Advanced Agentic Orchestration (Closed Beta) - a major upgrade to how agents handle complex, multi-step tasks. Available on request for selected customers.
Agent can break down complex requests into steps, plan an approach, execute actions, and deliver a final answer - all in one conversation.
New File Manager panel lets users upload files and view AI-generated documents directly in the chat.
Cross-session memory - agent retains context from previous conversations, so users don't need to repeat themselves.
Real-time streaming responses during multi-step tasks, with live progress updates as the agent works through each step.
Context-Rich Starter Questions Management - builders can now manually manage the context-rich starter questions generated by Webpage Awareness:
For every page saved by Webpage Awareness, builders can edit both the display message (what visitors see) and the agent message (what gets sent to the agent when clicked).
Manually edited questions are not removed after 30 days, unlike auto-generated ones.
URLs in the management modal are now cleaned up (no protocol/www prefix) and truncated for readability.
Available at Settings > Starter Questions > Manage (per saved webpage).
CLI Authentication - the CustomGPT CLI tool can now authenticate via a browser-based OAuth flow. Running the CLI opens a browser window for authorization, and a token is automatically issued back.
🛠 Improvements
PDF Viewer & Citations overhaul - a major update across citations and PDF viewing:
PDF Viewer is now available on all deployments: Share Link, Live Chat, Embed, and Website Copilot. Previously limited to Instant Viewer deployment only. Configure at Personalize > Citations. Enterprise-only.
Citations page restructured with a new master Enable Citations toggle and clear settings hierarchy - sub-settings only appear when their parent is enabled.
OpenGraph citations redesigned - raw URL overlays replaced with structured, fully-clickable resource cards showing document title, source domain, and favicon.
PDF Viewer styling improved - updated navigation, layout, and mobile responsiveness.
WCAG accessibility compliance improved for classic citations.
Instant Viewer deployment remains as a legacy option but is strongly discouraged. Existing agents with Instant Viewer configured have their settings transferred automatically.
Product Lookup role is now available on Standard plans. Previously required a Premium subscription.
Two-factor authentication UX upgrade - the TOTP verification page now uses a modern 6-field OTP input with automatic submission when the code is fully entered or pasted. Recovery code login remains fully supported.
SSO logout improvements - SSO-authenticated users can now properly log out, including guests from embedded agents. Fixed redirect URLs, tenant identification, and handling for cases where no logout URL is configured.
"Keep PDFs for viewing" now enabled on existing SharePoint and OneDrive sources. The setting was previously only available for newly connected sources.
SharePoint and OneDrive folder names now sync automatically when renamed in the source.
On mobile, the browser status bar now matches the chat header color when the chatbot is opened in fullscreen mode.
🐞 Bug Fixes
Fixed an issue where the in-app support copilot was not appearing on the dashboard.
Fixed the custom "I don't know" message configuration being hidden after the citations page update. The input field is now restored in Chatbot Settings.
Fixed source label filtering not being applied correctly, which could cause over-permissive access or incorrect "sorry" responses for agents using source labels (closed beta).
Fixed an issue where tasks were not displayed when previewing a shared conversation link.
Fixed a SharePoint picker UI glitch where folder contents would disappear when navigating back into a folder.
Fixed an issue where image/vision analysis was returning empty responses approximately 80% of the time.
Available on Optimal, Accuracy, and Understanding modes.
Available to users with access to the model dropdown.
Gemini 3.1 Pro is now available as an AI model option:
Spends one additional query per message.
Available on Optimal, Accuracy, and Understanding modes.
Available to users with access to the model dropdown.
Improved Numeric Search - a major upgrade to how agents handle part numbers, SKUs, and alphanumeric codes:
Retrieval quality for numeric and alphanumeric queries has been significantly improved.
Response times dropped from ~40 seconds to under 4 seconds on large datasets.
To enable: click the Settings button on the Build page and turn on Improved Numeric Search, then re-index (or at least re-index the files where numeric search matters).
New agents can enable the setting during creation. Existing agents that don't enable it continue using the previous numeric search.
Enabling this adds up to 30 seconds of processing time per document during ingestion, which is why it's opt-in rather than automatic.
🛠 Improvements
Notification call-to-action links (e.g., model announcements) now open in a new tab instead of navigating away from the current page.
🔌 API & MCP
Updated OpenAPI schema:
Added realistic example values across all 17 CustomerIntelligence fields.
Added 429 Resource Exhausted error responses to 69 endpoints.
Added streaming documentation with SSE event format and JavaScript client example for POST /chat/completions.
The is_ocr_enabled parameter now accepts boolean values (true/false) in addition to integers (1/0), restoring backward compatibility across all form requests that use this field.
🐞 Bug Fixes
Fixed an issue where the unsaved changes warning in Chatbot Settings was triggered by background polling refreshes, causing false popups even when no settings had been modified.
Fixed an issue where subscribed users who hadn't chatted with any agent yet were locked out of both Crisp live chat and AppWidget support.
Fixed an issue where inline citations could disappear after a conversation loaded, along with autoscroll jumps during streaming and redundant citation loading after streaming completed.
Fixed an issue where streaming failed when Web Search was enabled on an agent.
When using File Upload source with non-searchable PDFs, users can now choose the new AI Vision processing mode alongside traditional OCR.
One page of PDF processed with AI Vision counts as one Vision Credit.
AI Vision understands images within PDFs but does not extract them as separate files.
OCR has been flagged as "not recommended." AI Vision is available on Standard plans and above, while OCR remains Premium-only.
AI Vision cannot currently be used at the same time as regular image vision processing on the same agent. Users who need both should process PDFs and images separately.
Agentic Actions are now available on Standard plans:
Standard users can enable one Agentic Action at a time.
All Actions have higher query costs on Standard compared to Premium.
Some Actions have feature-specific limits on Standard (e.g., lower Document Analyst word limits, fewer Web Search calls per query).
The exact cost for each Action is now displayed on the Limits page based on the user's plan.
🛠 Improvements
Document Analyst quality upgrade - new "Improve answer relevance" toggle:
When enabled, the most relevant parts of uploaded files are prioritized before being sent to the model, leading to better answers.
The agent still uses its full Document Analyst word limit, but content is ordered by relevance rather than position.
If the uploaded file(s) are below the agent's limit, they are read in their entirety regardless.
ON by default for new agents, OFF for existing agents to avoid disrupting current behavior.
The Document Analyst configuration modal has also been refreshed.
New "Copy Button" visibility setting in chatbot settings. When disabled, the button to copy the agent's entire message is hidden from the chat interface.
The "Share" button in the app header has been replaced with a "Publish" button. Functionality is unchanged, but the action is now immediately visible with a label instead of an icon-only button.
Unsaved changes warning: if you try to leave a settings page or close the tab with unsaved changes, the browser will now warn you before navigating away.
Latest Prompts in the Analyze section are now clickable. Clicking a prompt opens a conversation modal showing the full conversation context.
Chat input layout improvements on mobile, including better spacing when the file upload tool is disabled and a more responsive starting screen layout.
Master Agents have been renamed to Multi-Agents across the platform.
🔌 API & MCP
Fixed 500 errors on the /pages/{pageId}/metadata endpoint when a non-numeric pageId was provided. The endpoint now returns a proper validation error.
🐞 Bug Fixes
Fixed an issue where child agents in Multi-Agent setups could answer questions outside their designated scope by referencing conversation history from unrelated queries.
Fixed an issue where the "Verify Response" (Explainability) button did not appear in the chat interface when message copy actions were hidden.
Fixed an issue where the login and registration pages had insufficient minimum height on mobile devices.
Claude 4.6 Sonnet and Claude 4.6 Sonnet Reasoning are now available in the AI model selector.
Claude 4.6 Sonnet Reasoning uses extended thinking to deliver higher-quality responses for complex queries, at a cost of 2 queries per message.
Master Agents are now available on demand:
Create a master agent that connects multiple specialized child agents under one interface.
Each child agent has its own knowledge base and persona, while the master agent controls the shared look and feel.
End-users can switch between child agents using a dropdown, without leaving the conversation.
To enable Master Agents for your account, contact the sales team.
🛠 Improvements
Smarter document-focused search:
When you ask a question about a specific document, the agent now detects this and focuses its search exclusively on that file.
This means more relevant content from the requested document ends up in the agent's context, leading to better answers.
You don't need to provide the exact file name - the agent can figure it out from your question and conversation history.
The feature is always active and can be disabled via Intelligence > General knowledge base awareness > Disabled.
Image processing for website-sourced agents has been upgraded:
When your agent crawls a website, images are now processed with context from the host page (first 500 words).
This results in richer image descriptions - for example, a product image now includes size, price, and properties from the listing page, not just visual features.
New "Selected Folders Overview" button on the SharePoint source page, letting you see at a glance which folders and files you've selected for your agent.
GPT-5 has been retired. All agents using GPT-5 have been automatically migrated to GPT-5.1 Optimal.
Opus 4.5 is now marked as legacy in the model selector. If your agent uses Opus 4.5, consider switching to the newer Opus 4.6 model.
YouTube URL handling improved - the agent now correctly processes YouTube URLs in various formats when provided via sitemap input.
Bulk update and delete is now available for website contexts in Starter Questions management.
SharePoint and OneDrive sync notifications are now handled more reliably.
Minor copy improvements on the SharePoint and related source pages.
🔌 API & MCP
Comprehensive filtering has been added to the Customer Intelligence analytics MCP tool:
15+ filter parameters including user emotions, intents, content sources, stakeholder status, risk metrics, leads, country, language, and date ranges.
AI assistants connected via MCP can now answer complex analytical questions like "Compare frustrated vs positive users in December" or "Which countries have the most unanswered questions?"
Fixed the issue with MCP server sessions expiring after a couple of hours. Sessions now automatically reconnect.
Fixed the integer schema for the leads filter parameter in the OpenAPI spec.
Added enum constraint for the request_source filter in the Customer Intelligence OpenAPI parameters.
🐞 Bug Fixes
Fixed the issue where batch updating documents on the Build > Documents page was not working.
Fixed the issue where document metadata was displaying incorrect URLs in OpenGraph tags.
Fixed the issue where the data source selection could become stuck after dismissing the model configuration dialog.
Fixed the issue where affiliate tracking IDs were not being saved correctly.
Fixed the issue where Customer Intelligence was showing inflated query counts due to incomplete chat entries being included in the results.
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.
