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.
A new option to sync all spaces accessible to the account has been added when creating a new agent, or editing existing agent’s sources.
If selected, all current and future Spaces will be synced.
Doc Analyst upgrade for Enterprise customers - on-demand increase of file size & word length for end-users using this agentic action. This enables greater flexibility and unlocks new, more complex use cases.
🎨 Agent UI Upgrade Project
Fixed the background color bleed issue that existed on rounded borders of Live Chat, Website Copilot and Instant Viewer deployments.
🛠 Improvements
Captured Leads have been added to the Customer Intelligence feature:
If there are collected leads on the agent, a new column is added to the Customer Intelligence table.
It is now possible to apply captured lead status (yes/no) as a filter.
Full lead information is available on Customer Intelligence modal.
Custom MCP actions are now fully supported with all Anthropic models.
Image citations and OpenGraph citations can now be used at the same time.
Users who don’t have access to Instant Viewer can now use the “Try it out” button to test a generic agent with PDF support enabled.
The “Try it out” preview for WordPress integration has been updated to match the Live Chat preview.
New notifications have been added to the system for following events:
First non-team member message for the agent.
More than 300 messages in a calendar week.
More than 1200 messages in a calendar week.
Account at 90% of monthly query / documents / words.
Account at >= 100% of monthly query / documents / words.
Agent at >90% documents.
Agent at >=100% documents.
🔌 API & MCP
Fixed the issue where optimal-choice was not the default setting on the /projects/{projectId}/conversations/{sessionId}/messages endpoint.
Fixed the formatting issue for request_source and response_feedback payloads on the /projects/{projectId}/conversations/{sessionId}/messages/{promptId} endpoint.
🐞 Bug Fixes
Fixed the issue where “Updated at” for every individual page was always updated to the entire source’s latest “Updated at” time.
Fixed the issue where end-users were unable to send the message to the agent after uploading a file to Document Analyst, and then removing it before sending.
Fixed the issue where the agent's meta knowledge flow was not being triggered on specific file names.
Fixed the issues with agent source cards on the Create page having different heights.
Fixed the issue where File Upload and Archives sources were not being shown as one upload source on agent’s Sources page.
Fixed the issue where the Chat-Only user role didn’t have access to any agent.
In-app tooltips have been re-styled and most now have the "Chat to learn more" button.
The button automatically sends a prompt to in-app copilot, providing instant response and assistance.
Future plan: Turn this in-house feature into a deployment option available for everyone.
CustomGPT.ai for Teams quality-of-life updates:
A new Team Administrator pre-defined role has been added, which mirrors the existing Administrator role with the additional privilege of being able to create new member roles.
If there is more than 1 team member who created agents for the team, their name is now displayed on the agent's card on the Agents page, and there is a new dropdown to filter by author.
🎨 Agent UI Upgrade Project
New major UI feature - Agent Style
All elements inside the agent now have the same edge roundness.
Three options are available: Sharp, Soft, Round. Old agents have access to the Legacy setting as well, where everything stays as it was.
This setting also affects outer edges on all deployments - including Embed & SGE.
More agent window size options
New window size added - Compact - preserves the width of the chat area available on the old Window setting, but with greatly reduced white space around it.
The old Live Chat Window setting is now called Focus.
Compact is the new default for Live Chat deployments.
Both Compact & Focus are now available as options on Website Copilot and Instant Viewer as well.
Existing agents are unaffected by the change.
Updated default Live Chat Bubble and SGE deployment dimensions for new agents.
New default layout for new agents:
Agent avatar is now visible by default, while User avatar is hidden.
To accommodate this, avatar visibility is now a Standard plan setting (previously was Premium)
The Fresh color scheme has been renamed to Adaptive.
Border has been added to the Starter Questions box to better accommodate the new default white background.
🛠 Improvements
All deployment options now have the "Try it out" button which instantly shows that very agent and how it will look when deployed on the website.
A new setting has been added to limit the rendered height of image citations to keep them within the 16:9 aspect ratio.
The new option to automatically resize oversized images before sending them to AI Vision has been added.
Improved loading speed of the Billing page.
🔌 API & MCP
Improved the response times of the /limits/usage endpoint.
Fixed the issue where agent_capability setting was missing in the GET response of the /projects/{projectId} endpoint.
🐞 Bug Fixes
GPT-5.1 is now correctly being used with all agentic actions.
Fixed the issue with Agent UI scroll bar incorrectly rendering on Chrome.
Fixed the issue where an empty Starter Question would render in the UI.
Fixed the issue where Document Analyst was sometimes ignoring the uploaded file.
Fixed the issue with Anthropic models that sometimes caused queries to fail if Complex Reasoning capability was enabled.
Fixed the numbered references issues that were sometimes present on the Complex Reasoning capability.
Fixed the issue where o4-mini models were returning error messages.
Fixed the mismatched card sizes on the Actions page.
For the first time ever, we added support for Anthropic's strongest model.
Available on agent capabilities: Optimal Choice, Highest Relevance, Complex Queries.
The smartest model we have in our selection.
Best at: complicated tasks, ambiguous prompts.
Available on demand to Enterprise customers.
OpenGraph citations - A new experimental feature has been added, which replaces numbered references with the webpage’s OpenGraph image, if available. Feature is available on Premium plans.
🎨 Agent UI Upgrade Project
Discreet shadow has been added to the agent window for Live Chat, Website Copilot and Instant Viewer deployments.
The new Fresh agent color scheme is introduced:
The new color scheme has just 1 color - agent primary - and secondary is programmatically derived from it.
This makes it easier for customers to make beautiful and sleek agents.
The old color scheme is now available as Legacy.
The default background for new agents is now white (previously it was an image).
🛠 Improvements
SharePoint Docs and OneDrive integrations will now use a new in-app file picker, providing greater flexibility and control..
Updated the readability of country and language data on the Customer Intelligence page by grouping lower-frequency entries into an "Others" category.
Translations have been added for the “Show more” button for Search Generative Experience deployment.
A standard moderation failed message is now displayed to the user if the file they uploaded to Document Analyst fails NSFW moderation.
Add new cards on the Developers page: Custom ChatBot UI, n8n workflows, and Chrome Extension.
🔌 API & MCP
The Customer Intelligence data for a particular query can now be included on /projects/{projectId}/conversations/{sessionId}/messages and projects/{projectId}/conversations/{sessionId}/messages/{promptId} endpoints by adding the includeInsights=true query parameter.
🐞 Bug Fixes
Fixed the issue where the agent was not always getting the full context when Drive Conversions agentic action was used.
Fixed the issue where GPT-5.1 was not working correctly if used with Custom Agentic Actions.
Fixed the issue where image citations were not being rendered correctly if two references were attached to the same paragraph.
