August Releases

August 26, 2026

Write More Targeted Workflows with Recipient Routing, Inbox Handoffs, and Date Variables

Three Workflow editor updates give authors more precision when building and maintaining Workflows.

Route by email recipient – Email ‘If’-conditions can match on the recipient (To) address the Customer wrote to, not just the sender or subject. This allows for routing by inbound alias – for example, sending mail addressed to a returns inbox down a different path – even when several addresses funnel into one mailbox.
Hand off to a specific Inbox – The "Handoff to human" ‘Stop’ step can send the Conversation to a specific Gladly Inbox instead of relying on a Topic-rule workaround. The selected Inbox is a default that Gladly Team routing rules still override.
Session start time and current date variables – Session start time and the current date and time are available as built-in variables.

Workflow Triggers Are Easier to Understand

The Workflow Triggers tile explains what each Trigger does and when it runs. Triggers have clearer names and short descriptions – "Before First Message" has been renamed to "On First Customer Message," and the Before Handoff tip links to the Route to Guide template. No change to how Workflows run.

Simpler Session Filtering When Creating Signal Scope

Choosing which Sessions a Signal evaluates is now a single choice: evaluate all AI Sessions (recommended) or narrow to a specific set. When you choose to narrow, the filtering experience has been redesigned:

Searchable Agent and Guide pickers – Find the Agent or Guide you need by typing instead of scrolling. Guides are grouped under the Agent they belong to, so same-named Guides are no longer ambiguous.
Removable tags – Every selection appears as a tag you can remove individually, so it's always clear what's included.
Comma-separated keywords – Enter multiple keywords in a single field, separated by commas.
Clear all filters at once – One control resets every filter, so you can start over without removing selections one by one.

Granular Permissions for the People Settings Section

Four new custom-role-assignable permissions – View Users, Manage Users, Manage Teams, and Manage Roles – let Admins build custom roles that grant user, team, or role administration independently, rather than all-or-nothing access to the People section.

Changelog Records Entry Point Changes

The Changelog tracks changes to Entry Points, including which Agent version an Entry Point serves, A/B tests between versions, and Entry Point deletions. Each entry names the Entry Point, what changed, and who made the change. Previously these changes left no record, so there was no way to answer who pinned a version or when an A/B test started.

Team Assist Feedback and Usage Report

A new report under Reports → Gladly AI gives Admins visibility into how Agents are using Team Assist and how helpful they're finding it. The report shows thumbs-up and thumbs-down feedback, the reasons Agents gave for negative ratings, and overall Team Assist usage. Results are available in-app and as a downloadable CSV.

User Role Summary Report

A new report under Reports → Gladly Team gives Admins and Team Managers monthly visibility into how Users are classified across User types. For each User, the report shows whether their activity that month classified them as a Support User, Task User, or Information User – making it easy to see how your team is using Gladly at a glance.

Agent Email, Agent ID, and Agent Team Now Available in Insight Builder

Three new dimensions – Agent Email, Agent ID, and Agent Team – are now available in Insight Builder. Add them to any new or existing custom report with no configuration required. They're also available to Insights Agent.

Conversation Metrics – Available for Assigned Agent and Initiator Agent, each at three points in the Conversation's life: when created, when closed, and current.
Contact Metrics – Available for Fulfilled by Agent and Agent when Ended.

Use these fields to break down performance by individual Agent, email, or team assignment alongside the metrics you already track.

Full Topic Visibility on Closed Conversations

Agents can now hover the Topics area of a closed Conversation to see all of its Topics, including freeform Topics and the full Topic hierarchy. Previously only the first one or two were visible, and freeform Topics were not included.

Team Assist Now Sees Conversation Topics and Note Authors

Team Assist can see the Topics applied to a Customer's Conversations and can tell you which Agent wrote a given Note, message, or Task. This gives Agents richer context when asking Team Assist about a Customer's history.

Five App Platform app integrations are now available, bringing store credit, returns, CRM, and subscription data into Gladly so Agents and Gladly AI can resolve more Conversations without switching tools.

Set up from Apps → Create Configuration, no developer support required.

Rise.ai – View a Customer's live store credit balance and transaction history from a dedicated Card on the Customer Profile. Agents can issue store credit and look up gift cards by code directly from the + menu.
Redo – Surface a Customer's recent returns, package-protection claims, and warranties with status, items, compensation, shipping details, and return-label links. Agents can look up returns by order number, generate a return-portal link, add comments, flag returns for review, and optionally update return statuses. Gladly AI can use Redo data in Guides.
HubSpot – Two read-only Cards bring CRM context to the Customer Profile: the Contact Card shows name, company, job title, lifecycle stage, lead status, and contact owner, while the Tickets Card lists recent support tickets with status, priority, and pipeline.
Refundid – A read-only integration that surfaces a Customer's Refundid returns – both Instant and Standard – with status, refund amounts, returned items, and shipment tracking. Agents can search by order number for returns that don't match the Customer's email and send a start-return link directly from the Card.
Skio (v4.2.0) – The upgraded integration adds a Subscriptions Card to the Customer Profile showing each subscription's status, next billing date, cadence, cycles completed, and the products on it. Gladly AI can look up, cancel, pause, or trigger an immediate shipment for a subscription during a Conversation.

To get started, configure an app via Settings → App Developer Tools → Apps.

[Action Required] Contact Summary and Work Sessions Reports: Older Versions Deprecated Next Week

We've migrated 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 these reports. The following Contact Summary and Work Sessions report versions will be deprecated next week, September 2, 2026:

ContactSummaryReport
WorkSessionEventsReport
WorkSessionEventsReportV2
WorkSessionEventsReportV3

If your team currently uses any of these versions, please update your integrations to use WorkSessionEventsReportV4 before September 2, 2026 to avoid any disruption.

Knowledge Sources: One Place to Manage Everything Gladly AI and Team Assist Knows

A new Knowledge Sources page is coming to the main navigation menu next week, giving Admins a single destination to view and manage the knowledge both Gladly AI and Team Assist draws from when answering Customer questions, or supporting Agents.

Today, connecting Gladly Answers and websites happens across different areas of the platform. The new page brings these together so you can see what knowledge sources are active, make updates, and identify gaps – no support involvement required.

CSAT Survey Template for Workflows

A new Workflows starter template will make it easy to collect Customer satisfaction scores on AI-resolved Conversations – no external survey integration required.

Ready to use out of the box – The template will build a complete end-of-Conversation survey that asks the Customer to rate the help they received, follows up for an optional comment, and records both for reporting.
Accurate survey reporting – The template includes start and finish marks so reports can show how many Customers were surveyed, how many responded, and how many dropped off.
No manual assembly – Previously, teams had to build each survey step by hand. The template handles the full flow automatically.

Interested in learning more? Reach out to your Account Manager or Gladly Support.

Brand Voice Configuration for Team Assist

Admins will soon be able to configure a brand voice for Customer-facing responses generated through Team Assist. Instead of Agents manually adjusting tone and style on every draft, Team Assist will apply your brand's voice automatically – so responses sound like your company from the first suggestion. This means less editing for Agents, more consistent Customer interactions, and a faster path from AI draft to sent reply.

Self-Serve Configuration for Customer Profile Cards in Gladly Team

An additional option in Admin Settings is coming to Gladly Team in the next few weeks, giving Admins direct control over a part of the Agent experience that previously required Gladly Support assistance.

Customer Profile card management – Add, remove, and reorder the cards that appear on the Customer Profile from Settings → Agent Experience → Customer Profile.
Changes take effect instantly across all Customer Profiles and only display cards on a profile when the Customer has a value for them.

App Platform cards can also be added from this page, removing another setup that previously required Support.

Signals: Evaluate AI Session Quality at Scale

Later this month, Signals will become available to all Gladly AI customers.

Define what matters – Write evaluation criteria in plain English around the things most important to your operation: sentiment, policy adherence, Customer feedback on a new product change, or anything else you want to track.
Run at scale – Evaluate hundreds of Sessions at once and see pass/fail breakdowns, giving you continuous visibility into how your AI is performing at a scale no team could match manually.
Drill into any result – Click into any evaluation result for the full transcript and AI reasoning behind the pass/fail decision.
Monitor and uncover insights – Track AI Sessions and surface Customer insights, directly within Gladly.

Signals is included with Gladly AI at no additional charge, subject to fair use limits.

[Early Access] Shopify Product Search for Gladly AI

AI can search your Shopify catalog directly so product questions get answered with up-to-date store data.

Real-time catalog data – Product cards with the real image, current price, working link, and true variant and inventory availability, pulled from Shopify on each request.
Semantic, typo-tolerant search – Customers can ask naturally ("Do you have this in size 8?") and Gladly AI matches them to the right products.
Custom fields included – Details that live only in your custom fields – care instructions, dimensions, ingredient lists – are surfaced to Gladly AI so it can answer questions web search can't.
Web search stays in its lane – Product questions use the Shopify catalog; policies, FAQs, and blog content still come through web search.

Shopify Product Search isn't a separate add-on – it gives Gladly AI a direct, real-time connection to your Shopify catalog for product questions, alongside the web search and Answers it already uses. To test it early, reach out to Gladly Support to get started.

Workflows Templates No Longer Open with Validation Errors

Fixed – The ‘Chat onboarding’ and ‘Route to Guide’ templates no longer open with validation errors already showing. You're still asked to choose a destination for each routing step before saving.

Chat Onboarding Data Passed On After the First Message

Fixed – The email and name a Customer entered when starting a Chat were not passed along after their first message. Workflows that used the Chat onboarding email got no value, and the handoff summary did not show what the Customer had entered.

Human Agent Requests No Longer Missed in Multi-Message Contexts

Fixed – A Customer's request for a human Agent could be missed when it arrived alongside page-browsing context or was split across several quick messages. Gladly AI Agents now correctly recognize these requests and transfer the Conversation instead of continuing to reply.

Small Signal Runs No Longer Stall

Fixed – A Signal evaluation covering a small number of Sessions could fail to finish and show as stalled. These runs now complete normally.

Search No Longer Fails on Mismatched Custom Attribute Types

Fixed – Search no longer fails when a Customer custom attribute's type in the profile definition doesn't match how it was indexed. The mismatched attribute is skipped and the rest of the search returns normally.

RESOURCE

On-Demand: Gladly AI Workflows Classroom Session

Weren't able to join us live? The Gladly AI Workflows: Build with Confidence session is now available on demand. It covers everything from core building blocks to advanced logic – including key use cases, testing and troubleshooting tips, and how Workflows fit into your broader AI setup.

Whether you're building your first Workflow or refining what's already live, this is a great way to get up to speed.

WATCH THE RECORDING

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.

August 19, 2026

Agents Liveboard: Filter and Sort the Working Agents List

Admins can filter the Agents liveboard by Channel, Agent status, and Focus Time, and sort the Working Agents list by Agent status, number of assigned Conversations, and time in current status. This makes it easier to spot Agents who are at capacity, idle, or in Focus Time too long.

New Workflow Step: Extract Information the Customer Already Provided

Workflow authors can add an ‘Extract’ step that pulls a value the Customer already mentioned – like an order number stated earlier in the AI Session – instead of asking for it again. If the value can't be found, the step leaves it empty so a later step can decide whether to ask.

Signals: Criteria Descriptions and Adjustable Sampling Rate

Two updates give Signals creators more control over how runs are configured.

Set the percentage of matching Sessions evaluated in each run, from 5% up to 100%. Increase the rate for broader coverage or lower it to evaluate a smaller sample. New Signals default to 20%.
When two criteria share a name, the picker now shows each criterion's description so you can tell them apart before adding one.

Easier Navigation Between AI Sessions

Admins and Managers can move between AI Sessions directly from the Conversation Review panel using Previous and Next buttons in the footer, eliminating the need to return to the list page when reviewing multiple Sessions.

Self-Serve Agent Actions Configuration in Admin Settings

Admins can expose App Platform actions to Agents directly from Settings → Agent Experience → Agent Actions – no Support ticket needed. Select the app and the configured action to make it available in the + menu in Gladly Team, giving Admins full control over which actions Agents see.

Team Assist Settings Page Update

The Team Assist settings page surfaces a dedicated "View Agent Sessions" selection, making it easier for Admins to find and review the Sessions where Agents used Team Assist. Go to Settings → Team Assist → View Agent Sessions to monitor how your team is using the feature.

Gladly Team Now Available in German

The Gladly interface now supports German. Agents can select ‘Deutsch’ under Agent avatar → Profile → Language to switch their interface to German, including translated dates, times, and Conversation Timeline history. The setting applies only to the Agent who chooses it and persists across sessions.

New App Platform Integrations: Smile.io, Rivo, Recurly, and Nash

Four new App Platform integrations bring loyalty, subscription, and delivery data into Gladly so Agents and Gladly AI can answer common Customer questions without leaving the Conversation.

Smile.io – View a Customer's loyalty points, VIP status, rewards, referral info, and recent point activity from a dedicated Card on the Customer Profile. Agents can adjust points and purchase rewards directly from the + menu when the merchant enables those actions. Gladly AI can use Smile data in Guides to answer loyalty questions and perform merchant-approved operations.
Rivo – Surface a Customer's loyalty profile – points, store credit, VIP tier, referral details – and optional membership status, renewal date, and pricing. Agents can adjust points, update a VIP tier, or request a membership cancellation. Gladly AI can retrieve Rivo data and run approved actions through Guides.
Recurly – See every subscription a Customer has – plan, status, charges, add-ons, discounts, and upcoming changes – in the Customer Profile. Agents can cancel, resume, or reactivate subscriptions from the + menu with a dropdown filtered to only eligible subscriptions. All subscription actions are also available to Gladly AI.
Nash – Look up live last-mile delivery status by order reference, including courier, ETA, tracking link, and proof of delivery for completed orders. When a delivery fails, the result includes the failure reason so Agents can explain what happened. Nash tracking is available to both Agents and Gladly AI.

To get started, configure an app via Admin Settings → Developer Tools → Apps.

CSAT Survey Template for Workflows

A new Workflows starter template will make it easy to collect Customer satisfaction scores on AI-resolved Conversations – no external survey integration required.

Ready to use out of the box – The template will build a complete end-of-Conversation survey that asks the Customer to rate the help they received, follows up for an optional comment, and records both for reporting.
Accurate survey reporting – The template includes start and finish marks so reports can show how many Customers were surveyed, how many responded, and how many dropped off.
No manual assembly – Previously, teams had to build each survey step by hand. The template handles the full flow automatically.

Interested in learning more? Reach out to your Account Manager or Gladly Support.

Brand Voice Configuration for Team Assist

Granular Permissions for People Settings

Signals: Evaluate AI Session Quality at Scale

Later this month, Signals will become available to all Gladly AI customers.

Define what matters – Write evaluation criteria in plain English around the things most important to your operation: sentiment, policy adherence, Customer feedback on a new product change, or anything else you want to track.
Run at scale – Evaluate hundreds of Sessions at once and see pass/fail breakdowns, giving you continuous visibility into how your AI is performing at a scale no team could match manually.
Drill into any result – Click into any evaluation result for the full transcript and AI reasoning behind the pass/fail decision.
Monitor and uncover insights – Track AI Sessions and surface Customer insights, directly within Gladly.

Signals is included with Gladly AI at no additional charge, subject to fair use limits.

[Early Access] Shopify Product Search for Gladly AI

AI can search your Shopify catalog directly so product questions get answered with up-to-date store data.

Real-time catalog data – Product cards with the real image, current price, working link, and true variant and inventory availability, pulled from Shopify on each request.
Semantic, typo-tolerant search – Customers can ask naturally ("Do you have this in size 8?") and Gladly AI matches them to the right products.
Custom fields included – Details that live only in your custom fields – care instructions, dimensions, ingredient lists – are surfaced to Gladly AI so it can answer questions web search can't.
Web search stays in its lane – Product questions use the Shopify catalog; policies, FAQs, and blog content still come through web search.

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

We've migrated 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 these reports. The following Contact Summary and Work Sessions report versions will be deprecated on September 2, 2026:

ContactSummaryReport
WorkSessionEventsReport
WorkSessionEventsReportV2
WorkSessionEventsReportV3

If your team currently uses any of these versions, please update your integrations to use WorkSessionEventsReportV4 before September 2, 2026 to avoid any disruption.

Redaction Request Settings Show Hidden Items

Fixed – Hidden shops and email patterns saved in the Redaction Requests settings appeared empty when the modal was reopened. The modal now displays the saved configuration.

Workflows ‘Use’ Step Updates Preserve Existing Input Values

Fixed – Updating a ‘Use’ step to a newer version of the same action now keeps the input values you already entered. Only new or removed fields change.

Idle-Triggered Surveys Complete All Questions

Fixed – A Customer satisfaction survey (or any Workflow set to run after a Customer goes idle) would ask an initial question and then stop. If the Customer answered, the reply was treated as ordinary Conversation instead of a survey answer, so no follow-up questions were asked and the response was never recorded. Surveys now continue through all their questions and submit correctly.

Guides and Answer Performance Reports Include the Most Recent Day

Fixed – Guides Performance Detail and Answer Performance Detail reports include the most recent complete day. Previously, these reports could stop a day short each morning because the underlying data was cached before that day's load had finished.

Silent Voice AI Callers No Longer Stuck in an Empty Queue

Fixed – A caller who stayed silent during a Voice AI call could be placed into a non-Agent queue and left waiting indefinitely instead of the call ending normally.

Guide "Go to Section" Steps Land on the Correct Section

Fixed – A Guide step that sends the Conversation to another section could land on the Guide's starting section instead of the intended one, causing unexpected handoffs. These navigations now go to the correct section.

Help Center Search Accessible on iOS VoiceOver

Fixed – Customers using VoiceOver on iOS were unable to reliably open the on-screen keyboard when selecting the Help Center search box and had difficulty moving through search suggestions once they appeared.

RESOURCE

On-Demand: Gladly AI Workflows Classroom Session

Whether you're building your first Workflow or refining what's already live, this is a great way to get up to speed.

WATCH THE RECORDING

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

August 12, 2026

Collect CSAT Scores Directly through Gladly AI Workflows

A new Workflows template, “Import SimpleSat Survey,” collects Customer satisfaction scores through SimpleSat without having to build from scratch.

Pre-built, ready to customize – Import your SimpleSat survey as a complete Workflow in a few clicks. The template includes rating questions, follow-up prompts based on score, and response submission, all pre-wired.
Captures feedback at the right moment – Triggered when a Customer goes idle, the survey checks if they still need help before asking for a rating, so feedback collection feels natural and doesn't interrupt an active Conversation.
Routes based on sentiment – Positive ratings close the Session automatically. Lower ratings hand off to an Agent, so your team can follow up while the experience is fresh.

Filter Gladly AI Sessions by Date Range

The AI Sessions page has an optional date-range filter. Select a window of up to 30 days to narrow the list to Sessions updated in that period – especially helpful for high-volume organizations where it also speeds up page load.

Workflows Editor: New Built-In Variables and ‘Ask’ Step Labels

Two updates bring more flexibility and clarity to the Workflows editor:

New built-in variables – Workflows can now reference the Contact ID, Conversation ID, and Chat onboarding email as built-in variables.
Clearer ‘Ask’ step columns – The 'Ask’ step's choice columns now say "What the Customer sees" and "What gets saved" instead of "Label" and "Value," making it obvious to Workflow authors what displays where.

Gladly AI for Helpdesks: Cross-Link Conversations and Tickets

Two updates make it easier to move between Gladly and an external helpdesk:

Conversation-to-ticket linking – Conversations handled by Gladly AI now include a note with the helpdesk ticket the Conversation was handed off to, with a direct link. Find a Conversation from its ticket or a ticket from its Conversation.
Zendesk Conversation ID on handed-off tickets – Zendesk tickets created when Gladly AI hands off a Chat carry the Gladly Conversation ID, so a ticket can be traced back to the Conversation it came from.
- The ID appears in the AI summary on the Zendesk ticket, and can be written to a Zendesk custom ticket fields by setting the Gladly Conversation Field ID on the Sunshine Conversations V2 integration.

Self-Healing Responses is Standard Across Gladly Agents

Self-Healing Responses is default behavior across your AI configuration. When a proposed AI response fails a quality check, AI receives feedback from the failed check and regenerates the reply.

The new response runs through the full suite of quality checks again – if it passes, it's sent to the Customer; if it still fails, the Conversation hands off to an Agent. Your quality standards stay the same, but now more recoverable Conversations stay with AI.

Find Tasks Faster with Universal Search

Gladly Team Search now includes Tasks alongside Conversations and Customers. Agents can search for Tasks by keyword, filter results to show only Tasks (or only Conversations), and open a Task directly from the search results. No setup required – Task Search is available to all Agents automatically.

Self-Serve Configuration for Agent Actions and Customer Profile Cards in Gladly Team

Two new Admin Settings are coming to Gladly Team over the next few weeks, giving Admins direct control over parts of the Agent experience that previously required Gladly Support assistance.

Agent Actions in Admin Settings – Expose App Platform actions to Agents directly from Settings → Agent Experience → Agent Actions. Select the app and the configured action to make it available in the + menu in Gladly Team. Coming to UAT/Sandbox this week.
Customer Profile card management – Add, remove, and reorder the cards that appear on the Customer Profile from Settings → Agent Experience → Customer Profile. Coming to UAT/Sandbox soon.
- Changes take effect instantly across all Customer Profiles and only display cards on a profile when the Customer has a value for them.
- App Platform cards can also be added from this page, removing another setup that previously required Support.

Agent Actions will be available in UAT / Sandbox environments beginning this week. If your organization is interested in gaining access to Agent Actions early, please reach out to your Account Manager or Gladly Support.

Agents Liveboard: Filter and Sort the Working Agents List

Soon, Admins will be able to filter the Agents liveboard by Channel, Agent status, and Focus Time, and sort the Working Agents list by Agent status, number of assigned Conversations, and time in current status. This makes it easier to spot Agents who are at capacity, idle, or in Focus Time too long.

If you're interested in getting access to these filtering options early, reach out to your Account Manager or Gladly Support.

Signals: Evaluate AI Session Quality at Scale

Later this month, Signals will become available to all Gladly AI customers.

Define what matters – Write evaluation criteria in plain English around the things most important to your operation: sentiment, policy adherence, Customer feedback on a new product change, or anything else you want to track.
Run at scale – Evaluate hundreds of Sessions at once and see pass/fail breakdowns, giving you continuous visibility into how your AI is performing at a scale no team could match manually.
Drill into any result – Click into any evaluation result for the full transcript and AI reasoning behind the pass/fail decision.
Monitor and uncover insights – Track AI Sessions and surface Customer insights, directly within Gladly.

Signals is included with Gladly AI at no additional charge, subject to fair use limits.

[Early Access] Shopify Product Search for Gladly AI

AI can search your Shopify catalog directly so product questions get answered with up-to-date store data.

Real-time catalog data – Product cards with the real image, current price, working link, and true variant and inventory availability, pulled from Shopify on each request.
Semantic, typo-tolerant search – Customers can ask naturally ("Do you have this in size 8?") and Gladly AI matches them to the right products.
Custom fields included – Details that live only in your custom fields – care instructions, dimensions, ingredient lists – are surfaced to Gladly AI so it can answer questions web search can't.
Web search stays in its lane – Product questions use the Shopify catalog; policies, FAQs, and blog content still come through web search.

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

We've migrated 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 these reports. The following Contact Summary and Work Sessions report versions will be deprecated on September 2, 2026:

ContactSummaryReport
WorkSessionEventsReport
WorkSessionEventsReportV2
WorkSessionEventsReportV3

If your team currently uses any of these versions, please update your integrations to use WorkSessionEventsReportV4 before September 2, 2026 to avoid any disruption.

Action Run Logs Show Customer Lookup Details

Fixed – Custom action run logs now show which email or phone number was used to find the Customer, alongside a link to the matched Customer Profile. Previously the log showed only an internal ID, making it hard to tell how the Customer was looked up. Older runs are unaffected.

Conversation Review Panel Opens the Correct Item on Voice AI Sessions

Fixed – Clicking a Voice AI response could open the wrong turn in the Inspect Summary in cases where the Customer spoke over AI mid-response. Reviewers now land on exactly the item they clicked.

Empty Signals Criteria Labels No Longer Accepted

Fixed – Criteria labels made entirely of spaces are no longer accepted when saving. Previously they could be stored through the API and offered to the AI as empty options. The label count messages now spell the requirement out – at least two labels, up to five.

Signals Run List Updates Live

Fixed – The Signals run list now updates on its own while a run is in progress. Previously, an active run showed "Running" with no Session count until the page was reloaded, even after the run had finished.

Transfer Conditions No Longer Jump the Page

Fixed – The "When to get more help" tile editor no longer jumps back toward the top of the page when adding or editing a transfer condition in a long list. The view stays where you were, so you no longer have to scroll back down after every change.

AI Voice No Longer Reads Agent Name Aloud

Fixed – On Voice AI (phone) calls, the AI Agent's name was read aloud at the end of its spoken responses. Signatures are no longer appended on Voice AI replies. Written Channels like Chat, SMS, and Email are unaffected.

Full Email Address Search Returns Conversations

Fixed – Agents can now find a Customer's Conversations by searching their full email address. Previously, longer addresses returned the Customer but none of their Conversations, and Agents had to delete the last character to see results.

PRODUCT

Reminder: Team Assist Is Available Now

In case you missed it last week, Team Assist – an AI copilot built into the Agent workspace – is live and ready to try. Agents get instant Conversation context, knowledge-grounded answers, and AI-drafted replies they refine and send. It's a paid feature, available for free for a limited time.

Contact your Account Manager or Gladly Support to get started.

RESOURCE

Fortune: The Customer Conversations AI is Making Possible

Gladly chief marketing officer Ali Fazal explains why the AI tools built to avoid customer conversations are enabling the interactions brands could never afford before.

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

August 5, 2026

Sharper Tools for Workflow Authors

Three updates give Workflow authors more precision when building and maintaining Workflows:

Static opening messages on ‘Ask’ steps – Give an ‘Ask’ step a message that's sent to the Customer word-for-word with no AI rewriting. The Customer message and AI instructions are each optional, so authors write only the part they need.
Date and time controls on conditions – When a step output holds a date (e.g. order date), the condition editor automatically offers comparisons (e.g. ‘seconds/minutes/hours/days/weeks/months,’ ‘ago / from now’) so no custom conditions are needed. ‘Ask’ steps can also collect Date, Time, and Date + Time answers, and Customer replies like "two days ago" resolve to real dates.
Static badge on ‘Add Note’ steps – The ‘Add Note’ content field shows a "Static" badge confirming the note is added to the Conversation exactly as written, with variables filled in. This makes it clear the text is not reworded by AI.

Guide Rules Evaluation Card in Conversation Review Panel

When reviewing an AI Session, you can now clearly see how a Guide's rules were evaluated – each rule's condition, the actual value it checked, and whether it matched – instead of a raw data dump. This makes it easier to understand why the AI handed off or moved to the next step.

Hide Redaction Requests by Email Pattern

Compliance Admins can hide redaction requests by Customer email pattern (Settings → Security and Compliance → Redaction Requests), in addition to hiding by Shopify shop. Patterns support full domains (mail.gladly.com) or wildcard masks (bounce-*@mail.gladly.com). Hidden requests are filtered from the list, counts, and exports but are never deleted.

Zendesk Ticket Field Mapping for Handoff Data

Data that Gladly AI collects during a Chat can be written into Zendesk custom ticket fields when an AI Session is handed off. Agents see values like an order number in the ticket's fields instead of reading through the transcript.

Gladly AI Conversations Glance Report

A new report gives you a lightweight, at-a-glance view of every Conversation in a given period and the Gladly AI outcome for each one. Each row shows when the Conversation was created, when Gladly AI received it, the Channel, whether Gladly AI was involved, and the outcome – Assisted or Resolved. Conversations Gladly AI was not involved in are included with a blank outcome.

Available in the UI, as a CSV download, and via the reporting API, filterable by date range and Channel. Access the report from Reports → Gladly AI → Gladly AI Conversations Glance.

Team Assist: More Control Over Quick Responses

Quick responses show the full prompt – Click the lightning bolt icon on quick responses in the Team Assist panel to reveal the complete prompt sent on the Agent's behalf. This update makes it clear that the button label is shorthand for a longer instruction.
Always-visible quick responses – Admins can configure individual quick responses to remain visible throughout a Team Assist session, not just at the start. Enable this in quick response settings so Agents always have one-click access to prompts they use at any point in a Conversation.

Agent Desktop Language Selection

Agents can choose the language their Gladly Team interface is displayed in – English or Spanish – from their profile. The selection is saved to their account and applied automatically, including date and time formatting. To update the language display click the Agent avatar → Profile → Language.

Loop Returns App Platform Update

The Loop Returns App Platform app now supports same-product variant exchanges for merchants without exchange fees. Previously, Gladly AI could look up return status and generate return links – it can now walk a Customer through a full exchange within the Conversation.

End-to-end exchanges in Chat – Gladly AI can check return eligibility, present in-stock replacement variants (a different size or color of the same item), and submit the exchange – all without sending the Customer to the Loop portal.
Only in-stock options shown – The exchange variant catalog surfaces only variants that are actually available, so Customers aren't offered items that can't be fulfilled.
Balance detection before submission – Gladly AI checks the draft return's totals after finalizing – including any price difference or exchange handling fee – and can flag an uncovered balance before the return is submitted.

This update applies automatically to pre-existing apps. To install Loop Returns for the first time, configure the app via Admin Settings → Developer Tools → Apps.

Signals: Evaluate AI Session Quality at Scale

Later this month, Signals will become available to all Gladly AI customers.

Define what matters – Write evaluation criteria in plain English around the things most important to your operation: sentiment, policy adherence, Customer feedback on a new product change, or anything else you want to track.
Run at scale – Evaluate hundreds of Sessions at once and see pass/fail breakdowns, giving you continuous visibility into how your AI is performing at a scale no team could match manually.
Drill into any result – Click into any evaluation result for the full transcript and AI reasoning behind the pass/fail decision.
Monitor and uncover insights – Track AI Sessions and surface Customer insights, directly within Gladly.

Signals is included with Gladly AI at no additional charge, subject to fair use limits.

[Early Access] Shopify Product Search for Gladly AI

AI can search your Shopify catalog directly so product questions get answered with up-to-date store data.

Real-time catalog data – Product cards with the real image, current price, working link, and true variant and inventory availability, pulled from Shopify on each request.
Semantic, typo-tolerant search – Customers can ask naturally ("Do you have this in size 8?") and Gladly AI matches them to the right products.
Custom fields included – Details that live only in your custom fields – care instructions, dimensions, ingredient lists – are surfaced to Gladly AI so it can answer questions web search can't.
Web search stays in its lane – Product questions use the Shopify catalog; policies, FAQs, and blog content still come through web search.

Search Will Include Tasks

Universal search is expanding to include Tasks alongside Conversations and Customers. Agents can search for Tasks by keyword, filter results by type, and open a Task directly from the search results. If you're interested in getting set up with Task Search, reach out to your Account Manager or Gladly Support.

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

We've migrated 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 these reports. The following Contact Summary and Work Sessions report versions will be deprecated on September 2, 2026:

ContactSummaryReport
WorkSessionEventsReport
WorkSessionEventsReportV2
WorkSessionEventsReportV3

If your team currently uses any of these versions, please update your integrations to use WorkSessionEventsReportV4 before September 2, 2026 to avoid any disruption.

Guide Deactivation Blocked When Used Within a Workflow

Fixed – A Guide can no longer be deactivated while a Workflow still routes to it. You'll see a message naming the Workflows to update first. If a Workflow does reference an inactive Guide, the Conversation is now handed off to a human instead of running the inactive Guide.

Workflow Editor Validation Timing

Fixed – Creating a new step in the Workflow editor no longer shows validation errors while you're still setting it up. Errors now appear once you move to another step, collapse the step, or save – so you're not flagged for a step you haven't finished configuring.

Section Rules Properly Gate Content for AI Agents

Fixed – When a Guide Section line was gated by a rule, AI could fall back to the Section's general instructions instead of following the gated content. Gladly Agents now receive the correct portion of the Section when a rule triggers.

Post-Handoff Messages Stay in the Same Conversation

Fixed – A Customer who kept messaging after their Chat was handed off could have those messages handled as a new Conversation instead of being delivered to the Agent already working with them.

Handoff No Longer Fails on Non-Text Collected Data

Fixed – Handing off a Conversation could fail if Gladly AI was configured to collect a data point that was not text (for example, a number or a yes/no value). Those handoffs now reach the Agent normally.

Conversation Review Panel No Longer Errors on Long Links

Fixed – A Conversation could fail to open in the Conversation Review panel when one of its quality checks had flagged an unusually long link. These Conversations now open and display normally.

Screen-Reader Labels on Icon-Only Buttons

Fixed – Controls such as the copy and expand buttons on JSON output announce their action to screen readers instead of appearing as unlabelled buttons.

Signals Run Page Updates Live

Fixed – The Signals run page updates on its own while a run is in progress. Run status, the number of Sessions evaluated, and result charts fill in live, and final results appear automatically when the run finishes. Previously, the page showed a frozen snapshot until the browser was refreshed.

Topic Archiving No Longer Blocked by Removed People Match References

Fixed – A Conversation Topic could not be archived if a People Match rule had referenced it at some point in the past, even after the Topic had been removed from that rule. Only rules that still use the Topic now block archiving.

Improved Source-Language Detection for Translated Messages

Fixed – Messages written in one language but containing quoted replies or text in another language are now correctly identified by their actual content language, improving translation accuracy.

PRODUCT

Reminder: Team Assist Is Available Now

Contact your Account Manager or Gladly Support to get started.

PRODUCT

Gladly's New Navigation Is Live

If you haven't explored the redesigned main navigation yet, now's a great time. Features are organized into clear sections – Gladly AI and Gladly Team each have their own area, grouped by what you do with them.

Two things worth trying:

Pin your go-to pages – Admins and Team Managers can star any item to pin it to a new Starred section at the top of the navigation panel, so your most-used pages are always one click away.
Collapse and expand groups – Open the sections you use and close the ones you don't. Gladly remembers how you leave them.

Nothing changes with your capabilities, permissions, or subscription. Need a quick orientation? Our overview video breaks down what moved where.

EVENT

Classroom Session: Gladly AI Workflows – Build with Confidence

Ready to get more out of Workflows?! Join us on August 12, 2026 for a Classroom Session covering everything from core building blocks to advanced logic. Whether you're setting up your first Workflow or fine-tuning what's already live, this is your chance to dig in with our team, explore real use cases, and walk away ready to build.

RESOURCE

Fortune: The Customer Conversations AI is Making Possible

Gladly chief marketing officer Ali Fazal explains why the AI tools built to avoid customer conversations are enabling the interactions brands could never afford before.

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

August Releases

August 26, 2026

August 19, 2026

August 12, 2026

August 5, 2026