Looking to build your first AI agent? This article is for you!   I’m beyond excited about the new AI Agent capability in ServiceNow—this is not just another feature; it’s a revolution in how we interact with systems! I put this to the test by building an AI-powered Travel Approval Agent that: ✅ Reads and understands company policies from the Knowledge Base 📖 ✅ Analyzes travel requests, justifications, and retrieves remaining allowance from an external source 🔍 ✅ Automatically approves or rejects based on policies – no predefined rules! 📊 ✅ Engages with the requestor, explaining the decision and next steps—all without any templates! 🎙️ 💡 Curious to see it in action? I recorded two videos:   📽️ Live Demo – Watch the AI Agent in action!   📽️ Step-by-Step Guide – Learn how I built it!   Here is the example of the instructions used in this video:   Pre-requisites: Instance on Yokohama Now Assist AI Agents plugin installed   Setup instructions: (navigate to "Now Assist AI agents" > Overview)     ### AI Agent ### //Describe and instruct// Name: Travel Request Specialist Description: The Travel Request AI Assistant helps officers streamline the travel request process by approve travel request while ensuring policy compliance and advise officers of next steps. It automatically calculates allowances, manage approvals, and provides real-time updates, reducing administrative burdens and ensuring efficient travel planning. AI agent role: You are a Travel Request Officer AI Assistant, an expert in State Police travel request management within ServiceNow. Your primary role is to help officers efficiently submit, track, approve, and manage their travel requests while ensuring compliance with State Police travel policies. You act as a knowledgeable, structured, and proactive assistant, guiding users through the process with clear, concise, and action-oriented communication. You aim to reduce administrative burden, prevent errors, and ensure approvals are processed smoothly. Your decision-making approach is policy-driven, systematic, and user-friendly, ensuring that officers understand their travel entitlements, submit correct information, and receive timely status updates on their requests. Instructions: General Guidelines: Always communicate in a clear, concise, and structured manner. Follow State Police travel policies when providing guidance. Flag potential errors or non-compliance issues and offer corrective guidance. Provide real-time updates on request status and next steps. Task-Specific Instructions: Policy Compliance & Validation Check if the request meets State Police travel guidelines (e.g., trip justification, duration, and expense limits). Validate that the selected accommodation and transport modes align with regulations. Flag any policy violations or inconsistencies and provide corrective steps. If compliant, proceed with the request approval Condition: If the request is non-compliant, provide an explanation and suggest corrective actions before submission. Steps Order: 1. Get the travel request details 2. List and summarise the requestor's travel history 3. Retrieve the requestor's travel allocation balance once (do not update it) 4. Approve or Reject the travel request 5. Send a nice email to the Requestor updating on the Approval decision Constraints & Limitations: It must follow State Police travel policies and not override compliance rules. It should not alter or create travel records without user input. The AI must ensure officers receive accurate and relevant information before submission. Each Step should run only once Travel allocation balance should only be checked once, and not be updated part of this action. //tools and information// Retrieval Augmented Generations (RAGs) Name: Travel Request Knowledge Base Retriever Description: This tool retrieves relevant Knowledge Base (KB) articles from the State Police ServiceNow instance to assist officers with travel requests, expense policies, and approval workflows. It ensures that officers have direct access to accurate, up-to-date policy information without manual searches. How the AI Uses This Tool: Identify User Query Context: If the officer requests travel policy guidance, expense claim procedures, or approval steps, trigger the RAG retrieval. Perform KB Lookup: Query the ServiceNow Knowledge Base for articles that match the officer’s question. Use natural language processing (NLP) to refine searches (e.g., “What is the meal allowance for a two-day trip?”). Return Relevant KB Articles: Display the most relevant KB articles with summaries and links. Ensure that articles are ranked by relevance based on the officer’s request. Provide Next Steps: If an article answers the question, summarize key points for the officer. If further clarification is needed, offer to refine the search or connect the officer with support. Inputs & Queries: User Query: The AI captures keywords from the officer’s request. ServiceNow KB Table Query: Query Syntax: sysparm_query=active=true^short_descriptionLIKE[query] OR textLIKE[query] Fields Retrieved: short_description, sys_id, category, text Filters Applied: Only active KB articles Sort by relevance and last updated date Supervised or Autonomous: Autonomous Display output: Yes Search Profile: Knowledge Portal Search Profile Search sources: Knowledge Table Fields returned: Short description + Article body Results limit: 5 Search criteria: Hybrid Semantic indexed fields: body + title //subflow// Name: [TR] Get the details of the travel request Description: Use this action to retrieve key details of a travel request, including destination, travel dates, purpose, requested for, expense estimates Supervised or Autonomous: Autonomous Display output: Yes Name: [TR] Get requestor travel request history Description: Use this action to retrieve the requestor's past travel requests, including destinations, dates, purposes, duration. The display output should be a summary in 1 small paragraph Supervised or Autonomous: Autonomous Display output: Yes Name:[TR] Find Requestor Annual Allowance Description: This subflow will be used to retrieve the requestor's annual travel allowance details. The subflow requires input of the Requestor Name and returns the remaining balance in days and stop. Do not run this action more than once. Do not update the balance Supervised or Autonomous: Autonomous Display output: Yes Name: [TR] Update Travel Request Approval Description: Use this action to update the approval status of a travel request. Input: request number and approval decision (values: Approved or Rejected) Supervised or Autonomous: Autonomous Display output: Yes Name: [TR] Send a travel request email Description: This subflow generates a professional, well-structured email to notify the requestor about the status of their travel request. The email should be formatted in clear business language, ensuring a structured flow with three distinct sections: (1) Summary of the travel request, (2) Approval decision with justification, and (3) Next steps and relevant guidance. The email should sound natural and well-written, demonstrating AI-powered clarity and effectiveness. Ensure the approval decision section includes a concise reason if applicable. If the request is approved, provide reassurance and relevant reminders (e.g., travel policies, reimbursement procedures). If rejected, include a polite and constructive explanation with guidance on possible next actions. The tone should be professional yet supportive, ensuring clarity while making the requestor feel well-informed. Example Output: Subject: Travel Request Decision – TRA0001037 Dear Sylvain Hauser, I am pleased to inform you that your travel request (TRA0001037) for travel to Newcastle (NSW) from 27th to 2nd has been approved. Your request met all necessary policy requirements, and we look forward to supporting your upcoming travel. As part of the approval process, please ensure that all arrangements are made in line with department policies. If accommodation or transport adjustments are required, kindly confirm them as soon as possible. For any further assistance or clarifications, feel free to reach out. Safe travels! Best regards, Supervised or Autonomous: Autonomous Display output: Yes //Availabilit// Status: Active ### Use Case ### Name: Travel request approval Description: Review the Travel request and approve or reject it based on defined criteria Instructions: If the user asks to get a travel request approved, invoke the Travel Request Officer agent Connect AI agents: Travel Request Officer //Trigger// Existing triggers: none //Display// Now Assist panel: On TESTRECORD: What to test: Travel request approval Task: TRA0001037         ... View more

We just deployed our first AI agents with a state government client. The job? Automate travel applications. Sounds simple — until you see what actually happened. The process was a mess: fragmented user data across platforms, tangled travel policies, layers of approvals. Perfect storm for AI. And the AI agents crushed it.   Approval times went from over a week to a few hours. The AI didn’t just get the green light — it sent out clean, policy-compliant emails with travel options, health info, and even nearby cafes. Fully automated. Client feedback? Best experience in a decade. Better than any human service experience. This wasn't a pilot. It was a paradigm shift.   Three big takeaways from this moment: AI agents are real and they’re not toys. They’re 24/7 autonomous problem solvers that can replace multi-step processes with 5-7 bulletproof moves. Data doesn’t have to be perfect anymore. For decades we’ve been chasing clean data lakes and structured data sources. Now, LLMs thrive in the mess. Think ChatGPT, Grok — making clear and articulate sense of the internet; the messiest data set of all. Governance is the next big thing. Final review layers, control towers, bias filters — all critical as agents scale. Don’t think it’s optional. We’re on the edge of a resourcing revolution. By 2030, you’ll see roles like: AI Architects Agent Trainers Control Tower Ops Edge Reviewers or final review layers And here’s the hard truth: these ai agents will outperform 80% of service/admin roles in public and private sectors. It’s uncomfortable. But it’s real. If you’re in delivery, consulting, or tech strategy, rip up your old playbook. The best work will come from creative strategy, not technical plumbing or classical process mapping. Ask yourself: If I had an  autonomous AI Agent that never sleeps, how would I reimagine this process from scratch?   AI Agent adoption and use cases will be slow... until it’s not. You’ll blink, and it’ll be 2030, and we’ll be living in a new world. So what should you do right now? Experiment. Be curious. Relearn. I resisted this at first — 20 years in tech and suddenly I felt like the 18-year-old intern knew more than me. But I leaned in. And it’s the best decision I’ve made in years.   This isn’t hype. It’s not going away. The AI agent wave is building — and you want to be ahead of it when it hits.   Learn more about ServiceNow's AI Agents: What are ServiceNow AI Agents? (2 min 46 sec) Idris Elba introduces ServiceNow AI Agents (1 min) Welcome to ServiceNow University – with Professor Idris (59 sec) ... View more

When managing user roles in ServiceNow, it's essential to distinguish between active users and those who have not accessed the system in a long time. The following steps will help you generate a report listing active users assigned to specific roles.     Steps to Generate the Report Access the User Roles Module Navigate to the "User Roles" module. Alternatively, type sys_user_has_role.list in the application navigator and press Enter. Apply Filters to Identify Active Users Click the funnel icon to open the filter options and build the following query: User > Active → is true User > Last login time → RELATIVE after 365 days ago User > Web service access only → is false (excludes API users) Role > Name → is [role name #1] OR Role > Name → is [role name #2] (Add additional roles as needed) Run the Query Depending on the number of users in your system, the query may take some time to process. Review the Results The list will display active users with the selected roles, allowing you to verify proper role allocation.       Enhancing Role Audits with Custom Reports This method is especially useful when combined with the custom scan Excel report available from your ServiceNow account team. These reports highlight all roles flagged as Fulfiller, helping you streamline role audits and ensure correct access permissions.     Published by Sylvain Hauser. From his internship at ServiceNow in 2007 to his certification as a Technical Architect (CTA), Sylvain has spent most of his professional life leading innovation with ServiceNow. ... View more

ServiceNow provides powerful out-of-the-box (OOTB) applications designed to meet common business needs. However, many organisations find that these standard applications do not always align perfectly with their unique workflows, integration needs, or scalability requirements. As a result, organisations choose to build custom applications using ServiceNow App Engine and custom application scopes, which are part of the Creator Workflow suite of products. This article explores the key reasons behind this preference and the benefits of custom development on the ServiceNow platform. ... View more

As businesses seek greater agility, scalability, and security, the need for robust mega applications—large-scale enterprise solutions that unify workflows, data, and automation—has never been more critical. ServiceNow’s single-platform approach, combined with its structured application scopes, offers a compelling framework for building these mega apps efficiently.   Building unique mega applications on ServiceNow using application scopes provides a structured, secure, and scalable approach to enterprise development. Think of ServiceNow’s Now Platform as an enterprise application development operating system, much like how Apple’s operating systems provide a governed, secure, and scalable environment for mobile and desktop applications. Just as Apple ensures developers follow strict guidelines for performance, security, and user experience, ServiceNow enables enterprises to build large, secure, and highly scalable applications using the App Engine.   By leveraging application scopes, governance, and advanced automation, businesses can develop mega apps tailored to their unique and large-scale problems while ensuring maintainability and security. As AI and automation continue to evolve with the likes of Agentic AI (autonomous AI Agents), ServiceNow’s platform ensures that businesses remain at the forefront of innovation, delivering powerful, future-ready solutions.   Australian Scoped Application Use Cases Gold Coast Health – Clinical Photography Application 🔗 Learn more [here]. Australian Energy Market Operator – Energy Distributor Supplier Demand Management & Supplier  Responsiveness - including negotiations of rate cards and volume discounts 🔗 Learn more [here]. Sportsbet: automate and consolidate identity access management, ensuring the security of customer data 🔗 Learn more [here]. Australian Department of Defence – Rifle Range Management Application 🔗 Learn more [here]. NSW Health – Health Outcomes and Patient Experience (HOPE) Platform  🔗 Learn more [here } NSW Healthcare Outpatients services, eliminating paper and faxes (connected 3400 GP clinics to hospitals clinics across NSW) 🔗 Learn more [here} Orica – Patent & Patent Lifecycle Management, Product Formulation Process 🔗 Learn more [here]. Australian Federal Police (AFP) National Operations State Service Centre Portal to receive and action reports and requests from other government agencies 🔗 Learn more [here]. NSW Police – BluePortal officer safety and mental well-being: 🔗 Learn more [here]. NSW Police - Integrated Police Operations: Officers can digitally request support from specialised units such as the Dog Unit, Mounted Unit, Marine Area Command, and Tactical Operations Unit. 🔗 Learn more [here].   Compass Group Hybrid Experience -  Service Portal & Apps custom branded a on Android & IOS APP Stores Guest App Digital Village in your Pocket (webinar on-demand)                 Compass Group Functionality  - Carousel updates, Book Events, Service Requests, Dinner Menu's, Knowledge Articles,  Feedback Forms / Surveys, Maintenance Requests with Images,  Way finding Maps, FaceID, SSO   Hiding Complexity for a Seamless Experience Consider how platforms like Uber and Amazon enhance the end-user experience by hiding complexity. When a user requests a ride on Uber, they don’t need to worry about driver assignments, route optimisations, or payment processing—everything happens behind the scenes to deliver a smooth experience. Similarly, Amazon automates order fulfillment, inventory management, and logistics so customers can seamlessly place and receive orders without worrying about backend operations. ServiceNow operates in the same way, providing a seamless experience for end users while managing complex workflows, approvals, integrations, and data exchanges behind the scenes. It effortlessly connects the middle office, back office, and external service providers, ensuring that processes flow smoothly without requiring users to engage with the complexities of enterprise systems. This allows businesses to focus on innovation and efficiency rather than being bogged down by operational intricacies.   The Lego Analogy: Building Blocks for Scalable Solutions Think of ServiceNow’s application scopes like Lego bricks. Each scope is a self-contained module, allowing developers to build large, complex solutions from smaller, well-defined components. Just as Lego structures can be expanded or modified without affecting the integrity of individual bricks, ServiceNow’s scoped applications enable businesses to scale their solutions while maintaining strong governance, security, and modularity.   Pro-Code Capabilities for Advanced CustomiSation While ServiceNow is renowned for its low-code/no-code capabilities, it also provides robust pro-code functionality. Developers can leverage JavaScript, Flow Designer, REST APIs, and the ServiceNow App Engine to build highly customised solutions. This enables organisations to meet complex business requirements while maintaining enterprise-grade scalability.   University of Melbourne Business Smart Customisation Management Application Including Business justification & benefit, technical impact, owner, audit and traceability, automated scan triggers - See best practice webinar here         Improved Security Posture and Reduced Risk These Australian government agencies have successfully leveraged ServiceNow to digitise workflows, enhance security, and improve efficiency. From policing and healthcare to defence and emergency response, ServiceNow is driving digital transformation across critical sectors. ServiceNow’s application scopes enforce clear boundaries between applications, reducing risks associated with data leakage and unauthorised access. By isolating different applications, organisations gain: Enhanced Governance: Clear access control policies ensure that only authorised users can modify specific applications. Data Protection: Scoped applications prevent data sprawl and unauthorised cross-application data sharing. Regulatory Compliance: Organizations can implement security frameworks that align with industry standards, such as ISO 27001 and GDPR.   The AI-Powered Future of Enterprise Application Development The integration of Agentic AI, AI and Generative AI (GenAI) is transforming enterprise application development, making systems more intelligent, autonomous, and adaptable. ServiceNow leverages these technologies to automate workflows, generate code, and optimise processes, significantly reducing development cycles and improving agility. Agentic AI for Autonomous Operations: Unlike traditional AI, Agentic AI can act independently, proactively executing tasks, making intelligent decisions, and optimising workflows without requiring constant human intervention. This enables ServiceNow applications to self-adapt, resolve issues, and streamline operations dynamically. AI-Augmented Development: AI-driven recommendations help developers build applications faster by automating testing, suggesting best practices, and detecting potential issues before deployment. Leverage natural language-based development to create workflows and applications, democratizing innovation across the enterprise. Intelligent Process Automation: AI-powered bots and predictive analytics enhance workflows by optimising task execution, reducing manual effort, and improving decision-making.   By integrating Agentic AI, and GenAI within ServiceNow scoped applications, enterprises gain a secure, governed, and intelligent way to innovate—ensuring autonomous, scalable, and self-optimizing workflows while maintaining full control over their enterprise ecosystem.   ServiceNow AI Agents | Put AI To Work For People   Conclusion In today’s rapidly evolving digital landscape, enterprises require scalable, secure, and seamlessly integrated applications to drive efficiency and innovation. ServiceNow scoped applications provide a structured and governed framework that enables organisations to develop and deploy custom solutions without disrupting existing workflows. Similar to Apple’s iOS model, ServiceNow enforces strong governance through application scoping, ensuring data integrity, security, and controlled access. Employees already use ServiceNow as their primary workspace, making it easy to introduce new applications without adding complexity or requiring extensive retraining. With prebuilt, modular components, organisations can accelerate development, reducing time-to-value. As a platform with enterprise-grade security, ServiceNow ensures all applications adhere to the highest security and compliance standards, mitigating risks associated with third-party integrations. Most enterprises are already connected to key data sources within ServiceNow, enabling scoped applications to seamlessly leverage existing integrations. Rather than introducing standalone tools, organisations extend their existing architecture, maximising ROI while maintaining a unified experience.     **NEW** ServiceNow Studio | Overview   ... View more