Build better products with our product team.
When I look through the edited articles, I want to know who was the last person who edited the article, so I can reach out to them if I have questions or it needs different updates. Being able to set a workflow in the system for edits would be great too. If I edit something and mark a status of “ready for review” it follows an approval process that I can build . (this goes along with my previous feature request).
Key DatesLimited Preview: July 2024 Preview: August 2024 What is itPrevent Copilot from assuming inputs where explicit answers are required Learn More:Developer docs on explicit questions
Key DatesPreview: August 2024 What is itExpands generative intent support to Queries & adds support for Smart Extraction. This is a Creator Studio triggering enhancement. FeaturesNegative Queries examples: Configure negative examples in Queries to prevent over-triggering & disambiguate similar use cases. Smart extraction support: Specify good examples for your slots to improve extraction.
What is itBring all your Creator Studio use cases (from the Classic architecture) to the new Copilot architecture as plugins. Key DatesLimited Preview: March 2024 Preview: August 2024 Current StateQueries & Events in Copilot are already in Preview! Paths in Copilot is in Limited Preview. Please use the experimental feature tab to enroll in the feature! We have finished implementing core capabilities and we are working on some ML enhancements before launching the capability to Preview. Key improvementsCopilot’s generative framework brings intelligent reasoning to your Creator Studio use cases. This means many out-of-the-box benefits (such as implicit slot filling, easy context switching & more). Check out our documentation for examples & details. Core CapabilitiesWe have finished implementing the core capabilities.Capability Name Status Release Date Paths - APIs, KBs & Free-text Solutions ✅ Supported Feb 2024 Paths - Free-input & multiple choice slots ✅ Supported Feb 2024 Paths - Date slots ✅ Supported April 2024 Paths - Markup support (free-text responses) ✅ Supported May 2024 Paths - Form actions ✅ Supported May 2024 Queries - API responses ✅ Supported Jan 2024 Queries - URL follow up actions ✅ Supported April 2024 Events - Event notifications ✅ Supported Jan 2024 Events - Event-triggered Paths ✅ Supported April 2024 Launch rules ✅ Supported Jan 2024 API logs ✅ Supported May 2024 Plugin ReliabilityAll plugins (especially multi-turn ones) have challenges when working with LLMs. LLMs may not correctly interpret how a plugin is supposed to be used. We want to ensure CREST plugins behave at least as well on NGCP (if not better). We’re evaluating & improving LLM behavior across a variety of LLM parameters to ensure this:Plugin selection: Does the plugin trigger when expected? Plugin re-selection: If a user replies to a plugin, does the Copilot stay focused? Slot filling: Are inputs extracted correctly? Question generation: When inputs are needed, is the Copilot clear (with help text as needed)? Inference confirmations: When inputs are assumed, is the user made aware? Action confirmations: Is the confirmation message clear before actions are executed? Response generation: Is the summary after actions are executed clear? Once we can guarantee a sufficient quality for LLM behavior with plugins, we will release the capability by default (as Preview). Related Roadmap CapabilitiesTo make it possible to control your plugins more reliably, we are introducing new developer controls. You can see those feature requests below. FAQQ. So when should I start rolling out Creator Studio in Copilot?A. You should start today (if you haven’t already)! We’ll continue to improve our LLM performance & build the above improvements over the next few months. Remember to enable the experimental feature flag for Paths in Copilot when you’re ready! Our team is excited to bring your Creator Studio plugins to Copilot. Please let us know what you think.
Key DatesLimited Preview: Jan 2024 Limited Preview: Aug 2024 Preview: Q3 2024 What is it Use a Queries plugin to resolve an entity needed and provide the object to a Path plugin FeaturesUse Queries to help complete Paths: Use a Queries plugin to resolve an entity needed and provide the object to a Path plugin Pass slots reliably: Pass data from your Query response to your Path actions. Enrollment in Limited PreviewEnroll in the feature through the “Experimental Features” tab in Creator Studio
Hi Team,I am really a big fan of MLS where it allow users to choose their own language in bot and then bot serve the form, KBA, send API messages in the respective language. Also we are so excited about message broker and relevant experience. At the same time I also concerned about one thing from ticket handling agent perspective. Here is the case, Consider I am an English speaking agent and one of the user added a comment to the ticket in their native language ex. French. The user comment is not translated on the SNOW end but added as is added by the user. Are we expecting agents to use any translator by their own, to understand the user description/comment? Is this expected? What happens if any agent don’t have access to any translator?cc: @andrew.mairena
Copilot now do not accept multi-line input as a supported data type from user when tried in Paths Workspace in Creator Studio.Please add the feature for Copilot to implement functionality of bot (Copilot) recognizing the new lines without passing it as whole one line and passes the message with ‘<br>’/’\n’ or any new line identifier wherever new line is necessary as payload to API for it to set user’s message successfully with new lines.
We are having challenges fulfilling customer request to display custom messages since Moveworks is unable to display interactive messages, in 2 scenarioswhen user has to be presented with an English Chat Option when outside business hours for Preferred Language Chat queue when No agent is available, need to present a custom message based on the preferred language
We would like to see a feature that allows our bot to ask for approval from a user’s manager’s manager if the requested approval has not seen any traction for x number of days. We sometimes see manager’s who are OOO especially around the summer months, or have managers who are not timely on approving requests, would be great if these would be escalated further. This could solve a lot of pto/vacation/leave situations for us.
We would love to have StafFlo External knowledge available to pull best practices. We just started using this company and would love to have any public knowledge available to all employees.
No rich text editor currently available to edit suggested articles => poor user experience for KB author No current integration with ServiceNow knowledge module for article editing => poor user experience for the KB author; extra time spent having to login and copy-paste suggested KB draft into SHARP No current integration with “Writing AI ready” Knowledge templates indicated by Moveworks and currently used to write articles that can be ingested by Ada => could result in publication of new articles that are not ingested “KB Updates” view should highlight (e.g. color coding) differences between existing KB and suggested KB by knowledge studio when these are opened side-by-side in 2 column view => to make clear for knowledge author what are the KB modifications suggested “Sources” indicated for KB update suggestion are not really individual sources, but different lines of text within a single INC with ingested Work Notes => this is misleading - knowledge author will interpret that an update suggestion comes from multiple tickets with related Work Notes. This skews perception of credibility of an update. Should be fixed so that 1 “source” stands for 1 ticket containing relevant hints for the respective KB update/creation suggestion. Knowledge Studio currently favors tickets with largest amount of Work Notes as a KB suggestion => for more accurate suggestions and information, the model should also consider ticket age (favor newer tickets over older ones), whether any major incident / problem ticket / P1-P2 ticket exists for the topic (might contain final resolution for a known major issue) … “KB Updates” currently only offers generic guidance on which KBs to update. For example, for a PKI Card KB Update suggestion, it displays a large number of existing KB articles without detailing which specific articles should the update be added in => model should be improved as to be more specific Information on knowledge gap areas per Coverage and Effectiveness used to be able in "Answers Insights" dashboard, now this has been significantly trimmed down within BPI. Can this type of dashboard or some metrics/info within be added to Knowledge Studio? Roles/Access management – need to clarify how this will align with our ServiceNow knowledge management roles => Granting Knowledge Studio access to every ServiceNow user with ITIL access is not something we want – some articles are restricted from view based on role. Also, before users are able to publish / edit articles, we require them to take specific trainings on the knowledge lifecycle and the KB editor tool. Additionally, we’d want them all to be trained in Knowledge Studio.
Currently, sources in Knowledge Studio are not visible, as demonstrated in the screenshot below. This functionality is critical for the effective use of KB updates.Reason for Request: Enhancing Credibility: Consistent visibility of sources ensures the reliability of KB updates. Knowledge authors depend on visible sources to validate the suggested changes, and reliable access to these sources supports accurate updates. Ensuring Complete Information: Reliable visibility of all relevant sources helps maintain the completeness of KB updates. Authors need access to every source to ensure updates are comprehensive and based on complete data. Improving Efficiency: Addressing this will enhance the efficiency and accuracy of the KB update process. Ensuring that all sources are consistently displayed will better support knowledge authors in making informed decisions.
Hello Team,Currently when there is any update on tickets where Category is Request and Subcategory is Change Request Below is the notification sentHello <user>, here's an update on this ticket. See below for updates:Please update the text and remove ticket and add Change request wording like belowHello <user>, here's an update on this Change Request. See below for updates:
Is it possible to get the Bot to attach recent conversation threads from the user prior to submitting the ticket when the ticket is raised via API? Currently, we have “the last two user utterances and the last two Copilot responses are shared with the agent at the start of the session” but this doesnt seem to accurately track conversation. I think it would be helpful if, when a new ticket is logged, the conversation the user had with the bot is included in the comments or description if it is relevant to the nature of their request
Hey team, Would like to improve the servicenow standard approval request notification being sent to users:Currently the notification comes without a way to tell the users what the approvals are for, it simply shows the Request ticket where the approval is necessary. In instances where a request would need multiple approvals the user will never know at what stage is the approval being asked for.Firstly, the notification shows the “requested by” at the top of the notification, which is pointless because the user who opened the request is always the bot so it will never be different, unless the users fill the request outside the bot then it would show who opened it. This would be better served by using the requested for value instead. In instances where multiple approvals are needed on a single request, we want to let the user know what the approval is about without changing the Request record, this could be done by utilizing the sysapproval_approver short description of the approval record, which would describe what the approval is about for each approval request We need to be able to let users know not only from which request the approval is necessary for, but also letting them know what the approval is about. In approval record in Servicenow, theres short description which could be used for this (sysapproval_approver table)
We are implementing HR on top of the IT domain that we already have up and running for a while. Domains are pre-set by MW for all clients and do not map to our department allocation, or the “scope” that each one of our internal teams cover. That makes it hard to get an accurate picture of the real adoption that we are getting for the new domain we are launching without reviewing the detailed interactions. It would be good to be able to influence the way domains are segmented by for example tagging what sources that are ingested by MW belong to each domain.
Copilot insights does not give any option to further filter into the "Knowledge Base" option (picture below) for domain specific metrics (e.g., Procurement).For Aug'24 month metrics, I will need the count of FAQ responses showing article titled "FAQ - Global Procurement" articles and corresponding "Skill Result" count. Could you please update the Copilot Insights dashboard by end of Aug’24 to include -Option to filter the FAQ responses by Article title (for e.g., Article title = “FAQ - Global Procurement”) and Skill Result (Resolved by Skill/ Engaged in Bot etc.) After typing the keyword in the Article title search box, ensure there is option to select ALL items from the dropdown shown. Otherwise, I need to manually select each item from the dropdown (~200 items) to filter these items with the keyword. Option to download the excel file of above data
Kairos is not one of MW current configured web crawlers for external sources. We were told that adding new sources is not currently supported and a product idea has to be submitted in the Moveworks Community for consideration.
Already have an account? Login
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.