecord patterns done right: encoded queries, OR conditions without surprises, GlideAggregate, pagination, and the security layer everyone forgets.
G&G ~ servicenow x ai field notes
From GlideRecord
to generative AI.
A field journal for builders working where ServiceNow meets AI. Practical posts on Now Assist, AI agents, RAG over the Now Platform, and shipping intelligent workflows.
Latest writing
58 articlesCIS-SPM Study Guide: Strategy to Delivery, Minus the Surprises
A practical study guide for the ServiceNow CIS-SPM exam: the portfolio hierarchy, demand management, resource plan states, agile and waterfall together, and a six week plan with PDI labs.
From Pilot to Platform: A Maturity Model for Scaling AI Agents Across the Enterprise
Most orgs are stuck with pilots that never become a program. A five-stage maturity model for scaling agents, and the trap of scaling before governance.
Script include patterns: where your server logic actually belongs
The three shapes of a script include, a worked TaskUtils example, client-callable boundaries, scoped API design, and how to actually test the thing.
Prompt Patterns That Actually Work in Now Assist Skills (and the Ones That Quietly Fail)
Prompting a platform skill is a different craft from prompting a chatbot. The patterns that hold up, schema-anchored, grounded, single-purpose, and the anti-patterns that quietly fail.
Testing AI You Cannot Fully Predict: Adapting ATF and QA for Agentic Workflows
Generative AI breaks the assumption ATF is built on: same input, same output. Testing non-deterministic workflows with property checks, evaluation sets, and adversarial guardrail tests.
Governing AI to the EU AI Act and NIST Without Slowing Your Team Down
Compliance stalls agentic programs when it is a gate at the end instead of a property built in. Operationalizing NIST and EU AI Act controls with AI Control Tower, without slowing down.
Scheduled jobs and events: doing work later, the platform way
Scheduled script executions for recurring work, the event queue for reacting to it, and the fire-the-event, do-the-work-elsewhere pattern that keeps both honest.
RaptorDB and the Unsexy Truth About AI Performance at Scale
Agents change the shape of your database load from a human trickle to a machine flood. Why data-tier performance becomes a first-class constraint on scaling autonomy.
HRSD's AI Moment: From Policy Lookups to Autonomous Onboarding Orchestration
HR service delivery offers a clean maturity ladder from policy lookups to cross-department onboarding orchestration. Climb it in order, and skip a rung at your peril.
CIS-HRSD Study Guide: HR Service Delivery Without the Mystery
Who the CIS-HRSD exam is really for, how the COE data model works, why HR security is its own animal, and a six week study plan with hands-on PDI labs.
AI Voice Agents in CSM: What Changes Technically When the Customer Talks to the Machine
A voice agent is not a chatbot with a microphone. The three constraints that reshape the design, latency, no undo, and turn-taking, and why graceful escalation beats heroics.
The SecOps Wrap-Up Agent: AI Inside the Incident Response Loop
Security is where the audit bar is highest. How SecOps AI agents accelerate summarization, correlation, and case wrap-up while the analyst keeps the judgment.
Fix scripts vs background scripts
Same JavaScript, different discipline. When to explore in the background script box and when to ship a fix script that travels with your release.
Token Economics: Cutting the Cost and Latency of Your Now Assist Skills
At production scale, tokens are a line item and latency is felt on every call. Where the tokens go, matching the model to the task, and measuring cost per resolution, not per call.
Self-Healing IT: How Predictive AIOps Moved From Alerting You to Fixing It
AIOps used to stop at a smarter alarm. The technical chain from ingestion to anomaly detection to autonomous remediation, and the boundary discipline that makes self-healing safe.
Evaluating a Skill Like an Engineer: Building a Test Set and Measuring Quality
It looked good in the demo is not QA. Building a representative test set, scoring groundedness explicitly, and regression-testing skills after every change, no data-science team required.
Workflow Data Fabric: Why the Boring Data Layer Is the Real AI Unlock
Everyone talks about agents and nobody talks about the data plumbing that decides whether they are brilliant or useless. Why Workflow Data Fabric, not the agents, is the real moat.
Business rule patterns: picking the right timing
Before, after, async, or display. A decision-shaped recipe for the four business rule timings, the double-update bug, the async previous gotcha, and the discipline that keeps rules maintainable.
Adaptive Thresholds Beat Static Alerts: The Quiet ML Win Most IT Teams Ignore
Most of your alerts are noise because the threshold is static. How learned baselines and anomaly detection cut the noise, and the tuning period that is the honest catch.
From Workflow to "System of Action": The Quiet Repositioning That Tells You Where Enterprise Software Is Going
A big-picture read on the shift from workflow to system of action to autonomous workforce, three predictions, and the one thing that could derail it.
CIS-Discovery study guide: pass the ServiceNow Discovery implementation specialist exam
A field guide to the CIS-Discovery exam: MID Servers, credentials, the four discovery phases, patterns, and the IRE knowledge that actually decides who passes.
Building an MCP-Exposed Action Without Opening a Security Hole
The GA MCP Server lets external agents take governed actions in ServiceNow. Expose one narrow action, scope the identity, log everything, and avoid building a remotely-callable backdoor.
Where ServiceNow AI Agents Fail, The Failure Modes Nobody Puts in the Demo
The failure modes nobody puts in the demo: stale grounding data, automating broken processes, the trust cliff, and silent drift.
Instrumenting Agents for Observability: What to Log Before You Scale Past Ten
An agent you cannot observe is one you cannot debug, trust, or govern. What to log per agent run, why selection traces matter most, and connecting to AI Control Tower before you scale past ten.
GlideAjax done right
The client script needs server data and there are three ways to get it, two of them wrong. The complete client-callable pair, the security angle nobody teaches, and when g_scratchpad is the better answer.
Data Readiness for Agents: Making Your CMDB and Knowledge Base Safe to Ground On
Your agents are only as good as the data they ground on, and most CMDBs are part fiction. The unglamorous, highest-impact prep: accuracy, freshness, ACL hygiene, and structure for retrieval.
Platform of Platforms: Why ServiceNow Is Betting Agents Will Run *Other* Vendors' Systems Too
ServiceNow wants to be the control layer for agents across every vendor's systems. Assessing the ambition, and the concentration risk for buyers.
CIS-EM study guide: pass the Event Management specialist exam
Everything the CIS-EM exam actually tests: the event pipeline, message key deduplication, CI binding, alert correlation, and service health, with a six week plan and PDI labs.
Background scripts without regret
A dry-run-first recipe for deleting a few hundred thousand stale records safely. Count first, log what would change, flip one flag by hand, and keep a grep-able trail.
Guardrails as Code: Configuring AI Guardian and Approval Gates for Autonomous Agents
Guardrails are not a slide, they are configuration. Placing every action on the autonomy spectrum, enforcing prohibitions with AI Guardian, and gating the risky five percent.
The Autonomy Tax: Decoding ServiceNow's New Tiered AI Pricing
ServiceNow restructured pricing around levels of autonomy. Decoding the assistance, agentic, and autonomous tiers, and which rung your work actually needs.
Add a button to a configurable workspace form
Your UI Action works perfectly in the classic UI and is simply not there in the workspace. One checkbox and one new script field fix that. A complete escalate button, start to finish.
Triggers, Not Chat: Event-Driven AI Agents with Flow Designer
The agents that move your metrics fire on platform events, not chat. Wiring event-driven agents in Flow Designer: precise triggers, tight context, deliberate branching, real error handling.
Non-Human Identities Are About to Outnumber Your Employees, Is Anyone Managing Them?
Non-human identities are about to outnumber your employees. The under-told security story of managing agents and the blast radius of one compromised actor.
CIS-CSM study guide: pass the Customer Service Management specialist exam
A working architect's guide to the CIS-CSM exam: the account, contact, and consumer model, the case lifecycle, the entitlement trap, and a six week plan with hands-on PDI labs.
Designing Tools for Agents: The Difference Between a Tool an Agent Uses and One It Abuses
An agent is only as good as its tools, and a tool is judged by whether the agent calls it correctly. Descriptions as prompts, input contracts, idempotency, and testing tool selection.
AI Control Tower and the Rise of "Agent Ops", the Job Nobody Had Two Years Ago
Every tech wave creates a new job. Meet agent ops, the discipline of governing agents at runtime, and the tooling ServiceNow put behind it.
Single Agent vs. Agent Team: When to Reach for the AI Agent Orchestrator
When one agent with a pile of tools starts picking wrong and looping, it is time to decompose. A field guide to the AI Agent Orchestrator, the patterns that work, and the costs nobody mentions.
The New Org Chart: What "AI Specialists" for IT, CRM, HR and Security Actually Mean for Headcount
ServiceNow now ships AI specialists as workforce. What that means for headcount, the career ladder, and managing a mixed human and agent team.
CAD study guide: pass the ServiceNow Certified Application Developer exam
A working developer's guide to the CAD: scoped apps, server and client scripting, Flow Designer, ATF, and deployment, with a six week plan and PDI labs that build a real application.
Under the Hood of Similarity: How doc2vec Actually Powers ServiceNow Matching
Open up the similarity model: doc2vec turns messy record text into vectors that match meaning, not keywords. Why matches degrade, and how to tune with the word corpus.
The Two-Day Rule: How One Company Cut Resolution Time by Deflecting 38,000 Tickets
One firm deflected 38,000 tickets and cut resolution time by two full days. The counterintuitive reason deflection helps the tickets that remain.
RAG Inside a Custom Skill: Wiring AI Search Retrievers the Right Way
RAG on the Now Platform is a concrete component, a retriever wired into a custom skill. Where retrieval quality leaks, and how to test it separately from generation.
Predictive Intelligence or Now Assist? A Real Decision Framework for the Two AI Engines
Two distinct AI engines, and reaching for the LLM when a cheap classifier would win is a design error. A real decision framework for Predictive Intelligence versus Now Assist.
"Vibe Coding" Comes for the Enterprise: A Skeptic's Field Guide to Build Agent
Zurich shipped vibe coding for the enterprise. A skeptic's field guide to Build Agent: the real magic, the governance nightmare, and who it is for.
CSA study guide: pass the ServiceNow Certified System Administrator exam from zero
The complete start-from-zero guide to the CSA: what the exam actually tests, the platform concepts that matter, a six week study plan, PDI labs, and the traps in the questions.
Why ServiceNow Built Its Own LLM Instead of Just Renting OpenAI's
Why ServiceNow built NowLLM instead of just calling a frontier model, and the build-versus-rent lesson any technical leader can steal.
Grounding Done Right: How to Stop Your ServiceNow AI From Hallucinating
Hallucination on ServiceNow is mostly a grounding problem, and grounding is something you control. The engineering fixes that make answers trustworthy.
Bring Your Own LLM to ServiceNow: When the Generic Connector Is the Right Call (and When It Isn't)
When NowLLM is not enough: a decision framework and walkthrough for wiring a third-party model through the generic LLM connector.
Plugging Claude or Copilot Into ServiceNow With MCP: A Practical Integration Guide
The GA MCP Server lets Claude, Copilot, or your own agent take governed actions in ServiceNow. A practical, security-first integration guide.
From Skill to Agent: Wiring Modular Skills Into Something That Actually Resolves a Problem
The leap most tutorials skip: composing modular skills into an AI Agent that reasons about which tool to use, built in AI Agent Studio.
Build Your First Now Assist Skill, No Model Training Required
You will not train a model. A hands-on walkthrough of building your first Now Assist skill in NASK, from input schema to Virtual Agent.
The Prompt Is Not the Product: What's Actually Inside a Now Assist "Skill"
A Now Assist skill is not a saved prompt. A look under the hood at schemas, grounding, and model routing, and why the prompt is the easy 20 percent.
Now Assist vs. the ChatGPT Tab Your Employees Already Have Open
Your employees already paste tickets into a chatbot tab. The honest case for when the embedded AI wins, and it is not about better writing.
The Sidecar Era Is Over, and Most of Us Aren't Ready for What Comes Next
ServiceNow says the bolt-on AI panel is dead. Here is what AI-native actually changes for your daily work, and what it quietly changes about your bill.
11 Million Resolutions and 230% ROI: Anatomy of an AI Deployment That Actually Worked
Reverse-engineering a documented win: 11 million autonomous resolutions, 230 percent ROI, and the boring decision that made it work.
Beyond the Chatbot: 5 ServiceNow AI Use Cases Where Nobody's Talking to a Bot
The chatbot is the least interesting thing AI does on the platform. Five silent, behind-the-scenes use cases where nobody talks to a bot.