Release Date: 06/09/2026: 

CX Manager

• Improved the load time of Views that are filtered by a source of chat
• Allowed the same field to be used more than once as a filter in Reports (e.g. setting two date filters for before and after)
• Updated the message on the Resolution modal for when a survey was already sent on a case to make it less confusing
• Fixed a bug where HTML would sometimes show in the case card in the case list in Inbox after a search
• Fixed a bug where tasks added to a Case and assigned to a Team were not showing in the My Team's Unassigned Tasks list view

Knowledge

Updated the styling (size, spacing) of body and H tag text in the Article Editor screen as well as the Article Preview screen for Libraries that don't have any custom CSS. The styles will now more closely match between the edit and preview states inside CXME

AI Agents

• Optimized AI Agent tool calls to be faster and more reliable
• Improved Copilot response quality by reducing the truncation of long article bodies and also stripping out excess HTML to reduce token usage
• Added a new waiting indicator in Copilot while the Agent is generating a response to a visibly show what it is doing across tool calls, knowledge search, generating responses, and more. 
• Improved the ranking order of Sources that are shown in copilot responses
• Made the source links in copilot responses clickable to open the source links in a new tab
• Added the ability to set monthly Spend Limits on AI usages across all use cases
• Turned all plain text URLs in agent responses into links in Copilot and Messenger
• Improved the load time of traces
• Revamped the trace details page to show the most important information at the top and hide a lot of the excess information that is not helpful for troubleshooting. This includes seeing the query and response as well as being able to load the full chat history for additional context

Admin & Settings

Added a Teams field to the Add User modal to make it easy to add a user to specific teams during the creation process

Release Date: 06/09/2026: 

This release focuses heavily on improving system stability, fixing known bugs, and enhancing specific communication and knowledge base functionalities. Here are the key changes in this release.

CX Manager

Communications

• Improved Email Formatting: Outbound email templates can now be updated to have the signature appear directly under the latest message rather than at the bottom of the full thread. This can be done by updating the tokens in your email template. While we kept the current CHAT_EMAIL token as it is to limit disruption, we added EMAIL_LATEST and EMAIL_HISTORY to allow you to customize exactly how you want the last message the history to appear in the email body.
• Faster Chat View Performance: Fixed a bug that was causing Chat Case Views to load slower than other Views.
• Duplicate Case Prevention: Fixed an Exchange forwarding loop issue that was bypassing loop detection and creating duplicate cases when some inbound emails were received.

Cases

• Log Activity Alignment: Improved log activity consistency by aligning the "Reopened" issue log events between the user interface and the API.

Automations

• Automation Accuracy: Fixed a bug where the "Case Modified" automation trigger was incorrectly evaluating exact issue tag matches. When an Automation was triggered by Case Modified, any condition using Case: Issue Tag failed evaluation and returned false, even when the current tag value matched the configured comparison value. Now automations with those conditions will be properly executed.

Knowledge

• Knowledge Base Styling Updates: Enhancements to how articles are previewed and styled internally and externally to ensure a consistent appearance. This will only be updated for Libraries that are using the default Modern theme without any customization.
• Search Improvements: Resolved an issue causing high latency and errors within the production search index, resulting in a more reliable search experience.

Messenger (Web & SDK)

• Link UI Improvement - We updated messages shown in Messenger to automatically linkify links shared in plain text. 

Forms

We have released over 20 updates to our new Forms product and we'll post a separate release note on those updates shortly.

You can now pre-populate fields on Forms within Journeys using data from the Case related to that Journey or from previous actions on the Journey. 

This enhancement is designed to save you time by reducing the need for repetitive copy and pasting when completing Forms within a Journey. It also allows internal teams or customers to easily validate existing data during the life of a journey. 

To pre-populate form data on a journey, navigate to the Journey Builder and open your journey. Select a Form Action and on the right side editor panel you will see the form fields with the ability to pre-populate the field with data from the related Case or from previous actions within the same journey.

Once saved and published, the next time you access that form on the journey from the journey timeline, the fields will be pre-populated with your selected data.

We have been hard at work updating all the workflows in the new CXME UI over the past few months. While the application is in Beta we have not been posting release notes for each update, but we will start posting batches of small updates in addition to major new features that are released.

Here are the updates since the beginning of April 2026.

CX Manager

Shortcuts & Navigation

• Added Control + Shift + E to open the Edit All Case Fields Drawer (when Case Details is visible).
• Added Control + Shift + L to open the Change Location modal from a Case.
• Added Control + Shift + C to create a new case from anywhere in the application.
• Added auto-focus on the search/filter field for select and multi-select fields so you can type immediately upon clicking.
• When opening the Product Drawer from the Add Product button, it now auto-focuses on the search field and allows for keyboard arrow navigation.
• Added the ability to open old checklists/forms directly from the activity timeline in a modal.
• Set a default value of "Me" for the Return To field in the Waiting modal to reduce clicks.
• Set a default value for Waiting Time to "Tomorrow at 9am" to simplify date/time editing.

Case & Location Management

• Dynamic Case Cards: Added custom/dynamic case card fields (from Settings) to the small case list cards and case header (up to two fields).
• Added Add Contact and Add Product buttons to the Case Edit All Fields drawer.
• Added access to Embedded Apps from the Locations screen, including auto-population of customer info like MID for pre-filtering data.
• Added validation to prevent creating a View name that matches an existing system, shared, or personal view.
• Added Org avatars back to the Change Location modal and optimized it to remove the initial API call for faster searching.

Performance & Stability

• Optimized picklist field loading and Inbox components (views list, comm pubsub) to reduce memory usage and lagging.
• Updated field saving logic: If no changes are detected when clicking out, the system cancels instead of making an unnecessary API call.
• Improved the virtual scroller and added general memory usage reductions across the app.

Bug Fixes

• Fixed a bug where Case Exports failed with only one field; the system now appends Case ID automatically.
• Fixed checkbox selection issues when multi-selecting cases for a merge.
• Fixed a bug where unsubmitted notes would carry over when navigating to a new case.
• Fixed restricted Tags showing when the Category field was blank; they now only show for defined Categories.
• Fixed rendering issues for < and > characters and HTML artifacts in search results or resolution notes.
• Fixed UI issues where fields "bounced" on small screens or text was cut off on thin panels.
• Fixed the Owner User sort by adding "Unassigned" labels and consistent avatars.

Tasks

• Updated Task Views to load much faster using new search APIs.
• Updated Task Cards with a status button, allowing you to set the status directly from the card.
• Added back the My Team's Unassigned Task view and All Open Task view, both with significant performance improvements.

AI

Agent Capabilities

• Multimodal Context: Article Writer and Copilot agents can now understand and use uploaded images, files, and URLs as context for their answers.
• Task and Journey Integration: Added open task and journey data to case summaries when the tool is enabled on the Summary Agent.
• Added back Sources in Copilot responses for better transparency.
• Added the ability to copy/paste files directly into Copilot sessions.
• Fixed an issue preventing the Draft Article from Case agent from working for service provider organizations.

Article Writer Improvements

• Significant reduction in hallucinations; the agent now accurately adheres to the specific language of provided text, files, and images.
• Added Track Changes for Article Writer Copilot so users can review and accept/reject edits.
• Added a Draft Article button to Case Actions to instantly generate an article from case troubleshooting details.

AI Studio & Cost Management

• Updated the Workflow visualization in AI Studio with improved UI.
• Fixed an issue where the total cost was showing an incorrect value.
• Added the ability to save a monthly spend limit across all AI use cases.
• Updated guardrails to allow agents to answer questions about any content, images, or files provided in-session.
• Added a UI check to prevent deploying an agent without a model selected.
• Fixed a bug where agents couldn't be "Undeployed" quickly.
• Updated the Content Sources UI in AI Studio with clearer descriptions.

Communications

Email Composer

• Updated the composer to support nested lists (Tab to indent, Shift+Tab to un-indent).
• Added a Contact List popup in the To/CC fields for quick selection of contacts associated with the Case/Location.
• Enhanced table formatting when pasting from Word, Excel, Docs, or Sheets and removed excess borders on secondary tables (signatures).
• Properly rendered UTF-8 characters (e.g., arrows in pasted accordions) in the message display.

Fixes

• Fixed a display issue specifically for emails sent from certain 3rd party systems with custom css.
• Added the ability to attach files to Quick Replies in CXME.

Connectors

• Updated marketplace routing so it now defaults to the Configured Connectors tab instead of Available Connectors.

Settings

Layouts & Tables

• Fixed a bug where resetting card/table layouts wouldn't fully clear the template or would carry over previous fields.
• Fixed a bug preventing layouts from saving with 0 fields.
• Fixed a bug where searching "Available Fields" on layouts was non-functional.

Permissions & UI

• Updated the primary Settings icon to show for any user with "Manage Forms" permissions, enabling form data exports.
• Made section headers in General and Security sticky on scroll.
• Fixed a bug where the System Admin Role would occasionally show no permissions instead of all permissions.
• Added the Custom Email Domain field to appv4 Email Configuration.

Knowledge

General Updates

• Added an Owner field to Articles, allowing each article to have a designated owner.

Editor Improvements

• Updated Froala to v5.1 for improved stability and bug fixes.
• Fixed a bug where the AI assistant modal blocked Control + Shift + Arrow highlighting.
• Fixed a bug where AI "Actions on Highlight" blocked standard text editing.

Bug Fixes

• Fixed a bug where using Control + K recently viewed items failed to route to the new article.
• Fixed a bug where article layouts would break or fail to resize on small screens.
• Fixed an issue where editing a cloned article title/subtitle would sometimes be lost on save.
• Updated "Contains," "Empty," and "Not Empty" filters with icons to prevent text cutoff.

Release: May 7 2026

CX Manager

• Fixed a bug with the password reset flow in the new CXME UI so you can now reset your passwords from the new user interface

Journeys

• We added the ability to archive a Journey in the journey builder. Once archived, no new customers can go into that Journey and the journey will be hidden from the main journeys list, but can be found through a filter. A Journey can be unarchived and updated if needed.
• Fixed an issue where tasks would sometimes not get created when used in parallel steps in a journey
• Fixed an issue where the closeout action sometimes did not properly close out a journey
• Fixed an issue where the loading spinner on automation actions on the journey timeline would sometimes not go away

Forms

• Fixed a bug where multi-select picklists didn't show on Forms when opened on a Case
• Fixed an issue where signatures on Forms did not properly save on submission

Knowledge

• Fixed a bug where opening a file from the article preview screen would sometimes result in a 403 on first attempt
• Added an Owner field on Articles that allows you to define owners for each article for easier filtering and workflows

Connectors

• Added Embedded Apps to the Location screen in addition to the Case screen
• Added a Calendly embedded app (full release post and documentation to come soon)
• Fixed a sporadic sync issue with the jira connector
• Implemented caching on our non-api connectors
• Updated Zoho connector to allow creating docs and hardened core flows

Tasks

• Added In Progress and On Hold statuses to Tasks and you can now set the status of the task from the list or the case

Reporting & Dashboards

• We launched Journey and Task analytics to give you near real time dashboards for your Journey and Task data. This includes overall stats, detailed insights, and friction points to help optimize your workflows. We are rolling this out now so please let us know if you would like access to these dashboards.
• We added to ability to add Case and Location data to your Journey and Task dashboards to bring additional insights into the your data.

Security

• We updated our CSP policy for improved security

New Task statuses are now available.

To help you better track and manage your tasks, we have added new statuses: In Progress and On Hold. This will allow you to more easily track tasks that are actively being worked on compared to tasks that have not yet been started or those that are stuck.

For each task, you can now choose from the following statuses:

1. Not Started
2. In Progress
3. On Hold
4. Completed
5. Canceled

In addition to these new statuses, we have updated the task cards with split buttons. This feature still allows you to complete a task with a single click while also allowing you to quickly move any task to any status, streamlining your workflow.

Stay tuned for more updates, as we will soon be adding enhanced search and filtering capabilities for tasks. We hope these improvements make your task management experience even more efficient and effective.

We have launched a new feature in our email templates that will enhance your communication capabilities. 

Previously, you could only use standard fields from the related case and location within outbound emails. Now, you can add custom fields from your case and location records in addition to standard fields.

This new feature allows you to create more dynamic and robust outbound emails tailored to your needs. For example,

• You could include a username from a custom field on the location in the welcome email during onboarding.
• You could share a dynamic login URL based on the product the customer purchased for a new product activation.
• You could share renewal dates or training scheduled dates in automated emails for richer communication.

You can find these new custom field tokens in the same token list where the current standard field tokens are in Settings > Email Templates (in the new CXME).

We hope that this enhancement improves your ability to communicate effectively and efficiently with your customers and look forward to seeing how you utilize this new feature to enhance your email communications.

Our Copilot and Article Writer AI Agents can now understand files and links provided to them as part of the context data. 

This means you can upload files or copy and paste them into the composer, and when the AI Agent processes your question or request, it will also review any images or files that you provide. That data from these additional content sources data will be added to the context of the session. Additionally, if you provide a URL, the agent will automatically review the content on that URL (if it is public) and use that data as part of its context as well.

This new capability allows you to do more with our AI Agents. A few examples include:

1. Give an agent an image of an system error, and the agent can use that error to search your knowledge base for the answer.
2. Include a PDF of a customer contract and ask the agent to review the contract for specific terms. 
3. Give an a URL of an external knowledge base article, and the agent can gather all the information and use that to answer your question.

We hope this enhancement will make your experience with our AI Agents even more powerful and efficient. We look forward to seeing how you use this new feature to streamline your tasks and improve your workflow.

Release Date: 04/21/24: 

CX Manager

• Added the ability to use custom fields in Email Templates. Previously only standard fields were available.
• Fixed a bug where the Email from Chat Room email template was not respecting the filters for Owner Team on a Case. It will now use the proper email template based on the Owner Team of the Case.
• Fixed an issue where cloned Cases from inbound emails to closed Cases were sometimes being assigned to the incorrect Owner Team.
• Fixed an issue with outbound emails sometimes not appearing in the message history. We will continue to harden this specific flow.
• Improved the loading time and process for email history on Cases.

Knowledge

• Migrated all Knowledge Libraries from the default theme to the modern theme for bug fixing, performance improvements, and design updates.
• Fixed a bug related to accessing internal articles for non content editors when the Article was restricted to certain Teams.

Journeys

• Fixed a bug where Tasks in multiple Parallel Steps would not all get properly created as the Journey progressed.
• Fixed a bug where Automation loading spinners on the Journey Timeline sometimes would not disappear when the automation completed.

Forms

• Fixed a bug where signatures were not properly saving and exporting on Form exports. 

APIs

• Updated API/v3 to allow cutomers/location/put and customers/user/put APIs to accept requests without customer_id when id is provided. This will help integrations where a Location moves to a new Customer and the original Customer ID is no longer valid.
• Added SAML SSO integrations for the new CXME application along improved SSO configuration workflows.
• Reduced the latency when redirecting a login after successful SSO login
• Improved the resiliency of our eventing system.

Data

• Fixed an issue where email transcripts were not always being included in AI-generated Case Summaries.

Reporting & Dashboards

• We are in the process of launching our new Journey and Task analytics data and pre-built dashboards. We will be rolling these out over the comings weeks.

To move AI from a novelty to a core banking utility, you need more than a prompt - you need an operational foundation to help govern this intelligence at all times. That is why we built  OvationCXM’s AI Studio: the unified command center designed to create, configure, and continuously improve high-performance AI agents within a secure, governed framework.

By layering AI directly into structured, governed workflows, we ensure that every automated step is anchored in a real-world operational context, allowing work to move predictably across your entire ecosystem. Without a central point of control, AI risks becoming another siloed application that increases operational complexity rather than reducing it - a significant risk in a high-stakes, regulated environment.

OvationCXM’s AI Studio provides the transparency needed to audit AI logic, the laboratory to safely test new models, prompts and rules in a sandbox, and the governance to ensure every digital assistant remains a compliant, audited extension of your institution’s policies.  

In this post, we discuss how we take an AI agent from a concept to a high-performing operational asset in four distinct phases. 

Phase 1: Build

In OvationCXM’s AI Studio, an agent is not a generic chatbot; it is a specialized digital employee with a specific role, voice, and set of boundaries. The process begins by defining the Agent’s functional purpose from one of our four specialized types. For example, you might deploy a Summarizer agent to instantly distill years of fragmented email threads into a single, actionable case history, or OvationCXM’s internal-facing agent (copilot) to work alongside your staff, suggesting the next best step based on live orchestration data. For direct engagement, the external-facing conversational agent handles real-time customer inquiries, while the article writer/editor ensures your knowledge base stays current by drafting and refining baseline documentation based on successfully resolved cases.

Once the agent’s purpose is defined, it’s time to select the best model from a library of over 300 industry-leading models. This flexibility allows you to assign a high-reasoning model for complex analysis while using a faster, lightweight model for high-volume data routing. Crucially, you can approve a subset of models for your organization or even bring your own keys (BYOK), enabling you to use your own enterprise accounts with the model provider of your choice. 

To ensure consistency, you can also configure your global branding with information about your specific organization, including your brand voice and desired tone. By anchoring agents in these specific Global Branding configurations, you ensure that every agent speaks with the professional tone and consistency your brand demands, regardless of its function.

Phase 2: Execute

In this second phase, OvationCXM’s AI Studio bridges the gap between conversation and execution. In addition to the high-quality responses and content you receive from agents, they can also take direct action on your behalf through integrated workflows and tools. Because banking tasks are rarely linear, you define advanced workflows that guide the agent through multi-step scenarios - such as verifying a customer’s identity across three different systems before it ever suggests a journey change. 

When the agent needs to interact with your systems, it uses a set of deterministic tools, including secure API calls that allow the agent to perform key tasks. These tasks can include fetching a real-time account balance from a core system or updating a record in your CRM. By using these tools, the agent doesn't have to guess. Instead, it acts with precision, using the authenticated data already present in your ecosystem.

Phase 3: Observe

With OvationCXM’s AI Studio, every interaction is captured in a detailed trace, providing an auditable, step-by-step view of the agent's reasoning, the context used, and the final response. If a logic gap appears, you can see exactly where the agent diverged from the expected path.

This transparency is bolstered by a continuous feedback loop. Users can rate AI interactions, and any poor rating is routed to a review queue immediately. This allows your team to take immediate corrective action - whether that means adding a new rule, updating a knowledge article, or assigning a task to a human team member to step in. The point is that you aren't just watching the AI - you are managing it in real-time.

Phase 4: Improve

The final phase is about evolution without risk. In traditional software, you use unit tests to ensure code doesn't break; in AI Studio, you use Evaluations. First, you define your Data Sets based on questions and verified answers that the agent must handle correctly.

Before any change to a prompt or a rule goes live, you run an Experiment. AI Studio utilizes an LLM-as-a-Judge to automatically grade the agent’s new responses against your pre-defined criteria. This allows you to iterate and improve your agents with total confidence, knowing that your quality standards are being both met and proven before the AI ever interacts with a customer or a sensitive workflow.

The Bottom Line

AI Studio isn't just a builder - it’s a comprehensive governance layer that bridges the gap between modern intelligence and legacy core systems.  It provides the infrastructure to ensure that as your bank scales its capabilities, it does so with the observability, safety, and precision that the industry demands. By prioritizing structured orchestration first and on-demand intelligence, OvationCXM helps you transform AI from a speculative novelty into a permanent competitive advantage.

Interested in seeing a quick demo? Contact us today.