June Releases

June 24, 2026

Gladly Agent Deployment Experience Updates

Following last week's redesigned Gladly Agent deployment experience, this release adds two more improvements to the Gladly Agent Version and Entry Points pages:

View Gladly Agent profile version from Entry Points page – The version preview panel on the Entry Points page now includes a "View Agent profile version" link that opens the read-only Gladly Agent profile for the selected version. Previously, you had to navigate to the Versions page to access this view.
Banner when no Entry Points connected on the Versions page – When viewing a Gladly Agent's version history, a banner now appears if the Gladly Agent isn't connected to any Entry Points, with a direct link to connect one. Previously, the page showed an empty Published tab with no clear next step.

Outdated Workflow Versions Flagged via “In Use” Panel

The "In Use" panel in the Workflows editor turns red when an older version of the Workflow is being used in one or more places. Outdated references are highlighted inside the panel. This makes it easy to spot which Workflows have references that should be updated to the latest version and make the change in one click.

Search Rules by Condition and Action Content

Rule search now matches the contents of a Rule's conditions and actions – including matched phrases, Custom Attribute names, Channels, and the names of referenced Topics, Inboxes, Agents, business hours, and campaigns – in addition to the Rule name.

The Rules list accessible from Settings → Orchestration → Rules is enhanced with Trigger, Condition, and Action filters along with result counts on the Active and Inactive tabs.

Entry-page Context for Gladly AI for Helpdesks Handoffs

When Gladly AI hands off to an external helpdesk, an "Opened on" line at the top of the Conversation transcript shows a link to the page where the Customer started the Chat – giving Agents the entry-page context they previously only saw in Gladly.

Scroll Indicator for Answer Search Results

Answer search within the Answers Panel now shows a clickable chevron at the bottom of the results list when more Answers are available below the visible area, making it clear the list can be scrolled.

[Action Required] Contact Export, Contact Summary, and Work Sessions Reports: Older Versions Deprecated Soon

We've migrated the Contact Export, the Contact Summary, and Work Sessions reports to new infrastructure that makes them 2-3x faster!

As part of this migration, we will retire older versions of all three of these reports, with ContactExportReport and ContactExportReportV2 deprecated first, in 3 weeks. If your team currently uses either of these versions, please update your integrations to use ContactExportReportV3 to avoid any disruption.

The following Contact Summary and Work Sessions report versions will be deprecated on September 2, 2026:

ContactSummaryReport
WorkSessionEventsReport
WorkSessionEventsReportV2
WorkSessionEventsReportV3

Updated AI Performance: Opt-Out Phase Begins June 24

As shared in the June 9 release notes, Gladly is migrating all organizations to updated AI models to ensure Customers benefit from the latest advances in performance and accuracy. The opt-in testing window closes today, and the updated models become the default for all Gladly Agents. Here's what that means for you:

Already enabled the toggle – No action is needed. Your Gladly Agents will continue using the updated models.
Haven't changed the toggle – The toggle will default to on the next time you visit the Basics tile, meaning your Gladly Agents will begin using the updated models automatically.
Previously turned the toggle off – Your opt-out choice is preserved. Your Gladly Agents will remain on the current models until you re-enable the toggle or until July 1, when the updated models become the standard for all Gladly Agents and the toggle is removed.

If you haven't tested yet, we recommend reviewing your top Guides after the switch to confirm AI responses are aligned with your expectations. Reach out to Gladly Support with any questions or feedback.

Refreshed Main Navigation

We'll be updating the main navigation menu to make Gladly easier to navigate as it continues to grow.

The new menu organizes features into clear, intuitive categories – separating Gladly AI and Gladly Team into their own sections, and grouping items by what you do with them (Analyze, Manage, Test, Deploy) rather than a flat list.

A few things to keep in mind:

Admin Settings stay the same – Existing Settings menu and selections are not affected.
Consistent across all pages – The full navigation menu will appear everywhere in the product, not just on certain pages.
Permissions are unchanged – What you see will continue to depend on your role and access level.

Stay tuned for more details in the coming weeks.

Signals: AI Conversation Quality Evaluation

Signals is a new way to evaluate the quality of your AI Conversations at scale – no surveys, manual review, or third-party tools required. Write evaluation criteria in plain English, run them against hundreds of Conversations at once, and see pass/fail breakdowns with the ability to drill into any result for the full transcript and AI reasoning.

Signals gives you continuous visibility into how your AI is performing, at a scale no team could match manually. Define evaluation criteria around the things that matter most to your operation – sentiment, policy adherence, customer feedback on a new product change, or anything else you want to track.

Write your criteria in plain English, run them against hundreds of Conversations at once, and get qualitative insights with the ability to drill into any result for the full transcript and AI reasoning. Monitor every AI Conversation and uncover Customer insights, right in Gladly.

Want early access? Signals is currently in beta and will be available for free temporarily. If you'd like to try it and share your feedback, please contact Gladly Support to get started.

Voice Mode Coming to the Guide Tester

Soon you'll be able to test how your Voice AI sounds to a caller before they experience it – without picking up the phone.

Voice testing is coming directly to the Guide Tester. Instead of typing, click the microphone icon, speak naturally, and hear the AI respond out loud using the same speech recognition, spoken voice, and pronunciation settings as a real phone call. See exactly how your Guide performs in a real voice conversation – the response timing, the language, the tone, all of it.

It's a private test conversation that never reaches live Customers or affects your reporting, so you can validate how callers will be understood and how responses will sound before going live. The full transcript appears in the tester afterward for review. No phone number or IVR setup is required – just open the Guide Tester, select Voice as the Channel, and start talking.

Before this, validating Voice AI behavior meant placing actual phone calls. Now you can validate the full voice experience right inside Gladly, catch issues before they reach callers, and tune your setup with confidence. Stay tuned for availability details.

We're Bringing Mobile Support to Gladly!

We are excited to introduce mobile support for Gladly Team. Designed for Agents on the go or away from their desk, this update lets you view your Customer list, open Conversations, and take action directly from your phone.

Want early access? Mobile support is currently in beta. If you'd like to be among the first to try it and share your feedback, please contact Gladly Support to get started.

Search Will Soon Include Tasks

Universal search is expanding to include Tasks alongside Conversations and Customers. Agents will be able to search for Tasks by keyword, filter results by type, and open a Task directly from the search results.

Workflow Editor, Runtime, and Reviewer Fixes

Fixed – Workflow actions with boolean or numeric parameters could fail when a static value was entered in the editor. Static values are now converted to the correct type before the action runs.
Fixed – A Workflow that called a sub-workflow from inside a conditional branch would skip the steps that came after it once the sub-workflow finished. The Workflow now continues correctly after a sub-workflow returns.
Fixed – A Workflow triggered before a Handoff or within a specific Guide section, whose Stop step was set to "Go to Agent" would hand the Conversation off to a human instead of routing it to the specified Gladly Agent.
Fixed – A Workflow triggered before a handoff whose Stop step targets a Guide could crash on the first Customer message that triggers transfer detection. This no longer surfaces as a generic "unexpected error" handoff.
Fixed – Move Up / Move Down controls on a step nested inside an ‘Else If’ or ‘Else’ branch crashed the editor page. Reordering now works correctly.
Fixed – Customer replies to idle Workflow questions (such as CSAT surveys) were incorrectly handled as new questions instead of resuming the paused Workflow. Replies now route back to the Workflow that asked the question.

Team Managers Can Restore Gladly Agent Versions

Fixed – Team Managers received an error when trying to restore a previous version of a Gladly Agent. Restoring a version is now available to Team Managers in addition to Administrators, matching the permissions for deploying a version.

Long Names in Changelog Table No Longer Overflow

Fixed – Long names in the Changelog table could overflow their column and collide with adjacent rows. Names now wrap cleanly within the column.

Chat ID Column Resized in Chat Configuration List

Fixed – The Chat configuration list (Settings → Channels → Chat) now gives the Chat ID column more room so longer Chat IDs display in full instead of being cut off.

Guide Section Bullet Points No Longer Dropped

Fixed – Instructions entered as bullet points in a Guide section – most often when pasted from Word or Google Docs – could be dropped from what AI actually receives, causing AI to ignore that section's guidance. Guide sections saved from now on correctly include this text.

Guide Tester Inspect Panel Reliability

Fixed – The Guide Tester's inspect panel no longer closes unexpectedly after selecting a turn. The selected turn is now linkable and survives a page reload, and errors inside the panel are shown inline instead of navigating you away from the page.

EVENT

What's New. What's Next. What's Possible with Gladly.

Join us on Thursday, July 9 at 11 a.m. PT for a preview of the latest innovations from the Gladly Product and Engineering teams.

We'll cover recent releases, share what's coming next, and give you an early look at the features designed to help your team work smarter and serve customers better.

RESOURCE

AI Customer Service for Ecommerce: What it Is, How it Works & What 'Good' Looks Like

WISMO. Returns. Peak season spikes. Ecommerce support teams face a unique set of challenges — and not all AI is built to handle them.

This guide breaks down how AI customer service works in ecommerce, where most implementations fall short, and what "good" looks like when the goal is customer loyalty, not just ticket deflection.

REVIEWS

You're In Good Company

Love using Gladly? Share your experience on G2 Crowd to help others discover how Gladly empowers better customer connections.

REVIEWS

Using Gladly with your Shopify store?

Using Gladly with your Shopify store? We'd love your feedback there too! Leave us a review on the Shopify App Store and help other merchants discover how Gladly creates seamless, revenue-driving conversations.

RESOURCE

Gladly Referral Promotion

Love using Gladly? Now’s your chance to share the experience with others in your professional network. Submit your B2C or e-commerce referral to receive up to $2,000! Visit the Refer-A-Friend program to learn how.

June 17, 2026

Insights Agent

Get instant answers from your Gladly data with Insights Agent. Ask questions in plain English and get summaries, charts, or tables back in seconds. What used to take multiple reports and dashboard navigation is now a single question and a direct answer, giving your team a faster way to understand what's happening across your operation.

Insights Agent works with the data already in your Gladly reporting: Conversation volume, Contact metrics, team member performance, SLA, Topic trends, and Gladly AI session data. That means you can look across both your human team and your AI Agent performance in one place.

What you can do with it:

Get quick answers on AI resolution rates, handoff reasons, and recontact patterns without pulling separate reports.
Spot trends across Conversation volume, Channel mix, and team member performance in seconds.
Ask follow-up questions in the same session to dig deeper into what you're seeing.

A few example questions to try:

"What were our top 5 Contact Topics last month?"
"Show me Conversation volume for the last 30 days, broken down by Channel."
"Compare AI session resolution rate vs. recontact rate for the last 30 days."

Insights Agent is available at no cost during this preview period, with paid pricing expected later this fall. Reporting access in Gladly is required to use it. To get started, reach out to your SAM or contact Gladly Support and we'll get it enabled for your org.

Redesigned Gladly Agent Deployment Experience

The way Admins deploy Gladly Agents to live traffic has been redesigned with a clearer layout, simplified flow, and better visibility into what's live. Here's what's new:

Deployment status at a glance – The Gladly Agent page features a clear callout showing exactly where each Gladly Agent is deployed and on which version, so you always know what's live.
One-click publish to all Entry Points – A new shortcut lets you publish the latest version to all configured Entry Points at once. Especially helpful for Gladly Agents serving multiple Chat or Email endpoints.
Entry Point configuration made clearer – The Entry Points page is redesigned to make A/B testing configurations front and center and highlights when a deployed version is behind the latest available version.
Improved version history – The Versions page is Gladly Agent-specific and consistently displays the date a version was saved, a summary of changes, and which Entry Points it is published on. You can also view older versions in a read-only mode directly from this page.
New Changelog placement – The Changelog is moving to the main menu, simplifying the Gladly Agent view without losing any insight.

These updates replace the previous deploy action with a more intuitive flow. No changes are needed on your end, the new experience is available automatically.

Faster Contact Summary and Work Sessions Reports

Contact Summary and Work Sessions reports have been migrated to new infrastructure, making them 2–3x faster! These reports now contain data in a rolling 12-month window – for example, on June 17, 2026, data will go back to June 17, 2025. This covers the vast majority of reporting needs while delivering significantly improved load times.

Descriptive Step Previews in the Workflows Editor

Hovering a step reference in the Workflows editor shows a descriptive preview for If, Stop, Remember, and Recall steps (e.g., "Stop, go to guide, @Order Help" or "Remember 'order_status'") instead of just the step type. This makes it easier to identify which step a validation error or output reference is pointing to.

Answer Events Included in Audit Log

Answer added, updated, and deleted events now appear in the Audit Log alongside other configuration changes.

Multiple Topics Conditions in Rules

Rules include more than one Topics Condition. Combine multiple Topics rows – each with its own "Any of," "All of," or "None of" operator – to build more precise Rules. For example, you can now create a Rule that matches Conversations with any of [Refund, Exchange] and none of [VIP].

Public API for Inbox Agent Membership

Manage which Agents belong to an Inbox programmatically via the public API. A new POST /api/v1/inboxes/{inboxId}/agents endpoint adds and removes Agents in a single request without navigating through Gladly Team.

Infinite Scroll for Answer Search

Answer search results from the Answers Panel now load additional pages as you scroll, instead of stopping at the first 50.

Dark Mode for Gladly AI

We’re excited to extend Dark Mode to Gladly AI! Designed for those pulling long hours or late-night shifts, this feature reduces eye strain and helps maintain focus by providing a sleek, low-light experience across more of the Gladly platform.

Each user controls their own Dark Mode setting – click your Profile/Avatar in the top right corner and select the option to switch from Light mode to Dark. Your choice only affects your view.

Updated AI Performance

Gladly continuously evolves the underlying models that power our AI to ensure Customers benefit from the latest advances in performance and accuracy. As part of those efforts, we will be migrating all organizations to updated models over the coming weeks.

Starting this week, you can opt in early to begin testing against new models. Navigate to your Gladly Agents → Basics tile → Early Access section, and select Updated AI Performance. We recommend turning this on now to validate your AI set up ahead of the full rollout.

Here is the rollout timeline:

June 9–June 23 (Opt-In): Click "Updated AI Performance" on any Gladly Agent to begin testing the new models. This is optional – your current models remain the default during this window.
June 24 (Opt-Out): The updated models become the default for all Gladly Agents. If needed, you can still revert individual Gladly Agents using the toggle in the Basics tile.
July 1: The toggle will be removed and the updated models will be the standard for all Gladly Agents.

A few tips to get the most out of the transition:

Review your top Guides after enabling the update to confirm AI responses are aligned with your expectations.
Monitor handoff rates and resolution quality during the testing window to catch any differences early.
Reach out to Gladly Support with any questions or feedback.

Refreshed Main Navigation

We'll be updating the main navigation menu to make Gladly easier to navigate as it continues to grow.

A few things to keep in mind:

Admin Settings stay the same – Existing Settings menu and selections are not affected.
Consistent across all pages – The full navigation menu will appear everywhere in the product, not just on certain pages.
Permissions are unchanged – What you see will continue to depend on your role and access level.

Stay tuned for more details in the coming weeks.

[Action Required] Contact Export Report: Older Versions Deprecated in 4 Weeks

We've migrated the Contact Export report to new infrastructure that makes it 2-3x faster!

As part of this migration, we will retire older versions of this report – ContactExportReport and ContactExportReportV2 – in 4 weeks. If your team currently uses either of these versions, please update your integrations to use ContactExportReportV3 to avoid any disruption.

We're Bringing Mobile Support to Gladly!

Want early access? Mobile support is currently in beta. If you'd like to be among the first to try it and share your feedback, please contact Gladly Support to get started.

Search Will Soon Include Tasks

Test Your AI at Scale with Simulations

We’re getting ready to launch Simulations, a new way to validate AI configurations before it reaches Customers. Define Conversation scenarios in plain language, or let AI generate them for you, and run the entire suite with one click. Stay tuned!

Workflow Editor, Runtime, and Reviewer Fixes

Fixed – Pasting into a Use step's variable input was erasing existing text instead of inserting at the cursor. Copying with a selection now copies only the selected content.
Fixed – Workflows with a branch containing more than 20 conditions failed to save with a validation error.
Fixed – Output variables from a Workflow's Use steps now appear in the variable autocomplete when writing section rules. Previously, only Ask step variables were suggested.
Fixed – Before-handoff Workflows run consistently when a Customer is transferred to an Agent on their very first message. Previously, a first-message transfer could skip these Workflows entirely.
Fixed – Conversations handed off by a Workflow showed "Unknown" as the handoff reason in the Conversation Review panel. They now display "Workflow handed off."

Gladly AI Conversations Page Slow When Filtering by Guide

Fixed – The Gladly AI Conversations page was loading slowly or timing out when filtering by Guide.

Conditional Guide Instructions No Longer Flattened

Fixed – A Guide section's conditional instructions ("If X is successful… / If X is not successful…") could be collapsed into a single unconditional instruction sent to AI, causing it to ignore the condition. Conditional Rules are now handled correctly.

URLs in Chat Composer Auto-Link on Paste

Fixed – URLs pasted into the Chat Composer are now automatically converted to clickable links, so Agents no longer need to type a space after a URL to link it before sending.

Improved Stability on Voice Channel

Fixed – A call ending abnormally could restart the telephony streaming service and disconnect all other Voice AI calls on the same instance.

Automatic Topics Setup Validation

Fixed – On the Automatic Topics setup screen, the ‘Company name’ and ‘Company description’ fields show a character counter and a clear inline message when a value is empty or exceeds the 1,024-character limit. Previously, an over-long description failed with a generic error that didn't explain the problem.

EVENT

Product Roadmap Webinar

Join us on Thursday, July 9 at 11 a.m. PT for our quarterly Product Roadmap webinar.

You’ll hear the latest from the Gladly Product and Engineering teams, including what we’ve been building, recent product updates, and a sneak peek at what’s coming next.

RESOURCE

How Do You Know if Your AI is Actually Working?

Most AI teams obsess over deflection rate. How many conversations did the AI touch? How many stayed away from a human?

But when Gladly studied what retail's best AI deployments have in common, a different pattern emerged.

EVENT

Next Week! Get Customized Quince Items at CCW Las Vegas

Stop by Gladly Booth #1121 on June 24–25 for live demos, practical conversations about AI in CX, and a firsthand look at how leading brands are combining AI and human service in one continuous customer conversation.

Spend 30 minutes with our team and we'll send you home with customized customer items from Quince.

Book time with our team

REVIEWS

You're In Good Company

Love using Gladly? Share your experience on G2 Crowd to help others discover how Gladly empowers better customer connections.

REVIEWS

Using Gladly with your Shopify store?

RESOURCE

Gladly Referral Promotion

June 10, 2026

Workflow Editor Improvements

A batch of updates to the Workflow editor upgrade the way Workflows behave at runtime, and provides more capabilities to tackle a great number of use cases.

AI Judge condition in ‘If’ steps – The If step includes an AI Judge option. Combine it with standard checks (email, name, step output) in the same chain, letting AI evaluate criteria that don't fit a literal comparison while deterministic conditions handle the rest.
Bump all Workflows in use to latest version – The "In Use" panel includes a "Bump all to v{N}" action that updates any live Workflow onto the latest published version. Workflows already at the latest are skipped automatically.
Variables in ‘Add Note’ action – The Add Note action supports variables. Type $. in the note field to insert Workflow data, such as values captured earlier or Customer details, directly into a note.
Workflow version shown in Conversation Review panel – The Conversation Review panel displays which version of a Workflow ran next to the Workflow name (e.g., "Spam Routing v6"), so you can tell exactly which version produced the steps you're reviewing.
Variables in Apply Freeform Topics – The Apply Freeform Topics step can pull values from earlier steps using the variable picker instead of requiring manually typed text. You can also combine variables with static text in the same field.

Improved Guide Selection for Image Messages

Gladly AI's intent classification accounts for image attachments. Previously, an image sent with no text was treated as an empty message, and an image with a caption was classified on the caption alone. The classifier now recognizes when a Customer has attached an image, so it can route these Conversations to the appropriate Guide.

Delete Inactive and Draft Guides

Customers can delete Guides in Inactive and Draft states directly from the Gladly Agent. A confirmation is displayed before deletion. Active Guides must be deactivated before deleting.

Answer Count Visible by Audience

The number of Answers associated with each Audience displays next to the All Audiences filter on the Answers page, making it easier to see how content is distributed.

Active and Archived Tabs for Rules and Inboxes

The Rules and Inboxes settings pages now include Active and Archived tabs, making it easier to navigate between current and retired items.

New Workflow Dimensions in Gladly AI Sessions Reporting

Several new fields are available in Gladly AI Sessions reporting:

Workflow (Y/N) – Flags whether any Workflow ran on the session.
Workflow Message Sent (Y/N) – Flags whether a Workflow authored at least one outbound message to the Customer.
Workflow Outcomes – Comma-separated list of each Workflow that ran and how it completed (e.g., "Authentication: COMPLETED, Order Lookup: HANDED_OFF"). Possible outcomes include: COMPLETED, ENDED, HANDED_OFF, and FAILED.
Distinct Workflows Run – Count of distinct Workflows that ran in a given AI session, with companion measures for totals and averages.
Workflow AI Messages Sent – Count of outbound AI messages authored by a Workflow.

Favorited Answers Ranked First in Search

When searching in the Answers Panel, Answers marked as favorite now appear at the top of the results list instead of their normal relevance-based position.

Updated AI Performance

Here is the rollout timeline:

June 9–June 23 (Opt-In): Click "Updated AI Performance" on any Gladly Agent to begin testing the new models. This is optional – your current models remain the default during this window.
June 24 (Opt-Out): The updated models become the default for all Gladly Agents. If needed, you can still revert individual Gladly Agents using the toggle in the Basics tile.
July 1: The toggle will be removed and the updated models will be the standard for all Gladly Agents.

A few tips to get the most out of the transition:

Review your top Guides after enabling the update to confirm AI responses are aligned with your expectations.
Monitor handoff rates and resolution quality during the testing window to catch any differences early.
Reach out to Gladly Support with any questions or feedback.

Redesigned Gladly Agent Deployment Experience

Next week, we're rolling out an updated experience for how Admins deploy Gladly Agents to live traffic. The Gladly Agent home page, Entry Points page, and Versions and Changelog pages are all being refreshed with a clearer layout and a simplified deployment flow. Here's what to expect:

Deployment status at a glance – The Gladly Agent page will feature a clear callout showing exactly where each Gladly Agent is deployed and on which version, so you always know what's live.
One-click publish to all Entry Points – A new shortcut lets you publish the latest version to all configured Entry Points at once. This is especially helpful for Gladly Agents serving multiple Chat or Email endpoints.
Entry Point configuration made clearer – The Entry Points page is redesigned to make A/B testing configurations front and center and highlights when a deployed version is behind the latest available version.
Improved version history – The Versions page is now Gladly Agent-specific and consistently displays the date a version was saved, a summary of changes, and which Entry Points it is published on.
New Changelog placement – The Changelog is moving to the main menu, simplifying the the Gladly Agent view, without losing any insight.

These updates replace the previous deploy action with a more intuitive flow. No changes are needed on your end – the new experience will be available automatically. Stay tuned for full details, documentation and more in next week's release notes.

Free Gladly AI optimization – no cost, no SOW!

Want to make sure your Gladly AI setup is working as hard as it can for your team? We're offering complimentary AI configuration reviews with our team – available at no additional cost. Teams that complete it see resolution rates improve by 10% or more.

Each session includes:

AI setup review – Gladly Agent, Guides, Workflows and Public Answers tuning
Best practices – What's working across our customer base right now
Hands-on training – Ensure your team can confidently manage and iterate AI independently

To book your session, email gladly-optimization-team@gladly.com and include the OMS your organization is currently using. We'll follow up with next steps!

[Action Required] Contact Export Report: Older Versions Deprecated in 5 Weeks

If you missed last week's announcement, we've migrated the Contact Export report to new infrastructure that makes it 2-3x faster!

As part of this migration, we will retire older versions of this report – ContactExportReport and ContactExportReportV2 – in 5 weeks. If your team currently uses either of these versions, please update your integrations to use ContactExportReportV3 to avoid any disruption.

We're Bringing Mobile Support to Gladly!

Want early access? Mobile support is currently in beta. If you'd like to be among the first to try it and share your feedback, please contact Gladly Support to get started.

Search Will Soon Include Tasks

Insights Agent: Just Ask Gladly

We will soon be releasing the Insights Agent, so you can ask questions about your data and performance in plain English and get instant answers. No digging through reports or waiting on analysts, just ask AI and get the insights you need directly from your Gladly dashboards.

Test Your AI at Scale with Simulations

Copy Link Button in Tester Now Links to Conversation Review Panel

Fixed – The "copy link" icon on the testing page copied a link back to the same test Conversation. It now copies a link to the Conversation Review panel for that session, making it easy to share or revisit a test Conversation in context.

Duplicate Verification Prompt on Rapid Messages

Fixed – A Customer sending two messages in quick succession at the start of a Conversation could receive the same identity-verification prompt twice. The AI now asks once and waits for the reply.

Failed Nested Workflow Steps Shown as Separate Cards

Fixed – The Conversation Review panel displays failed ‘Remember’ and ‘Recall’ steps as their own cards when they fail. Previously, the failure was only visible on the parent step error message. Reviewers can now see exactly which nested step failed and why.

Quick Reply Messages Render Formatting Correctly

Fixed – Quick reply request messages in the Chat widget now render HTML tags and markdown formatting as intended.

Gladly Chat on Shopify Checkout

Fixed – The Gladly Chat widget was not appearing on the Shopify checkout page under certain conditions when added via the checkout editor.

RESOURCE

How ProClip USA Resolved 51% of Chats with AI and Maintained 99% CSAT

ProClip USA needed to improve response times without sacrificing customer experience. Within 90 days of launching Gladly, the team achieved 51% AI resolution, 99% CSAT, and cut response times from 13 hours to less than one.

See how they did it

EVENT

Get Customized Quince Items at CCW Las Vegas

Spend 30 minutes with our team and we'll send you home with customized customer items from Quince.

Book time with our team

REVIEWS

You're In Good Company

Love using Gladly? Share your experience on G2 Crowd to help others discover how Gladly empowers better customer connections.

REVIEWS

Using Gladly with your Shopify store?

RESOURCE

Gladly Referral Promotion

June 3, 2026

One-Time Password (OTP) Settings and Audit Log

A new One-Time Password page is available under Settings → Security and Compliance. Workflows can send a one-time code to a Customer's email or phone number to verify they control that address before taking action – such as looking up or canceling an order. A starter Workflow template (User address verification) is available to get up and running quickly.

The settings page lets Admins configure the sender brand name and email ‘From’ address. A built-in Audit Log tracks every send, delivery, and verification attempt by recipient.

Searchable Workflow Triggers with Version and Direct Links

Dropdowns in the "Before First Message" and "Before Handoff" sections of the Workflow Triggers tile now include a search box. Each listed Workflow displays its version, is searchable by name or description, and can be opened in a new tab via the link icon.

Reorderable ‘Else If’ Branches in Workflow Editor

Rearrange ‘Else If’ branches by using the "Move Up" and "Move Down" options within the editor instead of deleting and re-adding them in the desired order.

Workflow Step Cards in Conversation Review Show More Details

Workflow cards in the Inspect Summary surface more context for each step, making it easier for Admins to debug Workflow behavior and understand how AI decisions were made:

Failed Workflow steps consistently show a red error banner on the title row across all step types. Expanding the card reveals the underlying error message.
Recall steps show more detail about what was returned and whether the runtime fell back to a default value.
Ask steps display the initial Workflow prompt, the Agent's outgoing message, the Customer's reply, and the collected value on one expandable row – each labeled and truncated to a single line for quick scanning, with full detail one click away.
Use steps show the action name in a single collapsed row. Expanding reveals the raw input and output exactly as recorded, making it easier to debug what an action was called with and what it returned.
Stop steps now lead with the final action the Workflow took. For "Go to" handoffs, the target Gladly Agent name is a clickable link in the row title. The expanded view shows reasoning, any Guides the Workflow redirected to, or errors.

Updates to Shopify Compliance Redaction Requests

Compliance Admins have more visibility, more export options, and more control over how they manage redaction requests:

The daily digest email now shows when its counts were generated, the age of the oldest pending request, and the age range of pending requests per type – so Admins can distinguish a stalled backlog from a fresh queue without leaving the email.
Compliance Admins can export the full redaction requests list as a CSV from the Redaction Requests page. The export includes the full Shopify Customer ID and surrounding metadata (request type, status, shop domain, fulfilment info), and respects any filters applied on the page.
Compliance Admins can opt out of the daily pending redaction requests digest email by clicking the ‘Settings’ button within Security and Compliance → Redaction Requests and unchecking the email opt-in.

Audit Log Includes Agent Email and Name

Audit Log entries initiated by an Agent now display the Agent's email and name, making it easier to identify who made each configuration change without looking up the Agent ID separately.

View AI Conversation from the Conversation Timeline Summary

Admins and Managers can jump to the corresponding Gladly AI Conversation directly from the AI summary within the Conversation Timeline. Click the external link button on the summary card to open the Conversation Review panel for that AI response – no need to go through the overflow menu.

Granular Topic Requirements on Conversation Closure

Admins can now configure specific Topic requirements that must be applied before a Conversation can be closed. Some of these requirements might include:

Require a topic from one or more parent groups.
Require a minimum number of topics overall.
Require specific freeform topics to be filled in.

Topics can also be marked as "Category only" so they act as organizing groups in the hierarchy and are never applied to a Conversation directly. When closure is blocked, the Apply Topics tooltip tells the Agent exactly which group or Freeform Topic still needs to be addressed.

Mid-Conversation Guide Reclassifier Now Default Behavior

Gladly AI now reassesses which Guide to use after every Customer message – not just the first one. If the AI initially picks the wrong Guide, or a Customer shifts topics mid-Conversation, Gladly AI seamlessly moves to the correct Guide. This behavior is now active by default across all organizations with no configuration needed.

A few tips to get the most out of this feature:

Write clear Guide descriptions so the reclassifier can route accurately.
Minimize overlap between Guides.
Keep each Guide self-contained rather than redirecting to another.

Learn more about best practices for accurate Guide selection.

Export Rules Available via the Support Tool Portal

The Configuration Exports panel within the Self-Serve API Export Tool includes an Export Rules option that downloads your routing and automation Rules as a CSV.

Each rule includes its name, priority, trigger, conditions, and actions – with all IDs resolved to readable names (Topics, Agents, Inboxes, etc.) so the export is useful without cross-referencing.

Spam Detection Management Available in Email Settings

A new Spam Management tab is available under Settings → Email, giving Admins direct control over Gladly's built-in spam detector. If the detector is flagging legitimate Customer emails as spam, Admins can now deactivate it themselves instead of contacting Gladly Support.

When active, the detector identifies potential spam so it can be automatically closed by Rules and bypassed by Gladly AI. Learn more about spam management.

Additional Gladly AI Workflow Outcome Dimensions in Insight Builder

Two new Conversation Metrics dimensions are available in Insight Builder:

Gladly AI Workflow – Shows which Workflows ran during a Conversation and how each completed, formatted as "WorkflowName: outcome" and comma-separated when multiple Workflows ran.
Gladly AI Workflow Deployed – A Yes/No flag indicating whether any Workflow ran on the Conversation.

Controls Accessible During Incoming Notifications

Agents can now access the top-right header controls (Search, Notifications, Profile Menu) while an incoming Conversation notification is on screen. The Customer name in the notification banner also displays more completely.

[Action Required] Contact Export Report: Older Versions Deprecated in 6 Weeks

If you missed last week's announcement, we've migrated the Contact Export report to new infrastructure that makes it 2-3x faster!

As part of this migration, we will retire older versions of this report – ContactExportReport and ContactExportReportV2 – in 6 weeks. If your team currently uses either of these versions, please update your integrations to use ContactExportReportV3 to avoid any disruption.

We're Bringing Mobile Support to Gladly!

Want early access? Mobile support is currently in beta. If you'd like to be among the first to try it and share your feedback, please contact Gladly Support to get started.

Search Will Soon Include Tasks

Insights Agent: Just Ask Gladly

Test Your AI at Scale with Simulations

Chat Widget Accessibility Fixes

Fixed – The Chat widget did not place focus in the message input when opened. Focus now lands in the correct field automatically.
Fixed – Pressing Escape did not always close the Chat widget. Escape now reliably closes the widget in all scenarios.
Fixed – Keyboard focus could become stuck on the Chat launcher button. Interactive elements now have proper accessible labels and structure.

Workflow Recall and Remember Steps No Longer Cause Unexpected Handoffs

Fixed – Conversations could unexpectedly hand off to an Agent when a Gladly AI Workflow used a Recall or Remember step. These Conversations are now handled by AI as expected.

AI-Created Tasks Resolve Datetime Formatting Issue

Fixed – AI-created Tasks could fail to be created in certain circumstances due to datetime formatting issues.

Yotpo Data Pulls Handle Inconsistent Timestamps

Fixed – Yotpo loyalty, Customer, and reviews data pulls could intermittently fail due to inconsistent date formats returned by Yotpo. Date fields are now converted to a standard format to prevent these errors

RESOURCE

What Retail’s Best AI Deployments Have in Common

Most companies assume AI performance comes down to which platform they're running. Gladly analyzed top-performing retail AI deployments and found a different story. The biggest predictor of success wasn't the technology; it was what happened after launch. Read What retail's best AI deployments have in common to discover seven insights from real platform data.

Get the guide

EVENT

Say Hi at CCW Las Vegas!

Join Gladly at Booth #1121 during CCW Las Vegas on June 24–25 for live demos, practical conversations about AI in CX, and a firsthand look at how leading brands are combining AI and human service in one continuous customer conversation.

Book time with our team

REVIEWS

You're In Good Company

Love using Gladly? Share your experience on G2 Crowd to help others discover how Gladly empowers better customer connections.

REVIEWS

Using Gladly with your Shopify store?

RESOURCE

Gladly Referral Promotion

Documentation Index

June Releases

June 24, 2026

June 17, 2026

June 10, 2026

June 3, 2026