Getting ready for Now Assist

Matt Dodd · ‎08-26-2024

(*updated as per Yokohama Patch 3)

Implementing Now Assist is a strategic move that can significantly uplift your organization's productivity and improve the engagement experience for your users and customers. To ensure a smooth and successful implementation it can be helpful to take several readiness steps in preparation. After numerous conversations with customers on this topic, a common ask is "What kinds of things can we do in preparation for it?"
There a numerous documents and articles written on the more technical aspects of this question, however not so many that talk about some of the other considerations - which is the purpose behind this article.

Knowledge Management
This is one of the key areas that will help make Now Assist successful. Ensuring that the knowledge base is up-to-date and contains relevant articles that Now Assist can leverage for AI search tuning. This will help provide accurate and actionable answers.
1. Leading Practices: All of the usual leading practices around Knowledge Management are especially applicable to Now Assist readiness. This includes:
  1. Retiring old and out-of-date content to ensure that Now Assist doesn’t surface this content to your users.
  2. Ensure a feedback mechanism exists to continuously improve the knowledge. Encourage users to provide feedback on articles, which can be used to refine and enhance the content.
  3. Schedule regular audits of your knowledge to identify gaps, outdated information to be retired, and areas for improvement.
  4. For more comprehensive tips specific to Knowledge, please refer to this excellent community post, Best Practices to use your Knowledge Articles with Now Assist
2. Access to content: Think about the audience for Now Assist and ensure that the various personas and roles that you have in your organization will be catered for correctly. Consider the industry you are in and which types of users will want to find/consume different types of information. Unless configured otherwise, Now Assist will potentially surface answers from all knowledge sources that the user has access to. Setting up and using User Criteria can help contain searches to the areas that are applicable to your users.
  Typically we cater for requester or fulfiller/agent roles quite well, but don’t always consider other differences such as examples of faculty/staff vs students in an education institution, or shop floor vs manager in a retail store. Technically they may be different types of 'Requesters' however your organizational processes may differ between these personas and you want to ensure that Now Assist gets the rights answers to the right people.
3. Review your Knowledge Creation Process: Consider which users should be able to leverage the skill to generate new Knowledge using Now Assist. You could potentially expose this skill wider to help augment your existing Knowledge team and reduce the backlog instead of (or in addition to) just reporting knowledge gaps.
4. Consider External Knowledge Sources: If you have alternative sources of knowledge information, it's worth consider whether it will also be suitable to leverage this directly alongside your ServiceNow Knowledge bases via our External Content Connectors. These can also be explored further on the ServiceNow Store, noting there may be licensing considerations for these.
Conversational Catalog Support
If you are looking to allow your customers to request catalog items conversationally with your Virtual Agent, then it’s important to review and understand the supported variables for the conversational catalog skills. For the full list of supported conversational catalog options please refer to the following page: https://www.servicenow.com/docs/bundle/yokohama-servicenow-platform/page/product/service-catalog-man...
Once the Now Assist plugins have been activated in your instances, you can use the Conversational Catalog Overview Dashboard to see a comprehensive overview of which catalog items are conversational already, and for those that are not - a detailed explanation of what is required to make it conversational.
A good approach at this point may be to review the most commonly requested catalog items and target any remediation efforts here for some quick wins.
Victor Chen has also written a great article on this topic that you can find here, plus an AI Academy session that you can watch here.
Incident/Case Data Quality
Incident and Case Summarization is available on records where there is more than 50 words (Washington Patch 3+) however you probably wont have much need to use it on those kinds of records as you’ll probably be able to read it by the time the summary comes back anyway. The previous limit was 200 words minimum (across all of the fields of the record being summarized) which is probably still a good guide. The real value here is on those complex cases where there are multiple updates in the activity log, status changes and re-assignments etc.
Once the incident/case is ready to be resolved, the Resolution Notes Generation skill will really help out in summarizing what happened and how it was resolved. This is where the importance of data quality comes in as it will be using the information in the record (and potentially related records) to create a summary. This information will be made available to other agents in future to help solve future issues. It will also be surfaced by other in-platform AI (such as the Task Intelligence similarity framework) and served up to agents working on similar issues. The vision here is also that Now Assist can help improve resolution note quality for helping resolve future issues.
AI Search and Tuning
AI Search is at the heart of Now Assist, as it is used to gather the data points to help Now Assist respond to user queries. AI search will be responsible for gathering the relevant information that is visible to the user and submitting it to Now Assist to generate its response (a process know as Retrieval Augmented Generation). If you are not using AI Search already, it is advisable to review this and activate it prior to attempting to implement Now Assist.
Once active, there are a number of tuning options that can be undertaken to ensure it is working optimally for your organization and to ensure it is looking at the right sources of information. It may be helpful to get familiar with the principles of AI search tuning to help positively influence the results provided by Now Assist. Result Improvement Rules are a good place to start with this too
For some great additional information in this area try these three great articles:
- Making AI Search Work: Practical Lessons from the Field
- Now Assist in AI Search - Nov 2024 release
- Now Assist in AI Search FAQ
Security and Data Handling
ServiceNow maintains detailed documentation around our security and data handling processes related to Now Assist and our Generative AI capabilities. Many customers have their own concerns around adopting AI solutions and naturally have questions about these kinds of things. ServiceNow aims to be as transparent as possible on these topics. Please refer to the following links for details:
AI Administrator role:
Consider who is the appropriate person in your organization to manage and own the Now Assist capabilities. Your system administrator may or may not be the right persona for this. Many of the Now Assist capabilities have new roles associated with them too, so there is some flexibility as to how you empower your teams to support these new capabilities. Additional to this, you may also want to think about which users/roles in your organization you want to allow to use particular skills such as Summarization or Knowledge Generation etc. You can see how to enable and configure the skills in the Now Assist Admin settings.
AI Data Steward role and the AI Control Tower:
This exciting new area was introduced recently as part of our Yokohama release and enable a new persona that can help shape the governance aspects of your company's adoption of AI. The AI Control Tower provides visibility of your deployed AI Assets and governance policies around how they are deployed, including an approval lifecycle for changes too. See the link for information on this area.
Instance Version:
Getting access to all of the latest and greatest Now Assist skills generally requires your instance to be on one of the most recent releases. Being on the cutting edge of this technology generally means staying on the latest release of the platform too, so to get the most value from this you will want to be on the latest release. Luckily ServiceNow makes it easier than ever to get your upgrades done faster and smoother with each release.
Instance Customization:
Lots of customers have different requirements and sometimes its necessary to tweak the out-of-box configuration to meet business requirements. If this is a path you have gone down then you may wonder how much impact this has on your ability to adopt Now Assist Generative AI capabilities. Let's say you decided to use a different field in your incident table, or added a different 'state' to your process. You may also want to check for any changes you may have made to the out-of-box UI Actions or the resolution workflow as these may affect the way you adopt the new Now Assist skills. This is the kind of thing to be aware of across each of the tables in the platform that will have the Now Assist capability added to it.
To cater for some of this, we released the ability to make a copy of certain out-of-box prompts and accommodate these kinds of changes (introduced in Washington DC release). The newly copied skill allows some basic tweaking of the inputs used and the role conditions that control when the skill can be used, plus the ability to add additional input sources (related tables or emails) if required.
For additional capabilities beyond basic configuration tweaks we also have the Now Assist Skill Kit available to allow greater freedom to create your own custom-built skills, or also to modify some of the out-of-box skills too. This area is a complete topic all of its own and there is yet another great article (Now Assist Skill Kit (NASK) FAQ) you can use to explore this area further. Eliza Orchard has also written a great article on the latest enhancements to Skill Kit worth checking out.
Transition to Now Assist for Virtual Agent:
As part of Now Assist, there is an new version of Virtual Agent included. This is an addition to the earlier NLU-based version of Virtual Agent that has been available for some years now. There are some considerations around this which you may want to take into account when preparing for Now Assist and Victor Chen has written a fantastic article Migrating NLU Topics to LLM detailing some reasons you may want to consider this transition, plus a comparison of the two technologies and a few limitations.
1. Compatibility: There is a 1:1 mapping between any ServiceNow Portal (i.e. the older /sp, or even the more modern Employee Center portal /esc) which means that you have a choice to make for each of them. Do you want to use an NLU-based Virtual Agent or a newer LLM-based Virtual Agent using Now Assist? If you are looking to transition from your current NLU-based VA, you may want to consider...
2. NLU Topic Migration: If you've spent a lot of time building your own topics and conversations for your VA NLU deployment, then typically you'll want to migrate these across to the new LLM framework. There is a Topic migration utility available to help with this.
3. Are you new to Virtual Agent?: If you haven't deployed Virtual Agent (NLU) at all so far, then you have a blank slate to start from, however if you already have an existing investment in NLU Virtual Agent then you may want to consider if/how/when you transition across. Obviously there will be some testing required to ensure that the experience for your end-users and agents is positive
4. Tracking the value from deflections: Value is an important consideration for any new investment decision and we are starting to see capabilities emerge that allow you to analyze and assess the associated value derived from the interactions with the Virtual Agent. I think this is an exciting space to watch for the future too 🙂
5. One or Many Assistants? Although you can only have one Virtual Agent per portal there may be a need to create multiple 'Assistants' (think of an assistant as a Virtual Agent profile which can be configured independently but still uses the same underlying LLM technology) which can be associated with different portals. In addition to giving each assistant access to different information sources they can also be associated with different 'topics' that you may have created - therefore you have some flexibility around how you deploy it for different audiences across different portals with different topics available to handle.
Hey, what about my developers and creators? Well, good news is there are a wide variety of capabilities that can help make these folks more productive. Check out the latest release notes for most up-to-date skills that your creators can leverage to get more done for you. Many of these skills are accelerators and may not necessarily require the same planning and consideration as the other areas prior to deployment - however it's well-worth considering which areas you might want to target first once these new super powers are enabled. A couple of additional articles you may want to dig deeper on in this area are also provided below.
1. Now Assist for Creator Welcome Guide
2. Usage Tips/Use Cases/Example Prompts for Now Assist for Code
3. Now Assist for Creator Product Hub area on the community. Check here for lots of other great content.
Whats this i hear about AI Agents?
Yep, this is a whole topic on its own to explore. Once you've nailed down the basics that we've covered here, then you can start thinking about deploying some AI Agents and leveraging agentic workflows. If you want to check our the latest in this space you can check out another great article by Victor about the latest enhancements to AI Agents in Yokohama Patch 3.
If you're interested to get started here, you may want to try and identify some relevant use-cases for your organization. There are a few approaches you can take to start on this journey including the following.
1. Explore the Out-of-box AI Agent Agentic workflows and see if there is anything there that resonates, or sound similar to what you need. This is a quick win and can be used as-is, or quickly cloned and then configured to suit your needs.
2. Use Process Mining in your instance to identify any areas where your processes are running sub-optimally and there is potential to address. @dangrady510 has written an excellent guide on doing this here for free by leveraging the Process Mining evaluation projects - including specific videos for how to do this in your Incident, Customer Case and HR Case records.
3. Exploring using the in-platform Predictive Intelligence similarity solutions for clustering against your task-based records to uncover groups of records that might uncover problem areas you can focus on.

So in summary, there are a lot of factors to consider when embarking on your Now Assist journey and some of the topics above are considerations you may choose to go deeper on in preparation for this. Below are some additional resources that may also be helpful to keep an eye on, or consider to continue the learning, plus some extra resources for our Impact customers too. I hope you find this useful.

Additional ServiceNow Resources:

Docs - Release Notes - All the latest Now Assist goodness released in Yokohama
ServiceNow Community – Now Assist & Generative AI Product Area
ServiceNow Expert Services – Put AI to Work with Now Assist
ServiceNow University - Now Learning Courses for Now Assist and AI Agents
Now Create – Now Assist Implementation Guides
ServiceNow Community – Getting Started with AI Search
ServiceNow Community – Knowledge Management User Group (with Video)

Impact Services:

Customers subscribed to ServiceNow’s Impact Offering can leverage a number of different Accelerators to help get ready for Now Assist and AI Agents. The following may be useful:
*Impact customers can view all available Impact Accelerators from this catalog:
https://www.servicenow.com/docs/bundle/yokohama-impact/page/product/impact/concept/accelerator-catal...

priyaradhakrish · ‎08-28-2024

Great article! Thanks Matt!

Yogesh Shinde · ‎01-06-2025

Great article! One of the key aspects is the adoption of Service Operations Workspace (SOW), as most of the Now Assist Skills are designed to be used through SOW rather than backend forms. Therefore, SOW and its related customizations are crucial to check during the pre-assessment or instance assessment before starting the Now Assist implementation.

Additionally, it's essential to properly implement and adopt AI Search and Virtual Agent. AI Search is the most critical and widely used functionality since it is accessible to all users, unlike Agent skills which are limited to agents. I plan to add field learnings to this article and encourage others to do the same. Now Assist is an excellent product!

AshishKM · ‎06-03-2025

This is great summary about preparation on Now Assist learning.

I landed on this page from "Now Assist ITSM" course's best practice section.