Claude 4.6 Opus is now available to all users who have access to AI model selector.
Introduced a new system where particularly expensive models, like Claude 4.6 Opus, are now available to all users who have access to AI model selector, but will be charged an extra query.
New Agentic Action is now available - Web Search:
Added as new Agentic Action.
Two modes of operation:
On explicit user request.
When the agent doesn't know the response.
Added query cost: 2.
Currently can work together with: Lead Capture, Webpage Awareness, Custom Button
Perplexity endpoint is used for search, which is generally both high quality and extremely fast.
Up to 3 searches are allowed per prompt - their utilization and exact content are decided by agent.
🛠 Improvements
A number of updates and enhancements have been released for the Control end-user access to agents via IdP feature:
There is new Private Deployment - Enabled (IdP) option, available if End-user IdP login feature is enabled for the account.
When enabled - the new IdP authentication method, without any user created in the system - will now work on all embedded deployment types.
Fixed a number of smaller issues related to the feature.
Image citations have been improved:
Image citation can now be clicked to expand to full screen.
On click it can be easily zoomed in.
Works on both desktop & mobile.
On all types of embeddings, the image is contained inside the embedding.
The collected leads information is now available on Customer Intelligence:
There is the new Leads Collected data view.
When selected, all currently configured lead collection fields are displayed on the Customer Intelligence page, enabling easy view.
All this information is also available on the export.
Verified Claims Score and Stakeholder Status are now available in the Customer Intelligence exports.
The agent’s intelligence tab has been improved:
Completely new layout to facilitate decision making.
Changed copy to make concept easier for new users.
Model selector offers clear use cases & benefits for each model.
Improved warning for 'General LLM Knowledge' option + additional reassurances if it's disabled.
Configuration summary is added to reflect the selected settings.
YouTube connector now can correctly ingest a single provided video.
Document's metadata editor is now moved to modal, instead of page, enabling easier work.
A simple builder UI has been added to document’s metadata editor to accounts who have access to experimental Source Labeling feature.
If the user is signed out, following any export link received on the email will now land the user on the login page, rather on 404 page.
Improved the processing and ingestion of PPTX files.
🔌 API & MCP
Fixed formatting and type issues with the /projects/{projectId}/reports/intelligence endpoint.
Fixed the issue with the open MCP server session expiring after a couple of hours.
The Spotlight Avatar dialogue has been added to the Product Lookup agent role.
🐞 Bug Fixes
Agentic tools are now initially disabled on a new agent created by duplicating existing one, to prevent a number of issues and inconsistencies.
Fixed the issue with Log page timing out and resulting in 503 errors on particularly large agents.
Fixed the issue with visually inconsistent loading of the Agents page.
Fixed the rare issue when selecting multiple SharePoint Docs folders.
Fixed the issue with the citation metadata sometimes not being correctly captured and stored during conversation interactions.
Fixed the issue with Confluence pages title sometimes not being properly indexed.
Fixed the server error issues when attempting to fetch the Customer Intelligence data of an empty conversation.
Image citations & OpenGraph citations are now available on Standard.
Both Standard & Premium can now ingest images up to 2048x2048px.
New, increased limits are now in force:
500 images/month on Standard
2500 images/month on Premium
Enterprise customers can now choose between the following vision processing models:
GPT-4o-mini
GPT-5-mini
GPT-5
GPT-5-Thinking
New AI Vision plan add-on is available, with $50/month for 1000 extra images per month.
🛠 Improvements
The Source Labelling feature has been extended, and it is now possible to use the Labels for each deployment type to enable it, and then add the desired labels to the embedded code snippet, so they can be sent on the query time. As a result, only documents with matching labels will be added to the agent's context.
In-app notifications are now being used to announce smaller features or changes.
Added the error message when trying to connect a non-existing SharePoint account.
🔌 API & MCP
Standardizes and improves API labels, summaries, and descriptions across the platform to make endpoints clearer, more consistent, and more developer-friendly.
The query time Source Labels are also available on the /projects/{projectId}/conversations/{sessionId}/messages endpoint.
🐞 Bug Fixes
Fixed the issue with YouTube timestamps sometimes not being attached correctly.
Fixed the issue with where Document Analyst was not providing a response if the user uploaded an image.
Fixed the issue with agentic action feedback for Document Analyst sometimes being broken.
Fixed the line break issue with the demo agent starter questions.
Fixed the issue with the Upgrade to Premium button sometimes not being visible on the upgrade popup.
Fixed the rare issue with numbered references not being rendered properly.
Fixed the issue where the copy on notification was displaying “1 hours”.
Fixed the edge flow on SSO-enabled accounts where it was possible to configure the SSO set up in a way that the account owner would get relegated to regular member role.
Fixed the issue with the app signup page sometimes having a non-white color.
Fixed the issue with manually edited document metadata not being protected when using the individual document refresh action.
CustomGPT.ai chatbots are now partially conformant with WCAG 2.2 level AA.
Partially conformant means that some parts of the content do not fully conform to the accessibility standard.
Latest review gave these results:
Agent landing page: 95%
Agent conversation view: 77%
Full report and accessibility mission statement are available on request.
A new set of UI features has been added:
There is now a new setting for configuring agent avatar and title alignment.
There is now a skeleton loader, adjusted for all chat states - with starter questions, without starter questions, and with active conversation.
Animations have been made much smoother when sending a new prompt or refreshing the conversation.
Live Chat icon & opening animation have been refreshed.
New error message design.
Smooth conversation refresh animation is now available on all deployments.
Agentic Actions feedback design is refreshed, together with Document Analyst-specific elements.
🛠 Improvements
YouTube quality-of-life update - videos used as citations will now have timestamps that will take the user to the correct minute that was referenced.
The document metadata information (title, URL, description, image) that was manually edited is now not being overwritten anymore on document auto-sync.
Improved the unhappy flows and handling for the Document Analyst agent.
🐞 Bug Fixes
Fixed the issue with Website + Image agent source where the images were not correctly processed if URLs contained additional parameters.
Fixed the issue where Custom MCP Actions were not always working correctly with Claude 4.5 Sonnet.
Fixed the issue with Custom MCP Action authentication token sometimes not being properly saved.
Fixed the issue with the Document Analyst agent sometimes giving the uploaded file as citation.
Fixed the issue that sometimes prevented correct reauthorization of the Sharepoint source.
Fixed the issue where Lead Capture custom information field was rejecting entries that contained empty space.
Fixed the spacing issue on the Auto-Sync modal.
Fixed the server timeout issue sometimes caused by feature announcement modal.
Major new CustomGPT for Teams enterprise feature: Control end-user access to agents via IdP:
Builder can do additional IdP configuration - by setting up relations between IdP user groups and CustomGPT roles - to enable end-user access control via SSO.
End-users will login using their IdP credentials and automatically be redirected to agent(s) which they have access to.
The CustomGPT account is not created for end-users authorized in this manner, and there is no limit on the number of such users per account.
There is a single account-level URL which can be shared with end-users.
The feature works for the Share Link deployment only.
Major upgrades for the Verify Responses feature have been released:
The feature is now available on-demand:
If the feature was not enabled at the time the prompt was made, it can still be run by clicking the "Run for this response" button.
The same can be achieved by calling this API endpoint: POST /projects/{projectId}/conversations/{sessionId}/messages/{promptId}/verify
We have introduced Verified Claims Score:
Calculated for each prompt as verified_claims / total_claims
Available on Verify Responses modal and on Ask page.
The data is now available on Customer Intelligence:
New Data View - Trust Building with Verified Claims & Stakeholder Status columns.
New filter - Verified Claims - where the user can input numerical value.
Also available on the Customer Intelligence modal.
The feature can now be used together with Webpage Awareness agentic action.
🎨 Agent UI Upgrade Project
Prompt Input Field
Complete design overhaul.
Default is now one line, which switches to two in case of some action like Doc Analyst enabled.
The send icon is now disabled unless there's some text in the field.
Numbered References
Overhauled popup design with much more professional-looking layout.
Updated number styling.
Added skeleton loader for improved user experience.
Search Generative Experience
Overhauled design with much more professional-looking layout.
Agent Title
Updated styling.
Updated default title color.
🛠 Improvements
The model used AI Vision processing for both agent sources and Document Analyst has been upgraded to GPT-5-mini.
Agentic workflow for Custom MCP Actions has been upgraded.
Prompts for Custom Button agentic action have been upgraded.
Chat interface will now correctly scroll to the bottom of the agent's message bubble, including action icons and citations, after response streaming is complete.
🔌 API & MCP
The Customer Intelligence API endpoint /projects/{projectId}/reports/intelligence now includes a total_queries field in its response, indicating the total number of queries matching the filter criteria.
🐞 Bug Fixes
Fix the issue where Document Analyst settings incorrectly displayed the tokens number instead of the words number.
Fixed the issue with the in-app agent preview, where the conversation got stuck due to unhandled error, if the agent's knowledge base is empty.
Improved how the system handles numbered references by introducing a more inclusive pattern for identifying and removing invalid or non-numeric citation-like tags (e.g., :cit[filename.docx]).
Updated the missing and broken documentation links across the app.
Fixed the issue where “My Content + LLM” setting sometimes wasn’t respected when querying via API.
Fixed the issue where Verify Responses data was visible to users without the Read: View Project Stats permission.
Fixed the issue where export conversation as PDF wasn’t an option on chat previews on the Personalize page.
A next-generation of AI visibility is available to Premium & Enterprise customers - Verify Responses:
A new Agentic Action with a base added cost of 4 queries.
While feature is enabled, all queries are analyzed in depth:
Claims the agent made are extracted.
Used context is searched to find sources for each claim.
Claims are flagged if no source is found.
Claims and their status are reviewed from the perspective of six stakeholders: End User, Security IT, Risk Compliance, Legal Compliance, Public Relations, Executive Leadership.
Each stakeholder provides assessment and final status is calculated.
Analysis can be accessed on the Ask page with the new icon - which is visible only to the builder on that page - there is no end-user exposure.
The process is done in the background, using Claude 4.5 Sonnet, and chat experience is not affected in any way.
Everything is available via API as well.
It is now possible to process images from websites with AI Vision using the new way to build an agent - Website + Images:
If the sitemap is in the correct format with image URLs, and this option is selected, images will be processed using the AI Vision.
Image descriptions are indexed, together with basic information about the parent page, and agents will use them to build responses whenever possible.
The feature is currently in early beta, with many upgrades scheduled.
Another early beta feature is available for Enterprise customer on request - Document Labelling:
Builder can create/edit/delete labels on the agent.
Up to 10 labels can be assigned to any document belonging to the agent.
It is possible to set up which team member has access to which label.
In query time, only sources the user has access to will be used to build the response.
If a document has no labels, it will be accessible to everyone interacting with the agent.
Setting the feature up works via API only - but on query time user-label restrictions limits are respected regardless of deployment type!
🎨 Agent UI Upgrade Project
Tooltips have been removed from the agent interface (copy, thumbs up/down, reset conversation, etc.)
Fixed minor styling issues.
🛠 Improvements
A new pre-defined agent role is now available for Premium accounts - Product Lookup:
Both generic & auto-generated personas are specialized for web-shop type of use case
Features like Numeric Search, Spotlight Avatar, Webpage Awareness, Context-Rich Starter Questions and a number of other settings are configured by default.
🔌 API & MCP
MCP Server deployment is officially not considered beta anymore.
🐞 Bug Fixes
Fixed the issue with Google Drive integration where some file types would forever stay in the queue even if indexing failed.
Fixed the issue preventing SharePoint integrations from re-authorizing upon token expiry.
Fixed the issue with PDFs sometimes not being processed correctly in the Document Analyst.
Fixed the issue with the “Add Knowledge” helper modal not being correctly triggered for new users.
Fixed the issue where Custom Button was added as an Agentic Action even if it was not used in a particular response.
Fixed the validation error when adding Custom Button with invalid link.
Image citations now respect the agent’s border roundness setting.
🛠 Improvements
Added full citations support to both end-user export paths, PDF and CSV, including numbered references.
🔌 API & MCP
Users with no API keys now have access to a new, more streamlined Developers page, designed to make their experience smoother.
The full filters support has been added to the /api/v1/projects/{projectId}/reports/intelligence endpoint: content_source, user_emotion, user_intent, language, user_id, external_id, country, risk_fidelity, risk_jailbreak, risk_prompt_leakage, risk_profanity, request_source and leads.
Updated the /api/v1/projects/{projectId}/sources endpoint’s payload to correctly contain all available agent sources.
🐞 Bug Fixes
Fixed the issue where demo agent colors were not being correctly mapped to the new Adaptive color scheme.
Fixed the issue with long links sometimes incorrectly adding the horizontal scroll inside chats.
Fixed the issue with the new Compact window for Live Chat and Website Copilot always using mobile font size.
Fixed the issue where uploading agent’s background images was causing problems for Standard users.
Fixed the issue where the Context-rich Starter Question didn’t respect the agent's roundness setting.
Fixed the issue on the Ask page where the text input field was not being correctly rendered without full page refresh, if previously selected conversation had expired.
Fixed the issue where on the Ask page, agent’s background settings weren’t being applied.
Resolved typography issues resulting from app-wide font change.
Fixed the alignment issues on Customer Intelligence modal.
Fixed the issue where in-app live chat and deployed agents were sometimes overlapping in the bottom right corner.
