Skip to main content
This page tracks the most recent updates to Great Question. New releases are posted here regularly.
Stay in the loop: Click the RSS icon above to get new releases in a feed reader (like Feedly), or forward the feed into your team’s Slack or email.
Five more participant languages, tree test paths, and calendar invite warnings

Five more participant languages

Participants now see more of Great Question in your study’s language.
  • Five new languages. You can now set a study to Canadian French, European Portuguese, Hindi, Japanese, or Russian, for 15 languages in total.
  • More of the experience is translated. The unmoderated test player, booking, rescheduling and time-proposal pages, the scheduler, survey and consent errors, email merge fields and footers, and the reward redemption page now appear in the study language.
See Participant Experience Language. (Participant Experience)

New

  • Tree test response details now show each participant’s path taken: every node they opened, closed, and chose, with timing. You can see exactly where people went wrong. See Unmoderated tree testing. (Study Templates & Methods)
  • Booking details now warn you when a calendar invite failed to send or update, and say who needs to reconnect their calendar. The warning clears once the invite is fixed. See Scheduling tool. (Platform & Integrations)
  • Your AI agents can do more through MCP. They can create panel studies and their signup forms, read and edit an AI-moderated study’s flow, steps, and welcome screen, read its report, and share participant and preview links for any study. See MCP available tools. (Platform & Integrations)

Improved

  • Booking confirmations, reminders, and thank-you emails now send from the mailbox set on the study, so they’re no longer canceled when a teammate’s connection is missing. (Participant Experience)
  • Batched invite campaigns now re-check eligibility before each batch, so candidates who became ineligible mid-campaign aren’t invited. See Candidate eligibility settings. (Repository)
  • You can now bulk delete candidates using filters on Import name or Created by import, and large deletes run more reliably. See Candidates 101. (Repository)
  • In AI-moderated studies, the builder now asks before an edit or deletion changes what participants’ earlier answers mean. See AI-moderated interviews. (Study Templates & Methods)
  • Publishing a study whose link is already taken now tells you to change the link instead of showing a generic error. (Study Templates & Methods)
  • The time zone now shows while you edit or review a booked session’s start time. (Study Templates & Methods)
  • Tree tests show the tree-loaded prompt only on the first of consecutive tree tasks, and the builder now tells you that you can paste or import a tree. The thank-you page’s button now reads Finish. See Unmoderated tree testing. (Participant Experience)
  • Duplicating a block in an unmoderated study now places the copy directly below the original. The prototype success rate tooltip now explains how it’s calculated. See Unmoderated prototype tests. (Study Templates & Methods)
  • Settings > Transcription keyterms now suggests that a few well-chosen terms work better than a long list. See Transcript keyterm prompting. (Repository)
  • If your name is managed by your identity provider, your profile now explains why it’s locked and tells you to ask your IT admin. See SCIM. (Users Roles & Permissions)
  • Clicking Log in while signed in takes you to your dashboard. Signing in from a shared clip, reel, insight, or session link takes you back to that link. See Sharing Great Question artifacts. (Platform & Integrations)
  • Analytics stacked chart tooltips now show a total and hide zero values, and tiles have clearer copy and tooltips. See Analytics. (Platform & Integrations)

Fixed

  • Closing a card-funded study with unused recruitment credits now refunds card and prepaid amounts correctly. See Incentives FAQ. (Billing & Subscriptions)
  • Screener questions are no longer lost when two autosaves overlap. See Screeners. (Study Templates & Methods)
  • Recordings no longer show as unavailable when a session ended up with two video rooms. (Platform & Integrations)
  • Rescheduling a session while the bot is still in the previous call now sends a bot to the new time. See Interview rooms. (Platform & Integrations)
  • Changing a highlight’s start or end now re-cuts its clip and updates any reel that uses it. See Reels. (Repository)
  • Clearing a Respondent audience field, or choosing All, no longer blocks publishing the recruitment request. (Platform & Integrations)
  • Unticking the Reliable internet connection requirement on a landing page now saves. (Participant Experience)
  • A recording delete that fails now shows an error so you can retry, and a failed insight delete now shows an error. (Repository)
  • The unsubscribe confirmation no longer spins forever when the request fails. (Participant Experience)
  • Tag merge, new attribute, and consent form upload dialogs now reset correctly after you close or retry them. (Repository)
Emails and Pages on User Interviews studies, turning off Livestream after a session, and screener logic fixes

Emails and Pages on User Interviews studies

If you recruit through User Interviews and also invite participants of your own, you can now edit the emails and pages those participants receive.
  • Emails, Pages, and reminders are available again. A live User Interviews request no longer grays out the Emails and Pages tabs, the screener preview, or the landing page link for the whole study.
  • A note explains who gets what. Emails, Pages, Automation reminders, and the send dialog show that User Interviews participants don’t receive Great Question emails or pages, because User Interviews contacts them directly.
  • Editing is a deliberate choice. The edit button reads Edit for your own participants.
See External recruitment with User Interviews. (Participant Experience)

New

  • Clicking a locked control, such as New study or Invite teammate, now opens a Get access dialog in one click that explains the feature and sends the right request. (Users Roles & Permissions)
  • The column picker on participant, study, and Repository tables now has Select all. (Study Templates & Methods)
  • On the new Studies page, you can start a filter straight from a column’s menu, and the selected view’s tab shows how many studies it holds. See The Studies page. (Study Templates & Methods)

Improved

  • You can now turn off Livestream in the interview room after a session to upload your own recording, even if the stream still shows as active. It’s only blocked while the Observer Bot is recording, and it unlocks once the session is marked completed or an hour after its scheduled end. The Upload recording dialog tells you when. See Interview rooms. (Platform & Integrations)
  • Repository list columns keep the widths you set across reloads, and the Duration column now shows each recording’s length. See Research repository basics. (Repository)
  • Before you publish a focus group, the review page breaks down how many participants you’re inviting. See Focus groups. (Study Templates & Methods)
  • Reactivating an archived study that was never launched now returns it to Draft, so it goes through your normal approval and funding steps when you publish it. (Study Templates & Methods)

Fixed

  • Renaming an answer option in a screener no longer deletes its qualify, disqualify, or skip logic. See Screeners. (Participant Experience)
  • Participants can reschedule again after a study’s moderators change, and a reschedule confirmation left open from before a moderator change can no longer switch the booking back. (Participant Experience)
  • Upcoming Interviews shows the new livestream for a rescheduled interview, not the failed one, and livestreams no longer stay marked active after a call ends. (Platform & Integrations)
  • A study email you just saved no longer reopens as unsaved. (Participant Experience)
  • Mark as completed in bulk now skips participants who opted out or aren’t in a status you can complete from. (Study Templates & Methods)
  • The scheduler preview keeps working when calendar checks are briefly unavailable, and adding availability blocks no longer saves twice. See Scheduling tool. (Study Templates & Methods)
  • Qualtrics survey studies whose question list can’t be read now fail with a clear error instead of retrying. See Qualtrics integration. (Platform & Integrations)
Clearer candidate eligibility, required devices, and grouping on the Studies page

Clearer candidate eligibility

Eligibility now tells you why a candidate can’t be invited, in your own words, and when they’ll be eligible again.
  • Reasons use your rule labels. The Eligibility column, candidate profiles, filters, sorting, and CSV exports show the label you gave each rule. Hover a reason to see the rule’s title and description.
  • Completed participants stay eligible for their own study. On a study’s Completed tab, participants are no longer marked ineligible just because they completed that study. Rules about other studies still apply.
  • See when a candidate is eligible again. Hover a reason in any table to see when it ends, without crowding the row. Candidate profiles show one combined date for when the candidate is eligible again.
  • Simpler rules to set up. New Completed study count rules default to the last 90 days, and the older # of completed studies option is gone from the rule picker. Rules you already saved keep working as they are.
See Candidate eligibility settings. (Repository)

New

  • You can now require Desktop, Mobile, or Desktop and mobile for a study from the Welcome step. Participants on the wrong device see which one to use before they start, and mobile-only studies show a QR code. See AI-moderated interviews. (Participant Experience)
  • You can now group the new Studies page by a field from the Display menu, and select a whole group from its header to act on it at once. See The Studies page. (Study Templates & Methods)
  • Settings > Incentives now shows a funds and credits summary, with allocated, spent, and total funds alongside your recruitment credits, so you can reconcile your balance at a glance. See Incentives 101. (Billing & Subscriptions)
  • Deleting candidates now shows exactly what the delete removes, such as scheduled interviews and research history, before it runs. (Repository)
  • The public REST API now documents transcript endpoints, so you can list, search, and fetch session transcripts. See Great Question API. (Platform & Integrations)

Improved

  • On the new Studies page, you can filter text custom attributes by is any of and pick values already in use, and every text filter now offers does not contain. Both also work on candidates. See Filters. (Study Templates & Methods)
  • Views are easier to manage. You can make a built-in view your personal default, see a view’s description on its tab and in All views, see who created a shared view, and duplicate any shared view. Only a team view’s creator or an Admin can change it. See Saving views. (Study Templates & Methods)
  • The studies row menu now shows single-letter keyboard shortcuts, such as O for owner and T for team. See Row actions. (Study Templates & Methods)
  • Hover an incentive’s status in the Incentives table to see what it means. The incentive amount field also explains which currency to enter. See How to send incentives. (Billing & Subscriptions)
  • Workspace access now lives in Settings > Security, and incentive auto-complete now lives in Settings > Incentives. The old Permissions page links to each new home. (Users Roles & Permissions)
  • Opening a participant profile from a session now shows their messages, consent, and survey responses, the same as from the Participants tab. (Repository)
  • Session video now grows to fill the space when you collapse the side panel. Reel clips now carry their highlight’s title. See Reels. (Repository)
  • Ask AI now shows formatted tables with clickable citations, and Copy response keeps the table. See Ask AI. (AI Assistant)
  • The Show me how assistant launcher is back on every page. (AI Assistant)
  • Availability blocks now show their start and end times while you create or resize them. See Scheduling tool. (Study Templates & Methods)
  • Participants no longer see optional camera, mic, or screen share shown in red when off. Stopping a required screen share opens the reconnection prompt, and participants are told when an AI-moderated session can’t continue. They can also return to an embedded prototype with Try embedding again. (Participant Experience)
  • New Last invited date filters on candidate lists and study participant tables now start at Is more than and include candidates who’ve never been invited, so finding people you haven’t contacted recently takes one step. (Repository)
  • Teammates whose personal data is masked can now search candidates by part of a name or email. The study picker grays out studies you can’t edit and tells you why. (Users Roles & Permissions)
  • You can now create studies with no incentive through MCP. Each user can make up to 60 MCP requests per minute. See MCP available tools. (Platform & Integrations)

Fixed

  • Is all of filters on custom choice fields now match every selected value, not just the first. (Repository)
  • Emptying the participation limit on a published study no longer clears it. (Study Templates & Methods)
  • The Participants CSV export is back for closed studies, and its Livestream status column is no longer blank. (Study Templates & Methods)
  • Rescheduling a Microsoft Teams interview after its start time no longer fails. Moderators no longer get an extra observer invite for studies without observers. (Platform & Integrations)
  • Signing in with Google from a stale page now recovers instead of failing. (Platform & Integrations)
  • SSO users whose names showed as placeholder text now get a name from their email on their next sign-in. (Users Roles & Permissions)
  • Bulk invites no longer time out on large workspaces, and edits to a candidate bulk invite are kept when it sends. (Participant Experience)
  • LinkedIn URLs and platform IDs from external recruitment, emails entered as first names, and restricted names in calendar titles are now masked for teammates without access to personal data. (Users Roles & Permissions)
The new Studies page, how prototypes launch, and participants by interview time over MCP

The new Studies page

A new version of the Studies page is rolling out. It shows every study as a row in one table that you set up your way. Switching only changes the page for you, and you can go back to the classic page at any time.
  • Set up the table your way. Choose which columns appear, drag them into order, resize them, and freeze the ones you need to keep in view.
  • Save and share views. Save your filters, search, columns, and sort as a view. Keep it to yourself, share it with your workspace, or give a team its own shared view. Each view keeps your unsaved changes when you switch away.
  • Find studies faster. Combine filters across owners, people, participants, incentives, dates, and custom fields, and choose whether a study has to match all of them or any of them.
  • Act on many studies at once. Select studies and change their owner, team, or status, archive them, or delete them in one step. You can also change a single study’s owner or team from its Actions menu, and actions you can’t take appear grayed out with the reason.
To try it, go to Studies and click Try the new studies page next to the title. The new page is rolling out gradually, so if you don’t see the option, it isn’t on your account yet. See The Studies page. (Study Templates & Methods)

New

  • You can now choose Iframe or New tab beside a prototype URL. Use New tab for sites that break inside an embed. The preview, participant experience, and screen-share setup all follow your choice. See AI-moderated prototype testing. (Study Templates & Methods)
  • You can now use MCP to list and search participants across all your studies by interview time, so “Which interviews are booked today?” takes one call. See MCP available tools. (Platform & Integrations)
  • If you’re an Admin, you can now turn on MCP right from the consent page when you first connect an MCP client. See MCP setup. (Platform & Integrations)

Improved

  • When you accept a participant’s proposed time and it can’t be booked, you now see why, such as a calendar conflict or a booking limit, and can choose another time. See Reviewing a time proposal. (Study Templates & Methods)
  • A reel now shows Building your reel while its video is being made, so you don’t need to refresh. MCP also reports when a reel is ready and how long it runs. See Reels. (Repository)
  • Participants can now pause their mic, camera, or screen share instantly. If a required device is lost, the reconnection prompt opens at once and closes by itself when the device is back. See AI-moderated interviews. (Participant Experience)
  • If a recording stops mid-session because of a dropped connection, it now restarts automatically, so you don’t lose the rest of the session. (Participant Experience)
  • When a participant opens a prototype in a new tab from Help, they’re now asked to share their screen again, so the recording captures the prototype. (Participant Experience)
  • Participant, moderator, and observer calendar invites now have clearer titles and descriptions, with one link to the session page. (Platform & Integrations)
  • Select all Thanks and ad hoc sends now tell you how many participants were left out because they joined or completed after the page loaded. (Billing & Subscriptions)
  • The AI moderator now keeps the session going when study material it expects is missing, instead of offering to end it. See AI moderation. (AI Assistant)

Fixed

  • Sessions where the participant left before recording started now show No recording instead of “still processing.” Unmoderated sessions whose recording never arrives or can’t be played now say so instead of waiting indefinitely. (Repository)
  • AI-moderated transcripts no longer go missing when the transcription contains an unreadable word. (Repository)
  • Filter chips on the new Studies page now name people instead of showing IDs, and filters written by the AI filter appear in the filter row. (Study Templates & Methods)
  • Study exports now keep fractional hours for duration, and count surveys and unmoderated studies as fulfilled. (Study Templates & Methods)
  • Candidate CSV imports saved in Windows encodings now import names and emails correctly. See Importing candidates. (Repository)
  • The duplicate-candidate error in Add candidate is no longer cut off, and the link to the existing profile is visible. (Repository)
  • Moving many studies with lots of participants to another team no longer times out. (Users Roles & Permissions)
  • Short candidate emails and phone numbers are now masked for teammates without access to personal data, and screener answers are visible only to people who can see the candidate. (Users Roles & Permissions)
Change a session's moderator, filter candidates by import, and safer bulk sends

New

  • You can now hand one or more booked sessions to a teammate with Change moderator, from the Participants table or the session header. The picker shows who can moderate and explains why someone can’t. See Changing a session’s moderator. (Study Templates & Methods)
  • You can now filter candidates by Created by import. It matches only the candidates a CSV import created, not existing candidates it updated, so you can safely review an import. See Importing candidates. (Repository)

Improved

  • Bulk Thanks and ad hoc sends now show their progress and any failure on the Participants tab, without a reload. (Participant Experience)
  • Creating a custom attribute now tells you why it failed, such as a name that’s already taken or reserved. See Custom attributes. (Repository)
  • The panel Page title field now appears only when participants will see it. (Study Templates & Methods)

Fixed

  • Select all sends no longer cancel when a participant’s status changes while the page is open, so everyone still gets thanked and paid. (Billing & Subscriptions)
  • Booking pages no longer show no times, or times a moderator may not have free, when a moderator’s calendar is slow to respond. Scheduled invite batches wait until the calendar responds. (Participant Experience)
  • Accounts created with email sign-up now save your time zone, so digests and emails use your local time. (User Roles & Permissions)
  • The Change moderator modal now fits on a phone, and teammate search no longer zooms the page on iOS. (Platform & Integrations)
Build insights and reels with MCP, an interview guide tab, and clearer Observer Bot errors

New

  • Build insights and reels with MCP. You can now use MCP to create, update, and delete insights, with highlights and reels placed inline. You can also edit or delete reels, add reels and insights to a study, and tag up to 20 artifacts per call. See MCP available tools. (Repository)
  • Video call studies now have a read-only Interview guide tab next to Notes in the interview room, so your notes start blank. See Interview rooms. (Study Templates & Methods)
  • You can now use MCP to search the whole repository in one call, with sort, Added by, and date filters. You can also look up a tag by ID or name, list one interview’s highlights, and get a study’s participant status counts. See MCP available tools. (Repository)

Improved

  • MCP repository results now include links that open the item in Great Question. Transcript matches open the session at the quoted moment. Restricted candidates and personal data stay hidden in repository results. See MCP available tools. (Platform & Integrations)
  • Participants now confirm before turning off a device the study requires. The session pauses until the device is back on. See AI-moderated interviews. (Participant Experience)
  • When the Observer Bot can’t record, the interview room now names the likely cause and links to the fix. See Observer rooms. (Platform & Integrations)
  • Library > History now finds older questions, even on accounts with more than 200. (Study Templates & Methods)
  • The approval banner now says Study needs approval before a request exists, and names the approver once one does. (User Roles & Permissions)
  • The interview cancellation page now has a Back button and a red confirm button. The reschedule and canceled pages use clearer buttons and copy. (Participant Experience)

Fixed

  • Candidate and participant incentive filters now read values in dollars, not cents. (Billing & Subscriptions)
  • Duplicating a study now copies all of its landing page settings. (Study Templates & Methods)
  • A participant’s sign-up no longer replaces an existing candidate’s full name, and calendar event descriptions now stay up to date. (Participant Experience)
  • Transcript-only sessions and their highlights now stay searchable in the repository. (Repository)
GQ Assistant in the sidebar, a new Incentives settings page, and more MCP repository tools

New

  • GQ Assistant now lives in the sidebar. Open Resources and click GQ Assistant (between Templates and Help center) for in-platform guidance whenever you need it. (Platform & Integrations)
  • You can now target Respondent recruitment by city. Under Location, pick one or more countries, then search for cities within them. Respondent recruits within 250 km (155 miles) of each city. City targeting is available for remote studies. (Study Templates & Methods)
  • You can now manage incentive funding from one Incentives settings page. It shows your Transactions and Allocations ledgers, lets you deposit funds, create invoices, and set a low balance alert in place, and links to the permissions and approvals that govern funding. See Incentives 101. (Billing & Subscriptions)
  • You can now use MCP to create repository tags and add or remove a single tag on a highlight, reel, or insight without rewriting its other tags. See MCP available tools. (Platform & Integrations)
  • You can now use MCP to create, update, and delete repository highlights from an interview quote or time range, including on AI-moderated transcripts. You can also compile highlights into a new reel in the order you choose. See MCP available tools. (Repository)

Improved

  • The research assistant now picks up a dropped response where it left off instead of asking you to retry. It also refuses to save a study flow over edits you made in the app since it last read the study. (AI Assistant)
  • The research assistant now offers to hand you to support when you can’t act on its answer yourself, for example when a feature is off for your account. (AI Assistant)
  • When a participant interrupts a follow-up question, the AI moderator now answers them and then returns to the same question. See AI moderation. (AI Assistant)
  • If an approver is deactivated or loses admin, their pending approval requests now return to the owner, and other admins can clear them. (User Roles & Permissions)
  • When an invite can’t be accepted, Great Question now explains which sign-in method the workspace requires. (User Roles & Permissions)
  • The workspace picker now lists your current workspace first, then the rest by most recently used. (Platform & Integrations)
  • Teammates without an uploaded avatar now show their picture from Slack, Google, or Microsoft instead of initials. (Platform & Integrations)
  • User and sender pickers now search every teammate on large accounts, not just the first page. (User Roles & Permissions)
  • The incentive balance banner now counts unpaid incentive invoices of any age, so your available balance reflects everything still owed. (Billing & Subscriptions)
  • The publish step’s incentive funding message is now simpler for USD studies and only mentions exchange rates for other currencies. Incentive table headers and cells show tooltips for truncated content. (Billing & Subscriptions)
  • Concealed identity studies now warn you that livestream isn’t available before launch, instead of hiding the option. See Concealed identity studies. (Study Templates & Methods)
  • Choosing Great Question as the call location now explains its limitations right in the picker. (Study Templates & Methods)
  • Sending a screener to a study at its participant limit now shows a warning before you send. See Screeners. (Study Templates & Methods)
  • Screener conditional logic now colors Mark qualifying green and Mark disqualifying red, so you can tell them apart at a glance. (Study Templates & Methods)
  • External recruitment B2B targeting fields are now labeled as a Filter or a Preference, so you know which ones exclude non-matching participants. See External recruitment. (Study Templates & Methods)
  • Disabled study settings now show the reason as text, not only on hover. (User Roles & Permissions)
  • Scheduling emails now show whether a session falls in daylight or standard time. (Participant Experience)
  • Screeners, surveys, and unmoderated email tasks now explain when an email address contains accented or special characters, in all survey languages. (Participant Experience)
  • Candidate CSV exports now use your attribute labels as column headers. See Exporting candidates. (Platform & Integrations)
  • Truncated upload names and participant segment filter values now show in full on hover. (Repository)

Fixed

  • Unused external recruitment funds are now returned after cancellations and no-shows. Funding for open seats is now correct after you raise a study’s incentive. (Billing & Subscriptions)
  • You can send new invites again while a study’s batch invite campaign is running. The invite Send button is disabled when no selected candidate would receive an email. (Study Templates & Methods)
  • Participants must start a task before opening an off-tab prototype, and Chrome no longer blocks the prototype tab when the study panel opens. See Unmoderated prototype tests. (Participant Experience)
  • The unmoderated location question no longer shows an error on the first keystroke. (Participant Experience)
  • Clicking a transcript timestamp in the repository slide-out now seeks the video. Session summary chapters past the first hour now show hours. (Repository)
  • Hiding a column from the Candidates table header menu no longer resets your filters. (Platform & Integrations)
  • The survey template title no longer saves, with a “Template changed” toast, when nothing changed. (Study Templates & Methods)
  • External recruitment requests that can’t be saved now show the reason instead of “Please try again.” (Study Templates & Methods)
Moderator craft quality improvements, new MCP repository tools, and a redesigned device setup step

Moderator craft quality improvements

We’ve shipped a major round of improvements to how the AI moderator runs sessions, shaped by your feedback and measured against our evaluation set of interview scenarios. The moderator now:
  • Asks more neutral questions and probes for what’s still missing to meet each question’s goal, grounded in what the participant actually said
  • Handles skips and early exits more gracefully, helps participants who need support, and acknowledges substantial answers before moving on
  • Sounds more natural, with less filler and less AI-sounding language
  • Follows your study setup more closely, remembers earlier answers, and stays aware of the other questions in the study
  • Moves cleanly from the final question into the study close
It also no longer mistakes its own voice for the participant’s answer or cuts off its last words. In text-based AI-moderated surveys, the answer box stays focused as each new question appears. (AI Assistant)

New

  • You can now use MCP to look up repository tags by name, see every reel that uses a highlight, and read the highlights, clips, reels, and sessions embedded in an insight. Your AI tools can now follow research findings back to their evidence. See MCP available tools. (Platform & Integrations)

Improved

  • The device setup step is redesigned. Each device shows a live mic level, camera feed, or screen preview once it’s on. When the prototype runs inside the study, Chrome now offers only the study tab for screen sharing. (Participant Experience)
  • Participants can now use Reconnect mic during an unmoderated recording if their microphone disconnects, so you don’t lose their audio. (Participant Experience)
  • On AI-moderated studies, the Summary tab now always appears, listed last under Results, even before anyone completes a session. (AI Assistant)
  • Study-scoped Ask AI now finds short answers that follow a moderator’s question, so it quotes them instead of replying that no quote was found. (AI Assistant)
  • Observers can now join a livestream as soon as recording starts. If the connection drops, a Retry livestream button appears. (Platform & Integrations)
  • Figma prototype alerts now check the study owner’s Figma account and name it. Collaborators are asked to contact the owner instead of reconnecting their own account. (Study Templates & Methods)
  • The external recruitment toggle now explains when a study’s currency must be USD. Recruitment fees in the incentives table now always display in USD. (Billing & Subscriptions)
  • Removing a saved payment method now shows a confirmation message. (Billing & Subscriptions)
  • Consent forms now check email and phone formats and explain address errors clearly. Candidate and survey forms also reject email addresses with unrecognized domains, and location questions show translated error messages. (Participant Experience)
  • The image upload dialog now lists supported file types and the 10 MB limit, and rejects oversized files before uploading. (Study Templates & Methods)
  • If a study’s connected email sender stops working, the study owner now gets an email about it. (Platform & Integrations)
  • Candidates CSV exports now always include the candidate ID. (Platform & Integrations)

Fixed

  • Qualify, disqualify, and skip rules on screener questions save correctly again, including grouped rules sent through the API and MCP. (Study Templates & Methods)
  • Turning off screening now hides the Sent screener and Applied tabs and keeps your questions in case you turn it back on. (Study Templates & Methods)
  • The screener disqualification page preview now shows the real page content. (Participant Experience)
  • Participant links now open no matter which status tab the table is showing. (Study Templates & Methods)
  • Images in email templates now appear in previews and sent emails. (Participant Experience)
  • Unmoderated studies no longer show a mic reconnect message after the participant finishes. The picture-in-picture panel can be reopened after it’s closed. (Participant Experience)
A new Analytics board, images in interview templates, and a smarter AI moderator

New

  • The new Analytics board is rolling out to admins on Enterprise plans. It brings recruitment, panel, consumption, and usage reporting into six tabs with one shared filter bar, and every tab has its own address you can bookmark or share. Charts now show the date range and filters they cover, and Overview tiles explain when there’s no comparison to show. See Analytics. (Platform & Integrations)

Improved

  • You can now add images to interview templates, just like in a study’s interview guide. (Study Templates & Methods)
  • You can now launch a panel signup form with no questions, so it works as a simple opt-in and consent form. (Participant Experience)
  • The AI moderator now sees an outline of the whole study, so it wraps up naturally on the last step and avoids asking what a later question covers. It also keeps the prototype link on the tasks and questions inside a prototype test. (AI Assistant)
  • Session recordings now start when the participant moves past device setup, so recordings no longer open with minutes of setup. (Participant Experience)
  • Closing a study with external recruitment now runs in the background and shows its progress, with a clear message if it needs to be retried. (Study Templates & Methods)
  • The email field in profile settings is now read-only and explains how to request a change, instead of accepting edits that didn’t save. (User Roles & Permissions)
  • Dropdown menus now open toward the side with more room, so long menus in short windows stay usable. (Platform & Integrations)

Fixed

  • Transcript timestamps in downloads, the API, and MCP now display correctly past the one-hour mark and in half-hour time zones. (Repository)
  • Study steps now appear in the order you authored them, with questions inside a prototype test listed after it. (Study Templates & Methods)
Dutch and Chinese participant languages, and tags and highlights on AI-moderated studies

New

  • Dutch and Simplified/Traditional Chinese are now generally available in the participant language picker on every study that already supports multiple languages, alongside French, German, Spanish, and the rest. (Study Templates & Methods)

Improved

  • Team pickers on the Invite page and on Candidate contact access are now searchable and height-bounded, so accounts with many teams can find one without scrolling. (User Roles & Permissions)
  • User pickers across the app (moderator, observer, owner, sender, table filters) now return a full page of matches in a stable name order, and a truncated selected value reveals its full text on hover. (Platform & Integrations)
  • On study Attendees, the remove control on moderator and observer cards has been polished and now also appears next to “Already added” suggestions in the search results, so a teammate can be removed without scrolling to their card. (Study Templates & Methods)
  • Reporting board polish: sections without a customer-meaningful heading no longer draw one, unassigned studies are now labeled Workspace instead of Unassigned, and the Most viewed research table has a proper Unique views column with a set of clearer tooltips and titles across cards. (Repository)

Fixed

  • Rescoring an applicant now auto-qualifies them when they meet the qualification criteria, instead of leaving them stuck at their previous status. (Study Templates & Methods)
  • Email templates with unsupported formatting now recover in the editor by dropping only the unsupported marks, instead of loading as a blank editor. (Participant Experience)
  • Long study titles in the study picker on Shortlist and Participation invite now ellipsize instead of overflowing the closed combobox. (Study Templates & Methods)
  • Repository sorting by Name is now faster and returns consistent results. (Repository)
A four-state control for incentive automation, plus scheduling, transcript, and incentive fixes

A four-state control for incentive automation

The Incentive Automation control under Settings > Governance > Permissions is no longer an on/off toggle. It’s now one setting with four states, and each state names both who can use automatic session completion and what new studies default to:
  • Never: No study can complete sessions automatically. This is the only state that also stops studies already running.
  • Only admins can turn it on: New studies start with it off, and only Admins can turn it on. Studies already running are unaffected.
  • Off for new studies: New studies start with it off. Creators can turn it on.
  • On for new studies: New studies start with it on. Creators can turn it off.
Every state except Never applies to new studies only; no state rewrites the setting on an existing study. Restricting the permission no longer retroactively turns off automation on live studies or emails their owners. Choose Never if you want live studies to stop too, and switching away from Never restores each study’s own setting.The Enable Incentive automation row is removed from the Feature Access grid, so this setting is now the single place to govern automatic completion. The Never and Only admins can turn it on states require a plan with advanced permissions. See User Roles and Permissions.

A heads-up before your balance runs low

Topping up your incentive wallet now offers to set a low balance alert right in the confirmation, instead of requiring a separate trip to Manage wallet. If the balance had run down close to empty before the top-up, the confirmation calls that out and suggests a threshold; if you already have an alert set, it shows the amount and lets you change it right there.Only Admins can set the threshold, since they’re the ones who receive it; other roles see a note explaining why instead of a control that won’t save. See Incentives 101.

Improved

  • Repository can now be sorted by Name, in addition to Created, Updated, and Owner.
  • The Choose new time modal (including focus-group scheduling) now shows which timezone times are displayed in, using the same indicator as every other scheduling picker in the app. (Interviews Scheduling & Calendar)
  • Calendar Sync now replays scheduling changes that failed to push while a calendar connection was expired, once you reconnect, instead of leaving them stuck. (Interviews Scheduling & Calendar)
  • A bulleted list item in the study editor can now hold a heading, without losing either the heading or the list. (Study Templates & Methods)
  • API requests that fail with a 422 now return a reason instead of an empty body. (Integrations & API)

Fixed

  • AI-moderated transcripts: fixed timestamp ordering and speaker separation issues that could produce out-of-order captions or collapse a two-person conversation into a single speaker. (Repository)
  • Editing a candidate’s email to one already used by another candidate now shows a clear validation error instead of failing unexpectedly. (CRM Candidates & Attributes)
  • Admins can once again see CSV import history for the whole account, not just their own imports. (CRM Candidates & Attributes)
  • Candidate profile incentive totals now display correctly formatted in USD instead of raw cents. (Billing Subscriptions & Credits)
  • The team wallet label no longer appears on studies that aren’t actually using a team wallet. (Billing Subscriptions & Credits)
  • Incentive-only placeholder studies no longer appear on the Studies page. (Study Templates & Methods)
  • Fixed screener invite email preview text landing out of order when a button appears inside a bulleted list. (Studies Participants & Screeners)
  • The “Available highlights” count in the reel editor now matches the filtered list when filtering by tag. (Repository Search Tags & Highlights)
  • Video player controls no longer overlap on narrow screens; they now collapse into compact controls. (Repository)
  • Recording now starts once the first participant joins, instead of when the host joins alone, so the idle timeout no longer burns down before the interview begins. (Interviews Livestreams & Observer Rooms)
  • Great Question managed room bookings now wait for the room link before sending calendar invitations, so invitations no longer go out with a blank location. (Interviews Scheduling & Calendar)
  • Canceling edits to a study’s branding now correctly restores the previously saved branding. (Study Templates & Methods)
  • Fixed the CSV export success toast reappearing when reopening the export modal. (Studies Participants & Screeners)
  • Fixed mobile incentive redemption failing for some participants when redeeming a Tremendous reward. (Studies External Recruitment & Incentives)
  • The “external participants not thanked” alert no longer fires indefinitely on studies from years ago. (Studies External Recruitment & Incentives)
  • Fixed the Workspace name field’s label pointing at the Company name field instead of its own field. (Account Users & Roles)
Questions tab, highlight reels from chat, and study reports for everyone

Improved

  • Clicking a quote citation in a report now seeks the recording to the cited moment, in addition to scrolling the transcript, in both in-app and publicly shared reports. (Repository)
  • Long-running assistant searches no longer trigger a false “assistant stopped responding” notice while a tool is still working. (AI Assistant)

Fixed

  • Partial responses no longer appear in the study’s responses list, question aggregates, or response drawer, so the counts you see match the report’s analysis. (Repository)
  • When a participant asks to skip a question, the AI moderator now records a real skip instead of a placeholder answer, and past placeholder answers are treated as skips too. (Participant Experience)
  • If a required screen share stops mid-session, the session now pauses until the participant restores it, so recordings capture the screen throughout. (Participant Experience)
  • Session recordings no longer clip the moderator’s opening. The session waits until the recording is confirmed live before starting. (Participant Experience)
  • Sessions that share a screen without a camera now play back as video instead of audio-only. (Repository)
  • A reel that fails to process is now marked as failed instead of showing as preparing indefinitely. (Repository)
  • Highlights from AI moderated sessions can now be added to reels. (Repository)
  • Recording now starts only after the participant confirms recording consent. (Participant Experience)
  • When a participant says they’re ready to continue, the AI moderator now reliably advances to the next question or task. (Participant Experience)
AI moderated studies, booking webhooks, and a combined spend report

New

  • You can now launch AI moderated interviews and AI moderated prototype tests (beta) from the study creation page, letting an AI moderator run sessions and follow-ups for you. See AI moderated interviews and AI moderated prototype testing. (Unmoderated Surveys & Tests)
  • Your integrations can now subscribe to a participation.booked webhook and read the assigned moderator from the participant API, so external systems know about a booking the moment it happens. See the Great Question API. (Integrations & API)

Improved

  • Eligibility rules for invite count, participation rate, response rate, and no-show count now accept a Custom period, so you can define the exact lookback window that applies. See Candidate eligibility settings. (CRM Candidates & Attributes)
  • The MCP server now exposes richer repository consumption tools, so AI clients can search, list, and read sessions, transcripts, highlights, insights, and reels through a single connection. See MCP available tools. (Integrations & API)
  • Admins can now set an incentive wallet low balance threshold and get email alerts when the available balance drops below it, so top-ups happen before studies stall. See Incentives 101. (Billing Subscriptions & Credits)
  • The participant table for AI moderated studies now shows recording status badges and refreshes automatically while recordings process, so you can tell an import in progress from a failure. (Unmoderated Surveys & Tests)

Fixed

  • Self-scheduling no longer creates a duplicate participation, so a stale No Show can’t linger next to a completed session. (Studies Participants & Screeners)
  • Closing a study now refunds only the recruitment credits you were invoiced for, keeping your wallet balance accurate. (Billing Subscriptions & Credits)
  • The interview room now disables Edit booking on sessions managed by external recruitment, with a tooltip explaining why. (Studies External Recruitment & Incentives)
  • Transcript deep-links now open the session side panel even if you previously collapsed it. (Repository Search Tags & Highlights)
  • Publicly shared sessions now play back recordings that previously appeared missing. (Interviews Livestreams & Observer Rooms)
  • Rescheduling a session with a livestream no longer fails on a malformed stream URL. (Interviews Livestreams & Observer Rooms)
  • Highlight reels that mix video and audio-only clips now process and play back reliably. See Reels. (Repository Search Tags & Highlights)
  • A failed recording re-import no longer removes the existing recording; the original stays playable and the import retries. (Interviews Livestreams & Observer Rooms)
  • Manually entered interview locations now apply correctly on studies that collect participant addresses. (Interviews Scheduling & Calendar)
  • Candidates now stay in your chosen order when eligibility filters are applied. (CRM Candidates & Attributes)
  • Creating a study from a team’s page now always assigns it to that team. (Account Users & Roles)
Multi-chat study workspace, multi-clip reels, and sharper AI reports

New

  • You can now keep multiple AI chats on a single study and switch between them, or start a fresh one, from the top bar. Each conversation keeps its own history, so you can explore different questions without losing a thread. (AI Assistant)
  • The study workspace now has dedicated Setup, Results, and Report tabs, and the report has its own URL. Reloads and shared links land on the right tab instead of resetting to the study. (Study Templates & Methods)
  • Report highlight reels can now stitch multiple clips into a single video, so a reel built from several moments plays as one continuous asset. (Repository)
  • The researcher chat can now read your study report, so you can ask follow-up questions about findings and evidence without leaving the conversation. (AI Assistant)

Improved

  • Reports now place computed charts and highlight reels inline beside the findings they support, instead of collecting them in the appendix. (Repository)
  • The report writer now draws on your study’s research plan and on expert researcher feedback, so findings are framed around your goals, research questions, and success criteria. (Repository)
  • Reports are easier to scan: headings scale by level, finding headlines are numbered, inline citations render as numbered reference pills, and detailed evidence pages through a carousel instead of a long scroll. (Repository)
  • AI-moderated sessions now resume after a dropped connection, so participants pick up where they left off instead of losing the moderator’s response. (Participant Experience)
  • The navigation sidebar now remembers whether you collapsed it, even after a reload. (Platform & Integrations)

Fixed

  • You can now remove sub-steps from a study’s workflow outline. (Study Templates & Methods)
  • In AI-moderated prototype tests, moderation now waits until the prototype has finished loading before asking the participant to begin. (Participant Experience)
  • Speech during device setup no longer appears in the session transcript. (Participant Experience)
  • Background moderation hiccups no longer mark otherwise-successful sessions as no-shows. (Participant Experience)
  • Voice responses now default to off for studies that aren’t AI-moderated. (Participant Experience)
  • Clicking a theme’s evidence in a report now opens the slideout focused on that theme, with the question’s other themes behind a toggle. (Repository)
  • New chats now show their generated title without a page refresh. (AI Assistant)
  • Opening a teammate’s study no longer replays the research goal as the first chat message. (AI Assistant)
Auto-complete every new study by default

Auto-complete every new study by default

Auto-complete can now be turned on once for the whole workspace instead of study by study. Under Settings > Governance > Permissions, the Incentive Automation toggle applies auto-complete to studies created from then on.It applies going forward only: existing studies and past sessions are untouched, and you can still override the setting on any individual study from its Automation tab. Duplicated studies keep the setting from the study they were copied from, rather than taking the workspace default.
Auto-complete acts on a session’s booked start time, not on whether the session happened. Any session still marked as Scheduled 24 hours later is completed, the thank-you is sent, and the incentive is released — even if nobody attended. To stop that for a specific participant, mark them as a no-show before the 24 hours are up, which cancels their incentive. Leave the default off if you’d rather review attendance before paying.
  • Auto-complete is now described consistently across workspace settings, study automation, and permissions: each one states that the 24-hour window starts at the booked interview time and that the incentive releases regardless of attendance.
Moderator in the participants API

Moderator in the participants API

GET /v1/studies/:id/participants now returns a moderator object for each participant, so you can see who is running a session without a second lookup. The field is available to all API and MCP consumers.
moderator is null when the participant has no moderator assigned. The user_id matches the user_id returned by GET /v1/interviews/:id/moderators, so you can join the two endpoints directly. See the API reference for the full participant schema.

MCP Skills

Admins can now author reusable instructions, skills, that every AI tool connected through the Great Question MCP follows automatically. A skill captures how your team does something (screener conventions, incentive rules, grounding standards for insights), so agents follow your process instead of guessing at it.Each enabled skill is advertised to connected agents with its name and description, and the agent loads the full instructions for whichever ones are relevant. Skills can also be set as prerequisites for specific MCP tools: when an agent calls a gated tool without the required skill loaded, the call is denied with a message pointing at the get_skill tool to load it. Manage skills under Settings → AI & MCP.See MCP: Skills.

Richer MCP context for agents

Agents connected via MCP can now pull a structured participation event log summarizing what each participant said and did in a session, giving them richer context for analysis and follow-up. See MCP available tools.
  • The incentives page now includes a sortable, filterable table with column header controls, making it faster to find and manage payouts across a large history. See incentives 101.
Autonomous MCP agents
Agents can now connect to Great Question on their own, give an agent a secure API token once, and it connects in the background whenever it needs to, without a human driving it. It only sees what that user is allowed to see, the same permissions and privacy as a normal login.Agents can also start from your saved study templates instead of rebuilding every screener question by hand, with new tools to list, search, read, and apply templates.
  • Editing an account user’s role now surfaces the exact reason a change is blocked (seat limits, permissions), so you can resolve it without guessing.
  • When Microsoft rejects a calendar event because the connected mailbox is over quota, the calendar owner and study owner now see a clear in-app warning naming the calendar, with a link to the interview.
  • Adding interview moderators by email now works when the person is already an account member.
  • Creating a study via MCP without a team now assigns your default team automatically.
Great Question MCP is here
Great Question now runs an MCP server, giving an AI agent, in Claude Desktop, Claude Code, ChatGPT, Cursor, or any other MCP-compatible tool, read and write access to your studies, sessions, transcripts, highlights, insights, and participant data. It can manage candidates, build studies, and handle recruitment and scheduling directly from a chat conversation.Connect at https://greatquestion.co/api/mcp/v1. Every path uses OAuth 2.1 with PKCE, so you authenticate through your browser with your existing Great Question credentials, no API keys or secrets to manage. See MCP setup to connect, and what’s available for the full tool list.
  • Sessions are now transcribed with Deepgram’s Nova 3 model for faster, more accurate transcripts.
  • A warning banner flags User Interviews participants who haven’t been paid within the required window.
  • Highlights and insights are now exposed as read endpoints, so an agent can pull the findings you’ve already captured, not just raw responses.
  • Fixed duplicate and orphaned meeting invites after moderator reassignment, calendars not refreshing after a reschedule, and Google Meet/livestream links stuck initializing.
  • Fixed reprocessing for recordings over 2GB, sessions missing from the repository after completion, and searchable-but-unlisted recordings.
  • Fixed MCP-created email templates rendering with an empty body.
In person studies
Participants can now provide an address for in-person interviews, so you can run studies that follow them into their own environment instead of a call.
  • Google address fields now return the full address after a selection is made, so the zip code is always included.
  • Observers can now view signed consent forms without seeing PII or downloading them.
  • The Members page now shows user email addresses, a role breakdown, name/email search, and filtering by role and status.
  • Eligibility rules now support “Any,” so a rule can match any filter instead of requiring all of them.
  • Cards can be set as default for billing and incentives.
  • Emails no longer get stuck or orphaned when a user’s connected account is removed.
  • Screener changes and edits persist, and library search works as expected.
  • Recordings now download as MP4 instead of FLV.
Shorter session timeout, for security
The “Remember me” login window was reduced from 30 days to 2 hours to meet security requirements.
  • Custom consent forms now show a preview instead of a thumbnail.
  • Sorting by participant rating always places unrated participants at the bottom, regardless of sort order.
  • Creators can request funding approval without the modal disappearing and incentives toggling off.
  • Studies funded by a Team wallet can now be closed when the refund exceeds the Team’s available funds.
  • Duplicating a study no longer errors if a former collaborator no longer has access.
Study Synthesis
A new AI Synthesis tab replaces the manual highlight board, auto-generating a structured summary once a study reaches 3 or more completed interviews, an overview, key insights, and major themes. Major themes carry inline citation badges that show supporting verbatim quotes in your session recordings, with chapter cards so you can scrub to individual moments.The legacy highlight board is still available under a “Highlights” sub-tab.
  • Unsaved-changes detection was added for eligibility rule edits.
  • Improved study duplication and sorting on the Repository table.
  • Corrected the URL used for the Databricks integration.

SCIM provisioning

EnterpriseEnterprise IT teams can now manage Great Question users directly from their identity provider through SCIM 2.0, automating provisioning, deprovisioning, and role management. Users are provisioned and deprovisioned automatically as your IdP changes, with name and email synced in real time. Push IdP groups to map to Great Question roles and Teams, with three sync modes (off, initial only, full sync). Configure it all at Settings → Governance → Provisioning, including bearer tokens, default roles, and IdP-managed roles and teams.

Data Retention v1.5

EnterpriseTake full control of your data retention policy with named rules for Recordings or Candidates, a preset or custom timeframe, and a deletion type. Rules run daily, with a validation step that shows exactly what will be deleted before activation and a 24-hour buffer before anything irreversible happens. Every rule creation, edit, status change, and deletion is recorded in a full audit trail, and rules can be paused or retired without losing that history.

Route approvals to specific admins

A new governance setting lets you route all approval requests to the account owner or a set of individual admins. When enabled, the approver dropdown is locked to that list across every request type, study publish, study funding, feature requests, and team requests.

Livestream status, visible everywhere

Livestream and observer bot status now shows up wherever you need it — the Interview room, participant table, slideout, and dashboard, so most issues no longer require a support ticket. You can resend the bot on demand from the Interview room, and pre-flight checks validate the URL, platform support, and meeting settings for Zoom, Meet, Teams, and Webex ahead of time, with proactive email notifications if something’s wrong.
  • Pagination now supports jumping to the first or last page from a clickable “Page X of Y” menu, across Candidates, Studies, Incentives, Repository, and in-study views.
  • A dedicated Ask AI tab was added to the Repository page.
  • Ad hoc messaging is now disabled for User Interviews participants, to prevent messaging conflicts.
  • Recordings now download with useful filenames (e.g. “Interview with Victoria.mp4”) instead of quality-based names.
Optional device permissions for unmoderated tests
Camera, microphone, and screen recording permissions can now be set to optional instead of required. When a permission is optional, participants are prompted to enable it but can skip and continue if they’d rather not, so you can collect richer data without blocking participants who can’t or won’t grant access. Available for all unmoderated studies; not available for AI-moderated studies.
  • Skip logic now works correctly in User Interviews studies.
  • Multi-select questions with “any of these” ideal answers now qualify correctly when a participant selects just one of them.
  • Auto-disqualification now works in User Interviews, matching how it behaves in Great Question.

User Interviews for external recruitment

We’ve partnered with User Interviews to bring you higher-quality participants: access to 6M+ verified participants (2x our previous panel size), a first match in under an hour, and industry-leading fraud detection, with 98.3% of sessions rated positive by research teams. You’ll continue to recruit through Great Question as usual, now with better quality, broader reach, and more consistent pricing.

AI Moderated Interviews

Conduct in-depth research at scale with AI that adapts in real time, probes for detail, and captures nuance, across time zones and hundreds of participants. Participants respond via video on their own schedule, and sessions flow directly into your repository. Available in English, French, German, Italian, Spanish, Russian, and Japanese. Interested in pricing? Reach out to sales@greatquestion.co.
  • Recruitment reach estimates and an estimated cost breakdown now appear for external recruitment requests.
  • Candidates can now be assigned an affiliation, a specific Team, the workspace, or no one, and the Study List has a new Affiliation column.
  • Snowflake now supports Key Pair authentication (Snowflake OAuth integrations are no longer supported).
Looking for something older? The full release history lives in the app. You can also check status.greatquestion.co for live service status.

Still need help? Contact us at support@greatquestion.co — median response time is 19 minutes during support hours.