May 28th, 2026
May 2026
This release brings meaningful improvements across PDF accessibility, Canvas LMS integration, AI-powered workflows, agent knowledge and connectors, and platform experience — including a new analytics dashboard, department-level security, per-user Canvas authentication, and stronger remediation reliability.
🗂️ PDF Accessibility & Remediation
What's new
Tenant-level analytics dashboard — Administrators can now view accessibility activity and outcomes across the entire tenant, supporting reporting and operational decisions without needing to export raw data.
Per-department security — Accessibility batches and files can be scoped by department or group so users only see and interact with content permitted for their organizational unit.
Manual review filter and rerun — Filter files flagged for manual review and create a new batch to rerun low-scoring or critical items with updated remediation settings.
Document queue visibility — Processing queue depth is now visible in the UI so admins and users can gauge system load and expected wait times.
Name your batch on upload — Users can assign a meaningful batch name at upload time rather than relying on system-generated labels.
Keyboard navigation and shortcuts — Full keyboard navigation, a / command palette, and navigation hotkeys improve WCAG-aligned use of the accessibility module.
Improvements
Processing columns and color-coded scores — The file list shows how each file was processed and uses color to highlight PDF accessibility scores for quicker triage.
Accessible queue for authorized users — Users beyond global admins can now see the accessible queue when their permissions allow.
Analytics dashboard access rules — Corrected layout issues and enforced role-based visibility for analytics data.
Upload flow resilience — Files remain in the list when navigating back; upload dates, metadata, and file count descriptions display correctly.
"New files" indication — The upload page again indicates which files are newly added.
Improved OCR for auto-tagging — More accurate tags on scanned PDFs through improvements to the auto-tag pipeline.
Canvas course selection for remediation — Users can change the Canvas course when making a course accessible; batch names are now consistent between batch view and the remediation report.
Bug fixes
Batch sharing — Group descriptions now appear in sharing dialogs; deleting a group updates the UI immediately; batches no longer remain visible after a group is removed.
Department security UI — Group names display correctly in security dialogs; previously selected groups are no longer cleared when editing access.
Remediation reports — "Scanned on" shows the correct timestamp; score colors reflect critical issues; "Changes Made" text is no longer truncated.
Batch status accuracy — Status text and icons align between the accessibility hub and batch detail pages; stuck in-progress batches and failed processing are handled more reliably; original PDF download 404s are resolved.
Preserve layout and full remediation — Fixes for figure alternate text and title failures in full remediation paths (Montgomery and Adobe checker scenarios).
Bookmark in preserve layout — Resolved failures when bookmark remediation ran under the preserve layout strategy.
Batch sharing reliability — Sharing dialogs, group delete behavior, and batch visibility after group removal all corrected.
Manual review filter — Filters behave consistently across batch states.
Filter grouping in batch — Filters inside a batch now group files correctly.
Remediation UI cleanup — Removed confusing steps (duration, inspect PDF tags, proceed to export) where not applicable; cleaned up hand-pointer styling on the remediation complete page.
📚 Canvas & LMS Integration
What's new
Per-user OAuth for Canvas — Each user now connects their own Canvas account via OAuth, replacing the previous shared admin token. This improves security and auditability across all Canvas-linked workflows.
Processing history on course files — The Canvas course files list shows prior processing runs, status, and history so teams can avoid re-processing the same file.
Predictable Canvas batch naming — Canvas batches are now prefixed with Canvas- and include batch numbers, making tracking and support easier.
Bug fixes
Canvas session and configuration — Fixed logout when opening Canvas pages and errors loading courses after reconfiguring Canvas integration.
LTI menu — Canvas LTI now shows the updated left navigation menu instead of a legacy layout.
⚙️ AI Workflow Builder
What's new
Scheduler for workflow automation — Workflows can be configured with scheduler-driven user input steps for recurring or timed runs.
File input node — Upload a file within a workflow and pass a file ID to downstream nodes for document processing, OCR, and related operations.
Pipedream inside workflows — Native agent Pipedream actions can now be invoked directly from workflow graphs, not only from standalone agent chat.
Bug fixes
Pipedream file upload — Resolved failures when uploading files as part of a Pipedream action in a workflow.
Account reconnect — Reconnecting an integration no longer lists duplicate email addresses.
Trigger permissions — Creating triggers now correctly respects role permissions.
🤖 Agents & Chat
What's new
Configurable knowledge base settings — Chunk size, chunk overlap, and Top K are now configurable per agent, allowing retrieval to be tuned for different content types and use cases without code changes.
Tenant-level Pipedream controls — Tenant administrators can disable Pipedream actions and triggers organization-wide.
Environment-level connector toggle — Administrators can enable or disable the Pipedream connector per environment (e.g., different settings for non-production vs. production).
Clickable web crawler sources — URLs and documents from the web crawler now appear as clickable references in agent conversations.
Improvements
Knowledge base settings UX — "Reset to default" applies standard values (800 / 50% / 10); the settings icon matches design; an obsolete field has been removed; updates persist and apply to chat responses correctly.
Citation rendering across models — File and web sources display correctly with Claude Opus/Sonnet, Grok-3, and other LLM options; web page titles render in chat.
Cleaner crawled content — Boilerplate content (navigation, footers) is stripped from crawled pages; configurable chunk selection reduces unnecessary token usage.
Global LMS settings — Canvas and other LMS configuration now lives under a global Settings tab accessible across all modules.
Large document support — Single documents over 30 MB are now handled without silent failure.
Runtime file visibility — Files uploaded for an agent session display correctly and are not hidden when tools are enabled.
Bug fixes
Chunk overlap validation — The UI previously allowed 0% chunk overlap that the API rejected; frontend and backend are now aligned.
Memory on Top K-only change — Updating only Top K no longer unintentionally clears other knowledge configuration.
Connector enforcement — When connectors are disabled, users can no longer access Actions and Triggers.
Pipedream reliability — Core Pipedream actions and triggers restored after a regression.
Connection status for Actions — Success messages now only appear when the external account is actually connected.
User Access Finish button — Saving user access from the Agents wizard now completes correctly.
🏗️ Platform & Experience
What's new
Default landing screen — Users now land on the Home screen after login instead of Accessibility, matching the primary navigation experience for most roles.
Improvements
WorkOS branding — Sign-in now displays the CampusMind logo; invitation emails use the CampusMind product name.
Home icon in navigation — The sidebar now uses a Home icon rather than a Chat icon for the main entry point.
Bug fixes
Create Group validation — Minimum character rules are now enforced consistently when creating groups.
Notes
Knowledge base chunk size and overlap changes clear and rebuild indexed knowledge for the affected agent. Allow time for re-indexing to complete after saving.
Pipedream tenant and environment controls are tenant-wide. Confirm the desired settings with your administrator before go-live if your organization uses or plans to restrict Pipedream.
Canvas per-user OAuth replaces the previous shared admin token. Existing Canvas configurations should be reviewed and reconnected by individual users where applicable.
For questions about any of these changes, please reach out to your CampusMind account team.
May 6th, 2026
Product: CampusMind · Track: Montgomery · Fix version: 4.0.7_Montgommery
This release focuses on Accessibility: clearer scores and status in the file list, a tenant-level analytics dashboard, stronger OCR in the auto-tag pipeline, and fixes for score color coding and group naming rules.
New & enhanced
Tenant-level Accessibility analytics (CLASS-1107)
Adds an analytics dashboard at the tenant level so administrators can monitor Accessibility usage and outcomes for their organization from a central view.
File list: processing context and score visibility (CLASS-1062)
Extends the Accessibility file list with columns that surface processing configuration and PDF accessibility scores with color-coded presentation so teams can see status at a glance while working through batches.
Auto-tag pipeline: OCR quality (CLASS-1108)
Improves OCR accuracy in the auto-tag flow by replacing PaddleOCR with a more accurate approach, raising the quality of text extracted from documents before tagging and downstream processing.
Fixes
Score color coding (CLASS-1186)
Corrects inaccurate color indication for accessibility scores so UI colors match the actual score bands and reduce misinterpretation.
Create Group — minimum name length (CLASS-991)
Ensures minimum character length for group names is enforced consistently (including environments where it was previously inconsistent).
Included work items
April 30th, 2026
Overview
This release improves knowledge base configuration and reliability for AI agents, adds administrative controls for optional workflow automation integrations, and includes usability and quality fixes across related settings and group management.
What's New
Per-agent knowledge retrieval settings
Configure how knowledge content is split, overlapped, and retrieved — including how many results are considered — so different agents can be tuned for different content and use cases.
Tenant-level controls for Pipedream automation
Support for disabling Pipedream actions and triggers at the tenant level when policy requires it.
Environment-level Pipedream connector control
Administrative control to enable or disable the Pipedream connector per environment (e.g., different posture in non-production vs. production).
Improvements
Knowledge settings and chat — After updating knowledge settings, chat behavior remains stable and predictable (no silent failures when continuing a conversation).
Memory behavior when changing retrieval settings — When only certain retrieval parameters are updated, conversation context is handled consistently, reducing unexpected loss of thread continuity after configuration changes.
Knowledge settings UI — The settings panel reflects saved values when reopened, and the layout aligns with the intended design, including icon corrections and removal of a non-applicable field.
Client-side validation for advanced options — Prevents invalid configuration values that the service cannot accept, so users receive immediate feedback instead of a failed save.
Bug Fixes
Group creation — Enforces minimum name length rules consistently, including environments where the rule was not applied uniformly before.
Notes
Scope and behavior should be validated in your environment after deployment, especially for knowledge tuning and automation/connector policies.
If your organization uses Pipedream or plans to restrict it, confirm the desired tenant and environment settings with your administrator before go-live.
Relevant User Guides:
https://campusmind.featurebase.app/en/help/articles/8386104-agent-actions-and-trigger-library-enabl…
https://campusmind.featurebase.app/en/help/articles/7086176-adjust-advanced-agent-knowledgebase-set…
April 9th, 2026
Version 4.1.0 — April 2026
We're excited to share what's new in this release. This update brings meaningful improvements across PDF accessibility, AI-powered workflows, agent performance, and platform reliability.
All Changes
🗂️ PDF Accessibility & Remediation
We've made substantial enhancements to our accessibility pipeline, making it easier to audit, remediate, and manage PDF documents at scale.
Richer audit reports (CLASS-984, CLASS-1053) — Accessibility audits now produce detailed before-and-after comparisons so you can clearly see what changed and what still needs attention. Failed files are flagged visually in red for quick identification.
AI-assisted metadata extraction (CLASS-997) — Before any auto-tagging occurs, the system now automatically extracts document metadata (title, language, author), improving tagging accuracy and reducing manual corrections.
Batch processing limits (CLASS-1056) — Users are now capped at 50 files per batch, ensuring consistent performance and fair resource usage across all users.
Per-user security controls (CLASS-1051) — Accessibility features now enforce user-level security, ensuring each user only sees and manages their own files and batches.
Improved file status visibility (CLASS-1034) — New batches with an in-progress status now appear at the top of the list immediately, so you're never left wondering if your upload was received.
Consistent PDF download naming (CLASS-1045) — Downloaded remediated files now have accurate, consistent filenames.
Back-button file retention (CLASS-1019) — Files uploaded to the accessibility tool are no longer lost when navigating back from the remediation page.
Various UI fixes (CLASS-1015, CLASS-1020, CLASS-1030, CLASS-1055) — Corrected error messaging in remediation reports, aligned icon styles across the batch and accessibility pages, and resolved several display inconsistencies.
Stability improvements (CLASS-1070, CLASS-1071) — Fixed a crash that occurred when inviting users with malformed email addresses, and corrected the default selection behavior on the accessibility page.
⚙️ AI Workflow Builder
We're introducing a major new capability: a drag-and-drop AI Workflow Builder that lets you visually design, configure, and run multi-step AI workflows — no coding required.
Visual workflow designer (CLASS-933, CLASS-934, CLASS-935, CLASS-936) — Build workflows by dragging and connecting nodes on a canvas. Supports actions, triggers, and LLM-powered steps in a clean, intuitive interface.
File and image input support (CLASS-974, CLASS-975) — Workflows can now accept file uploads and images as inputs, enabling document processing and OCR-based use cases.
User access controls for workflows (CLASS-939, CLASS-923) — Administrators can now control which users have access to specific workflows.
Publishing workflows (CLASS-919) — Completed workflows can be published and made available to end users.
Improved debugging and error handling (CLASS-937, CLASS-938) — The workflow builder includes built-in debugging tools and clearer error messaging to help you identify and resolve issues faster.
Execution history (CLASS-987) — Workflow execution history is now correctly visible within the chat window, not just from the workflow view.
Several UX fixes (CLASS-995, CLASS-1002, CLASS-986) — Resolved issues with blank responses from certain AI models, wording inconsistencies in action menus, and a button that incorrectly re-enabled itself after saving.
🤖 Agents & Chat
Claude model support (CLASS-841) — CampusMind now supports Anthropic's Claude models, expanding your choice of AI beyond OpenAI offerings.
Expanded model compatibility (CLASS-800) — Fixed model selection issues that prevented GPT-4.1 and GPT-5 from being properly applied to agents.
Chat widget stability (CLASS-951) — Resolved a crash that occurred when sending multiple messages while an agent was processing a previous response.
VTA disclaimer fix (CLASS-989) — The Virtual Teaching Assistant disclaimer now appears only once per session instead of on every message.
Agent visibility (CLASS-706) — Newly created agents now appear in search results immediately after creation.
Overview page fix (CLASS-982) — Resolved an issue where the agent Overview page showed no results.
Trigger and save fixes (CLASS-902, CLASS-909) — Fixed incorrect button labels on Trigger and User Access pages, and resolved a bug where the success message appeared twice when saving triggers.
Long agent name support (CLASS-965) — Fixed a database error that occurred when adding a group to an agent with a long name.
🏗️ Platform & Performance
Source URLs in chat (CLASS-1004) — When the assistant retrieves content from web sources, the source URL is now included directly in the chat response for easy reference.
Web crawler improvements (CLASS-1005, CLASS-961) — The crawler now outputs cleaner Markdown files with properly formatted, clean URLs — making content easier to review and use downstream.
Faster permissions loading (CLASS-798) — Significant performance improvements to how tenant-level permissions are loaded, reducing latency across the platform.
Custom branding for chat widget (CLASS-877) — The chat widget will respect your tenant's custom branding color as the default, providing a more consistent white-labeled experience. (Rolling out in the next update)
Load testing & reliability (CLASS-640, CLASS-761) — We conducted comprehensive load testing and addressed performance bottlenecks to ensure CampusMind remains stable under high usage.
Azure Marketplace (CLASS-238, CLASS-750) — CampusMind is advancing toward full availability on the Microsoft Azure Marketplace, making it easier for institutions to procure and deploy.
For questions about any of these features, please reach out to your CampusMind account team.
March 6th, 2026
Status: Coming Soon Release Type: Upcoming Release
We're continuously working to make CampusMind better for you. Here's a high-level preview of what's on the horizon — from expanded AI model options and smarter branding controls to a visual workflow builder and major accessibility upgrades.
ℹ️ These features are currently in development or testing. Details and timelines may change as we get closer to release.
What's Coming at a Glance
🔮 Upcoming Features
CampusMind Coming to Azure Marketplace (CLASS-238)
CampusMind will soon be available directly in the Azure Marketplace. This makes it significantly easier for institutions already using Microsoft Azure to discover, procure, and deploy CampusMind — all within their existing Azure environment and billing setup.
Build Agent Workflows Without Any Coding (CLASS-796)
We're introducing a visual drag-and-drop workflow builder that lets anyone — technical or not — create powerful multi-step agent workflows. Simply connect steps visually to automate complex tasks, no technical knowledge required. This is one of our most exciting upcoming capabilities and will open up a whole new level of automation for your institution.
Support for Additional AI Models (CLASS-841)
We're expanding the AI models available within CampusMind, giving administrators and agent builders more options when configuring agents. More model choices means more flexibility to find the right fit for specific tasks, audiences, and workflows.
Web Widgets Automatically Match Your Brand Colors (CLASS-877)
Your institution's brand colors will soon be applied automatically to all chat widgets by default — no manual setup needed. This ensures a consistent, professional look across every touchpoint where your agents appear.
Redesigned Actions & Triggers Interface (CLASS-921)
The Actions and Triggers section is getting a fresh new look. The redesigned interface will be more intuitive and faster to configure — making it simpler for both technical and non-technical users to set up automated agent workflows.
Platform Performance & Stability Upgrades (CLASS-839, CLASS-840)
We're investing in core platform improvements that will make CampusMind faster, more stable, and better equipped for future capabilities. All existing features will continue to work exactly as expected — no disruptions, no breaking changes.
Summary
The next release is shaping up to be one of our most impactful yet — bringing no-code workflow automation, a major accessibility overhaul, expanded AI model support, and a more polished experience throughout the platform. We'll share more details, including release dates, as development progresses.
CampusMind AI Platform | For questions, contact your CampusMind administrator.
March 4th, 2026
Release Date: March 5, 2025 Release Type: Monthly Release
We're excited to ship CampusMind 3.0.0 — our biggest monthly release yet. This update brings powerful new automation capabilities, a cleaner and faster interface, significant accessibility improvements, and a wave of bug fixes that make the platform more reliable than ever.
What's Changed at a Glance
✨ New Features
Agents Now Show What They're Thinking (CLASS-740, CLASS-794)
Instead of staring at a spinning loader, users now see live, contextual status messages while an agent is working — things like "Analyzing transcript…" or "Calculating eligibility…" This makes wait times feel shorter, keeps users engaged, and makes it clear the agent is actively working on their request.
Automate Agent Actions Based on External Events (CLASS-768, CLASS-852, CLASS-853, CLASS-854)
Agents can now respond automatically to external events — like incoming emails, form submissions, or activity from other tools — without any manual intervention. A clean and simple interface makes it easy to set up, view, and manage all your automated triggers in one place. This is a big step toward fully automated agent workflows for your institution.
Accessibility: Bulk Course Selection & Batch File Processing (CLASS-827, CLASS-828)
Two major time-savers for accessibility workflows:
Bulk Course Selection — Select multiple courses for accessibility processing at once instead of going one by one.
Batch File Processing — Up to 10 files are now processed at the same time, dramatically cutting down turnaround time for large course loads.
Web Crawler: Add Multiple URLs at Once (CLASS-891, CLASS-918)
Setting up a web crawler no longer means adding URLs one at a time. You can now paste an entire list of URLs and kick off the crawl in a single step. Each URL is tracked separately with its own document name, making source management much cleaner and easier to navigate.
Clickable Source Links in Agent Conversations (CLASS-894)
When an agent cites a website as a source in a conversation, that source is now a clickable link. Users can click directly on it to open the original webpage in a new tab and verify the information themselves — making agents more transparent and trustworthy. This works for all web sources referenced in agent responses.
Smarter Document Processing (CLASS-907)
Documents that are rotated or oddly oriented are now automatically corrected before text extraction begins. This means more accurate results and better accessibility output — with no manual fixes needed on your end.
Refreshed Left Navigation Pane (CLASS-881, CLASS-884, CLASS-885)
The left-hand navigation has been cleaned up significantly:
Favorite agents and recent conversations are now tucked into expandable dropdowns to reduce clutter
Quick access icons for Accessibility and IT Workforce tools are now pinned directly in the pane for faster reach
Overall navigation feels tighter, faster, and easier to use
Faster & More Reliable Platform Updates (CLASS-524, CLASS-634, CLASS-658)
A set of behind-the-scenes infrastructure upgrades that directly benefit every user:
Deployments are now fully automated, meaning faster updates with fewer interruptions
Core platform features are automatically tested after every release, so issues are caught before they reach you
Enhanced security and performance controls ensure the platform handles traffic reliably at scale
🔧 Improvements
Faster & More Reliable Document Autotagging (CLASS-916)
We've upgraded our document autotagging engine to deliver faster, more reliable results at scale — with no change to output quality.
Web Widget Session Persistence (CLASS-920)
Conversations in the chat widget now persist as users navigate between pages on the same website. No more lost context, no more restarting mid-conversation.
Bulk Web Scraper UI Fix (CLASS-922)
Resolved several interface issues in the bulk scraper that were making the feature difficult to use. The workflow is now smooth and consistent.
🐛 Bug Fixes
Student Account Permission Issue (CLASS-612)
Students invited as VTA Admin or Professor were unable to trigger pipelines. This has been resolved — role-based permissions now work correctly across all account types.
Agent Name Cannot Be Modified (CLASS-650)
Editing an agent's name would snap back to the original on every keystroke, making it impossible to rename agents. This is now fully fixed.
Uploaded Files Not Appearing in Knowledge Base (CLASS-745)
Files uploaded to the knowledge base were not showing up after upload. Uploads now appear immediately and are ready for agent use.
Observability Search Not Working (CLASS-763)
The search function in the observability section was broken, making it hard to find logs and trace issues. Search is now fully functional.
Chat Widget Branding Not Rendering (CLASS-892)
Custom logos and agent names set in the widget configuration were not showing up in the live widget. Branding changes now apply immediately and display correctly.
Summary
CampusMind 3.0.0 is a milestone release. From smarter agents and powerful automation to a cleaner interface and rock-solid reliability improvements, this update is built to help your team move faster and deliver better experiences to your users. As always, reach out to your CampusMind administrator with any questions.
CampusMind AI Platform | Version 3.0.0
February 20th, 2026
CampusMind v2.3.5 – Web Crawler & Widget Improvements
Release Date: February 26, 2025 Release Type: Feature Release
This release addresses minor feature improvements to web widgets and the web scraper to improve behaviour when using AI agents on websites.
✨ What's New
1. Web Crawler – Bulk URL Addition (CLASS-732)
We've enhanced the web crawler to support adding multiple URLs at once, making it faster and more efficient to set up crawlers for multiple web pages.
Key Capabilities:
Bulk URL Input – Add multiple URLs in a single operation instead of one-by-one
Simplified Workflow – Streamlined interface for bulk URL addition with minimal configuration
How It Works:
Click "Create Webcrawler" to see two options:
Create a single webcrawler (existing workflow)
Create from a list of URLs (new bulk option)
Select "Create from a list of URLs"
Copy and paste your list of URLs
All URLs are processed simultaneously with optimized default settings
Benefits:
Save time by adding multiple URLs at once
Faster setup for websites with many pages
Sync settings and scraped documents per URL separately
Better source tracking with URL-based document names
Cleaner, more intuitive interface for bulk operations
🐛 Bug Fixes
2. Chat Widget – Custom Settings Fix (CLASS-733)
Fixed an issue where custom logo and agent name changes in the widget customization section were not appearing in the actual widget display.
What's Fixed:
Custom logo/agent image changes now render correctly in the widget
Agent name customizations are now properly displayed
CDN cache updates correctly when settings are changed
Widget configuration is fetched and applied reliably
Impact: Your custom branding and agent names now display correctly in the chat widget, ensuring a consistent brand experience for your users.
3. Web Widget – Session Management (CLASS-731)
Fixed an issue where conversation history was lost when users navigated between pages on the same website. The widget was resetting on each page navigation, causing users to lose their conversation context.
What's Fixed:
Persistent Conversation History – Web widget now maintains conversation history across page navigations on the same website
Seamless User Experience – Users can navigate between pages without losing their conversation context
Session Management – Improved session handling ensures conversations persist throughout the user's browsing session
Impact: Users can now navigate through your website while maintaining their conversation with the agent, eliminating the need to repeat information or restart conversations.
Summary
This release brings significant improvements to the web crawler with bulk URL addition capabilities, along with important bug fixes that enhance the reliability and user experience of the chat widget. These updates make it easier to manage web content and provide a better experience for your website visitors.
CampusMind AI Platform | Version 2.3.5 | For questions or support, contact your CampusMind administrator.