RapidflareRapidflare Documentation

What's New

Admin Experiences Release Notes

August, 2026

New Features

  • Selective ingestion and Partial Retry from failing URLs: You can now run an ingestion against a specific list of URLs from the dashboard, or "Partial Retry" an earlier run to pick up just the URLs that failed in it (up to 100). No more re-crawling an entire source when only a handful of pages need reprocessing.

  • Optional agent version and description: The agent header no longer prints a placeholder Version: 1.0 when the hub has not configured one — version and description are now optional fields and are omitted from the UI when unset.

  • Catalog v2 product editor: author CTAs, assets, and typed metadata inline: The Catalog v2 product editor now supports authoring typed product CTAs, assets (images and files), and metadata fields directly from the admin dashboard.

  • Configurable hub display order: Hubs on the dashboard now appear in a shared order configured for your organization — the same for everyone in it — instead of an order held locally in each person's browser.

Improvements

  • Pro Agent progress timeline: Pro Agent turns now emit human-readable progress events ("Searching the knowledge base…", "Running a command…", "Writing a file…") that also persist to the conversation history. Tool activity is legible both live and on reload, and completed turns show duration instead of a stuck spinner. Previously each row appeared blank with an invalid timestamp.

  • Filespaces & Skills row actions in dark theme: Row overflow (three-dot) menu icons on the Filespaces and Skills hub pages are visible again in dark theme.

  • Sources view surfaces documents recovered via fetch fallback: When ingestion recovers a document via the automatic fetch fallback (used when a source's primary fetch is blocked by a CDN or edge-network protection), the Source detail view now shows which documents were rescued, so admins can see where the fallback engaged.

  • Dark-mode consistency across pickers, taxonomies, and catalog relations: Continued dark-theme cleanup covering option pickers, taxonomy browsers, catalog-relation UI, and empty-image placeholders that were previously hard to read against the dark background.

  • SSO login errors are now accurate, branded, and actionable: A failed SSO login explains what actually went wrong, in Rapidflare's own copy, instead of one catch-all message — including whether the account is missing from the organization, has been deactivated, or has an invitation still pending.

  • Compare up to 30 products at once: The Compare view now handles up to 30 products in a single comparison, raised from 12.

Bug Fixes

  • Hub-scoped conversation counts and Catalogs listing: The hub overview page and the Catalogs page now show only the current hub's data. Both surfaces had been aggregating counts and listing catalogs across every hub of the customer, so different hubs looked deceptively identical.

  • Skill authoring keeps your work when a save is rejected: Fixed an issue where a Skill that failed validation closed the editor and discarded everything the author had typed. The editor now stays open and shows what needs fixing, so no work is lost.

July, 2026

New Features

  • Pending invitations visible in user management: The users table now includes invites that haven't been accepted yet, so admins can track invite status and follow up without leaving the dashboard.

  • Add Source dialog refresh — 8 new self-serve connectors, source icons, and filter search: Confluence, WordPress, Helpdocs, LearnUpon, Aptify, Khoros Community, Salesforce Cases, and Vimeo are now self-serve source types from the dashboard. The dialog gained per-type icons and a filter search box for the growing list.

  • Catalog V2 taxonomy browser: Typed-attribute creation with unit-prefix type-ahead, vendor management, and CSV import/export at both the taxonomy and node scope.

  • Per-customer integrations management: Super-admins can toggle integrations on or off per customer and delete connections directly from the dashboard.

  • Role-based Filespaces visibility with hub-default attach: Filespaces can now be scoped to org-super-admin, admin, or member; a hub can also pin a filespace to be attached by default on every new conversation.

  • Source tags persist on save: Tags set on a source through the admin config editor (including the new institutional_knowledge tag) now correctly round-trip through save and refresh; they were previously being silently dropped from the payload.

  • Rapid Catalog: description column is optional: Rapid Catalog ingestion no longer requires a description column on the source sheet, making it easier to onboard catalogs whose upstream feeds don't carry product descriptions.

Improvements

  • Ingestion phase warnings surfaced on completed stages: When an ingestion phase completes with warnings in its logs, the source detail view now flags that at the top level, so operators don't miss issues buried inside collapsed logs.

  • Consistent daily analytics counts across the dashboard: The daily-trends chart, its drilldown, and the conversation-history page now all use the viewer's local day boundaries, so the same conversations are counted the same way in every view.

  • LLM-judge confidence in the QA Panel and analytics grid: The internal review workflow now surfaces judge confidence alongside its verdict on both individual conversations and the analytics grid.

  • Analytics cards and drill-downs stay in sync: Fixed a mismatch on non-production environments where totals on analytics cards could disagree with the drill-down list beneath them. All environments now honor caller-supplied scope consistently, so the numbers line up top to bottom.

June, 2026

New Features

  • Catalog type selector in source configuration: When configuring a catalog source, admins can now tag it with one of four catalog types — Primary, Competitor, Starter or Accessory. The tag drives downstream agent behavior (for example, starter catalogs are surfaced as companion product suggestions; see Agent Platform).

  • Projects: super-admin management UI: A new Projects screen for managing hub-scoped Project libraries. Admins can drag-and-drop folder uploads (directory hierarchy is preserved, OS-junk files are filtered out, and large folder uploads are batched with backoff). Chat now supports multi-selecting one or more Projects to attach as reference material for a Pro Agent conversation turn. The platform side of Projects is documented under Agent Platform.

  • Per-message Agent stats popover (super-admin): Each AI message in a conversation now has a one-click "Agent stats" affordance in the message toolbar, opening a popover with latency marks (time-to-first reasoning token, time-to-first tool call, time-to-first answer token, agent work, total) and token usage (input including cached subset, output) for that single turn. Useful for debugging "why was this turn slow?" without leaving the conversation view. Super-admin only.

  • Role-based hub visibility: Hubs can now be scoped so that only specific admin roles (super admin, admin, or member) see them in the dashboard, sidebar, hub pickers, and conversation exports. Empty permissions preserves the current "visible to all" behavior, so existing hubs are unchanged.

  • Analytics: channel and form-factor breakdowns: The copilot analytics page now breaks conversations down by the channel they came in on (Web, Slack, Discord, Email, Public API) and, for Web, by form factor (embedded launcher vs AI Overview). When a hub has only a single channel or form factor, the card renders as a concise summary line instead of a one-bar chart. Backed by the unified conversation origin model on the Agent Platform.

  • Analytics: (i) info tooltips on every chart: All 17 charts on the analytics page now carry a hoverable info icon explaining what each breakdown or trend measures. Empty charts also hold their card space with a "No data found" message, so the layout no longer reflows when a chart has no data for the selected range.

  • Discord bot activity status configuration: The deployment page in the dashboard now has an Activity Status control (type + text) for each Discord bot. The status is applied on every gateway reconnect, so e.g. "Listening to /ask for questions" appears under the bot's name in Discord servers.

  • Confirm-before-disable for deployments: Disabling a deployment now goes through an explicit confirmation modal to prevent accidental disable clicks.

Improvements

  • "Last quarter" / "this quarter" shortcuts in date pickers: The dashboard's datetime selector now includes quick-select shortcuts for the last and current quarter, alongside the existing day / week / month / year shortcuts. Also fixed a long-tail cursor-jank issue when editing time inputs.

  • Organization selector groups paused customers: The organization selector now lists active customers first and paused customers at the end of the list, separated by a divider — replacing the previous show/hide checkbox. Reduces the chance of accidentally selecting a paused customer during demos and day-to-day navigation.

  • Misc admin polish: A handful of smaller usability fixes — typing in the organization-search box no longer suggests the currently selected organization back to you, and editing a customer's display name now keeps the underlying identity-provider name in sync. Plus a couple of small fixes on the Trigger Ingestion "bypass cache" toggle.

  • "Rapid Catalog" source label: The admin source picker and source-type displays now consistently read "Rapid Catalog" instead of the older internal label.

  • Source schedule UX polish: A new Schedule column filter (manual vs. scheduled) on the Sources list, and the Save button on a hub's Schedule tab now correctly disables after a save instead of staying enabled.

  • Customer admins can self-serve more workflows: Three capabilities previously gated to Super Admin are now available to Admin users:

    • The Pro Agent toggle in Converse (per-conversation long-horizon agent mode).
    • The Filespaces management page and the ability to create new Filespaces.
    • File attachments in the Converse chat page.

Bug Fixes

  • Failed analytics conversation search now surfaces an error: When a backend error prevented loading the conversations preview from an analytics drill-down, the panel previously showed a misleading "No conversations found" message. It now surfaces a clear "Failed to load conversations" error and a toast notification.

  • Hub Sources list sorts correctly: Source names in the Hub Sources list now sort correctly alphabetically.

  • Disabled-sources view loads cleanly: Opening the Sources view filtered to disabled sources no longer errors out; the page now renders the disabled list correctly.

May, 2026

New Features

  • Shared link admin view: Shared hub and shared conversation pages now resolve through the platform admin path, allowing admins to inspect and manage shared links directly from the dashboard.

  • Sitemap URL pattern filters: New include and exclude URL pattern options on Sitemap source configuration let operators scope a crawl to specific URL subsets without code changes.

Improvements

  • Longer additional guidelines: Agent additional guidelines limit has been raised from 5,000 to 7,000 characters, giving operators more room to fine-tune system prompt instructions.

  • Ingestion UI polish: Several improvements landed across source detail and ingestion views:

    • Workflow progress summary now appears as subtext below each stage heading, making in-flight progress easier to read.
    • Running-status color is consistent across the source list, source details, and ingestion history pages.
    • The "View logs" link copy is now consistent, and the logs modal scales responsively to the viewport.
    • The Chunks tab is hidden on catalog/glossary source detail pages where it does not apply.
    • URL list sources can once again be edited to add new URLs (regression fix).

  • Hub delete from the dashboard: Hubs can now be deleted directly from the admin dashboard. Appearance settings and destructive actions like hub delete now live together under a single consolidated Configure surface.

  • HubSpot ticket handoff: Admins can now route human-agent handoffs to a HubSpot ticket, alongside the existing Salesforce ticket flow.

  • Slack app installation from the dashboard: A full in-dashboard flow for installing the Rapidflare Slack app, with cleaner wording and a fix for cases where the install window opened twice.

  • Editable hub names: Admins can now rename hubs directly from the dashboard, with duplicate-name validation enforced on both client and server to prevent two hubs sharing the same name.

  • Khoros Community: search-query support: The Khoros Community source now accepts a search_query parameter to scope ingestion, with a simplified configuration that derives auth endpoints from the base URL.

Improvements

  • Conversation history user filter — sort + pagination: The user filter on the conversation history page is now alphabetically sorted with infinite-scroll pagination on large user lists. The Users column itself is sortable end-to-end.

  • Dashboard no longer loses paused ingestions: Fixed a long-latent race where the source detail view could get stuck on "Ingestion in progress" with all stages complete after clicking approve / cleanup on a manual-approval ingestion. The view now transitions cleanly without a manual refresh.

  • LLM query suggestions polish: Cleaner popover anchoring when the suggestion list resizes, no spurious popover reopen after picking a suggestion, and stable loading-to-list transitions in both Converse and the embedded search experience.

  • Clearer source status labels: Fresh sources now show an "Awaiting" status label in place of the previous "NOT STARTED" copy, making the pre-ingestion state easier to read.

  • Account-grouped sidebar: Integrations, organizations and user-management items are now grouped under a single Account section in the side navigation, replacing the previous Utilities placement.

  • Editable Salesforce ticket summary on handoff: When a conversation hands off to a Salesforce ticket, users can now review and edit the AI-generated summary before the ticket is created, and the auto-generated summary itself is more neutral by default. Reduces back-and-forth between support and end users on tickets where the AI's framing needed a small tweak.

  • User management for domain admins: The user management screen is now available to domain admins as well, who can view and manage the users on their side directly from the dashboard. For domain admins, the Rapidflare team's internal user list is not surfaced.

  • Bypass-cache toggle on Trigger Ingestion: Superadmins can now check a "bypass cache" option on the Trigger Ingestion flow to force a fresh re-extract on a single source or document without dropping to the CLI. Helpful for unblocking customer support investigations.

  • Catalog source navigation from the content page: Clicking through to a RapidCatalog source from the content listing page now lands on the correct catalog detail view (was previously routing to the generic source view).

  • Clearer catalog onboarding error feedback: RapidCatalog source onboarding aggregates ingestion-time errors and surfaces explicit feedback in the dashboard when hyperlinks or columns are missing or empty, so the cause of a failed catalog ingestion is obvious from the source page.

  • Hub-name edit polish: Editing a hub name now shows a tooltip with the current name on hover, and a close button to cancel an in-progress edit without saving.

Bug Fixes

  • YouTube playlist source creation fixed: Creating a YouTube playlist source no longer errors with Source not found on the final "Configure and finalize" save step.

  • Activity report "Unresolved" count accuracy: The Unresolved count in the daily activity report now matches the conversation and message totals shown in the conversation history view. The report was previously inflated because the background job pulled values through a broader-search API that mixed in feedback items.

April, 2026

New Features

  • Non-OAuth integrations in the UI: Admins can now connect API-key-based and other non-OAuth integrations directly through the admin Integrations page.

  • Editable collection names: Admins can rename collections directly without recreating them.

  • Discord escalation & routing controls: Deployment settings now include tabbed Discord configuration with escalation rules, routing, and notification channel selection.

  • Discord onboarding choices: Admins can choose Auto-Reply vs. No Auto-Reply behavior during Discord forum channel setup, with improved gateway stability eliminating prior infinite retry/reconnect issues.

  • Jira ticket filtering and JQL: Admins can scope Jira ingestion to specific issues (e.g., only active bugs) using filters or raw JQL, reducing ingestion noise and improving content relevance.

Improvements

  • User management improvements: User lists are now alphabetically sorted, checked filters surface at the top, and Super Admin role is restricted to company email domains.

  • Guided extraction type checks: Numeric parameters now reject string values on create/update, preventing misconfigurations.

  • Source navigation keeps hub context: Drilling into source details and navigating back now preserves the hub filter, so admins don't lose their filtered view.

  • Cleaner analytics averages: Per-day conversation and message averages now display as rounded numbers (~N or < 1) instead of long decimals.

  • Improved hub onboarding: Hub setup now captures an editable hub name and agent configuration, reducing friction for new admins.

  • Accurate live ingestion counts: Source list and detail views now show live ingested-document counts instead of stale metrics, and the ingestion overview auto-refreshes with errors visible even after a workflow completes.

  • Google Drive error transparency: Auth/permission errors for Shared Folder ingestion now surface clearly (401/403/404) instead of opaque 404s.

  • Dashboard UX polish: Agent → Hub terminology alignment across the admin UI and instant org-switcher scrolling.

Bug Fixes

  • Document viewer formatting fix: The raw document viewer now preserves line breaks for non-URLList sources (including SharePoint records), so ingested content displays as intended.

February, 2026

Improvements

  • Redesigned Notes Column in Conversation History: The Notes column now shows note text when a conversation row is expanded. Clicking the text opens a popover with the notes and an Open message link, which navigates to the conversation page and opens the Notes tab in the QA panel.

  • Conversation History Column Persistence: Selected columns in Conversation History now remain visible after page refreshes or when accessed via shared links.

  • Auto-Open Message Feedback Panel on Thumbs Up/Down: The message feedback popover now opens automatically when a thumbs up or thumbs down is selected.

January, 2026

New Features

  • QA Mode for Admins: A new quality assurance mode that provides enhanced evaluation tools for reviewing AI Agent responses. Admins and super admins can access additional columns and filters in the conversation history to evaluate response quality.

  • Promoted Answers Management: Admins can now create, edit, and manage promoted answers directly from the dashboard. Configure specific responses for frequently asked questions to ensure consistent, accurate answers.

  • Conversation Notes: Add notes to conversations in the history view. Notes help teams track context, flag issues, and collaborate on customer interactions.

  • User Management: Comprehensive user management with the ability to:

    • Invite users via email
    • Add existing users to your organization
    • Manage user roles and permissions

Improvements

  • Enhanced Conversation Export: Improved Excel export format with better alignment, additional columns, and conversation column for better analysis.

  • Analytics Drilldown: Click through from analytics summaries to see the underlying conversations, making it easier to investigate trends and issues.

  • UI Support for Adding a Fluid Topics Source: Users can now add a Fluid Topics source directly from the interface.

  • Support for Adding Multiple URLs in Source Configuration: Users can now add multiple URLs at once from a Source’s Configuration tab using the ‘Add URLs’ button. This feature currently supports URL lists, YouTube playlists, and Sitemap source types.

  • Product Filter and Title Search in Conversation History: Added product filtering and title search to help users quickly find and review relevant conversations.

  • Show Human Query in Expanded Conversation History: The expanded view now displays the human query, providing better context and improving review clarity.

  • Trigger Ingestion UI Improvements: The ingestion overview now auto-refreshes and shows errors even after a workflow is completed, improving visibility and monitoring.

December, 2025

Features

For backward compatibility, existing links to https://copilots.rapidflare.ai will continue to work and redirect to the new unified dashboard experience.

Improvements

  • Hyperlink Support in QA Panel Notes: Notes in the QA panel now support hyperlinks, allowing users to add clickable references, resources, or documentation.

  • Add Description Field for Source: A description field has been added to source configuration to provide context and improve understanding of each source.

  • Enhanced Ingestion Progress Details: The ingestion progress view now includes Triggered By, Triggered At, and Workflow ID for better tracking and visibility.

  • Export Functionality in Sources Dashboard: Users can now export all ingested sources directly from the Sources Dashboard for reporting and analysis.

  • Google Drive Shared Folder as Source: Support for Google Drive shared folders has been added, enabling ingestion and management of content directly from shared folders.

October, 2025

New Features

  • Agent Model Selector: Administrators can now select which AI model powers the agent, choosing between different AI providers and configurations for optimal performance based on your specific needs.

  • Integration Management Page: New integrations page showing all connected services (Discord, Slack, etc.) with easy configuration and status monitoring.

Improvements

  • Redesigned Dashboard Navigation: Updated information architecture with improved header, context-aware side navigation, and copilot landing pages for easier navigation.

  • Source Description Filters: Filter sources by description text in addition to URL and title, making it easier to find specific content.

  • Clickable Links in Ingestion Summary: Links in the ingestion summary are now clickable, enabling users to quickly access related sources or content for faster verification and navigation.

  • Search Users in Conversation History: Users are now searchable within the conversation history page for faster filtering and review.

September, 2025

New Features

  • QA Panel
    • Introduced a QA panel in the conversational interface that provides detailed evaluation for each query. You can read more about QA Panel described here.

Improvements

  • Improved Security for your API Keys

    • The API key management experience has been greatly improved. All new API keys you generate are now publishable and can be safely included in your website or application code. Our backend automatically protects your API key from abuse, spam, and bots, so you do not need to worry about exposing it publicly.
    • You can specify a list of allowed domains when creating your API key. Our backend systems will only allow requests coming from domains you choose to allow-list. Specifying domains is optional but highly recommended. You can read more about our updated API key management described here
    • Existing API keys continue to work as before without any action needed on your end. However, we strongly recommend that you generate a new API key from our admin dashboard under Hubs » Configure » Security with your trusted domains, and update to the latest version of our Embed SDK in your web app as described here.

  • Persistent Sort & Filter in Conversation History: Sort and filter settings in conversation history now persist even after navigating away, ensuring users can maintain their preferred view and easily track relevant conversations without reapplying filters.

July, 2025

Improvements

  • Improved Search Experience

    • The search experience have been improved enabling rapid locating of documents across sources.
    • The search results can now be further sorted and filtered helping you locate the content you were looking for more effectively,these results can be shared to other admins as well by simply copying the URL, reducing time to spot specific content.
    • The search results can be downloaded as spreadsheet by clicking the download button next to the search button.

  • New Source Types: Added support for new information source types:

    • Google Drive Shared Folders: Connect shared Google Drive folders to automatically ingest documents.
    • Fluid Topics: Import content from Fluid Topics documentation platforms.

  • Source management improvements

    • The content tab now allows for filtering based on the document's URL, title and enabled status.
    • Enhanced and easier editor for source configuration.

  • Ingestion

    • Added ability for admins to revisit and review the last committed ingestion. Click on the VIEW INGESTION SUMMARY button in source page to see the details.
    • More descriptive and useful error logs for rapid solving of ingestion related issues.
    • You can now export the ingestion details as a csv by clicking the download button near the ingestion status of the workflow.

May, 2025

New Features

  • Analytics Drilldown: New analytics drilldown feature allowing admins to click through from high-level metrics to see the specific conversations behind the numbers.

  • Live Ingestion Monitoring: View actively running ingestions directly from the sources list page with a compact progress overview. No need to navigate to individual source pages.

  • Document Content Viewer: New dedicated page for viewing extracted content from documents, showing exactly what text the AI Agent uses from each source.

  • Content Tab Filters: Filter content within sources by document URL, title, and enabled status for easier management of large knowledge bases.

Improvements

  • Improved Source Details UI: Redesigned source details pages with better organization of overview, content, and configuration tabs.

  • Search Across Sources: Global search functionality to find content across all sources from the top navigation.

  • Starter Prompts Auto-Generation: Generate starter prompts automatically based on your product catalog and content, customized for your specific products and use cases.

March, 2025

New features

We have a number of new features for Admins.

  • Information Sources

    • You can now add various sources via the dashboard. Please note that only the following source types are supported at the moment.
      • URL list: Provide URLs of web pages to extract and retrieve the web page content.
      • Glossary: Link Google Sheets containing table of related words and terms.
      • Product catalog: Link Google Sheets featuring product features and specifications.
      • YouTube playlists: Specify YouTube playlists to extract and gather data from videos within the playlist.
    • Source details pages contain the detailed information about the content used by AI Agent to generate responses in conversations
      • You can disable or enable a source to control the information AI Agent uses to respond.
      • Overview tab: Provides users with the latest details of the source, such as, the last time a source was ingested or who triggered the ingestion etc.
      • Content tab: List of the currently ingested documents used by AI Agent to respond to queries. Click on a content to view more details.
      • Configuration tab: Modify the configuration used to ingest the source.
    • Document details pages let the user view the actual text content used by AI Agent. Individual documents can also be enabled or disabled to control what information is available to the AI Agent.
    • Content Search
      • You can now search and find content across sources, available in the top-right of sources page. Search results are categorised into tabs based on source type for easier and efficent lookup. Click on a search result to view the full document.
      • Token search: Find exact matches for your query, helpful when the exact wording is known.
      • Similarity match: Find semantically close matches to your query.

  • Ingestions

    • You can now manually trigger ingestions on sources, allowing self service refresh of the AI Agent's knowledge for more accurate and up-to-date responses.
    • All actively running ingestions can be found in the sources page with a compact overview of the progress.
    • Click the source name in active ingestions to enter the source details page for comprehensive stage-by-stage progress and error logs.

  • AI Agent Configuration

    • You can now auto-generate starter prompts customised to the products and product families available. Users with elevated controls can additionally specify the nature of the prompts and range of products it must cover.

February, 2025

New features

  • You can now add an icon from a vast library of icons to each starter prompt category. This icon will be displayed next to the category name in the list of starter prompts.
  • You can now handoff a conversation to a human support agent. This feature is available in the conversation screen and allows users to transfer the conversation to a human agent for further assistance.
    • This feature is disabled by default. Contact us at support@rapidflare.ai if you would like to enable this this feature for your enterprise.

Bug fixes

  • Fixed a bug where the AI Agent would not scroll to the bottom of the chat window when new messages were received.

Dec 6, 2024

New features

  • You can now generate your own API keys in the configuration section of the admin dashboard. You can generate API keys and define expiry dates for them. API keys can be used to access the AI Agent API or to integrate the AI Agent widget into other websites. API keys can be revoked at any time, and the expiry date can be extended or shortened as needed.

  • We now support Single Sign On via Okta and other identity providers. See here.

  • Roles. We've introduced the concept of Roles and role based access control into the product.

  • Can enable/disable slack AI Agents via the dashboard

Bug fixes

  • Fixed a bug where conversation artifacts such as comparison tables would sometimes fail to get downloaded as a PDF file.

Sep 5, 2024

Bug fixes

  • Fixed a bug where the user would get logged out of the dashboard sooner than expected.
  • Fixed a bug where the theme selection was not being remembered between sessions. Now the light or dark theme is sticky and remembers the choice on the same browser correctly.

New features

  • You can now download a conversation as HTML, Markdown, PDF, JSON or Excel from the AI Agent conversation screen. This is similar to the admin dashboard conversation history export feature.
  • Analytics page has been revamped with more actionable metrics, and deep links back to conversation history.

Improvements

  • New search field in the conversation history table in the Filter by user menu to search for specific conversations by one or more users.
  • Deprecated conversation feedback: The feedback feature has been removed from the conversation history screen. You can still provide feedback on individual messages in the conversation history screen.
    • The conversation feedback feature was removed because user's already had the ability to provide feedback on individual messages in the conversation history screen. The individual messages feedback are aggregated to provide an overall conversation feedback score.
    • Conversation history table view now has only a single column called Feedback instead of the 2 separate columns it had previously for Message feedback and Overall feedback which was confusing.
    • Conversation history table view now has a new Mixed feedback filter in addition to the Good feedback, Bad feedback, and No feedback filters. The Mixed feedback filter shows all conversations with a mix of both good and bad feedback.

Aug 24, 2024

New features

  • New sharing features for admins to enable users to share conversations.
    • Sharing Conversations: You can share a conversation through URL, email, HubSpot, or with anyone. Recipients of the shared link can view the conversation.
  • Conversation history
    • Now enables export to PDF. This allows viewing all the conversations, messages exchanged and feedback on conversations in PDF format.

Aug 9, 2024

We are catching up on our July release notes in this early August release notes update.

New Features

  • Admin dashboard AI Agent configuration screen now allows for a secondary color selection as well as text color selection in both light and dark modes.
    • Secondary color selection helps control the background color of chat mesages and input boxes.
  • Microsoft Social login enabled for both admin and AI Agent dashboards.
  • Conversation history
    • Now enables export to excel. This allows for faster review of conversations, messages exchanged and feedback on conversations in a more convenient format.
    • Filter by specific user IDs
    • Filter by specific types of conversation and message feedback
  • Provide Feedback: new navigation item to provide feedback to us on either the admin or AI Agent dashboards. You can attach screenshots too.

Improvements

  • More robust, improved configuration experience.
  • Improved storage for your logos. This makes rendering the configuration page faster.
  • Better visibility for what tabs have been edited in the configure experience.
  • Overall faster experience across the dashboard, especially conversation history.

June 25, 2024

Features

  • You can now use your voice to input your questions to the AI Agent. You can also listen to the response as audio by clicking on the speaker icon.

Improvements

  • Major redesign of the AI Agent chat experience. The AI Agent chat window is now fullscreen and works well on both mobile and desktop screens.
  • You can now see your recent conversations and all the content related to your current conversation on the right in a tab on desktop and on the bottom on mobile.
  • You can see a rich preview of any link in the AI Agent's answer or references by simply hovering your mouse ovr it.

Bug Fixes

  • Implemented virtualization for chat messages list to ensure that rendering of large chats with hundreds of messages will not be slow.

June 21, 2024

Improvements

June 7, 2024

Improvements

  • AI Agents dashboard, https://copilots.rapidflare.ai

    • Major refactor of user facing dashboard to a new technology stack, with lots of improvements and a slightly different look and feel.
      • Faster rendering for previously slow pages
      • Collapsible left navigation bar
      • More compact conversation history table with better controls for date selectors, filters and sorting of rows

  • Admin dashboard, https://dashboard.rapidflare.ai

    • Bring in new AI Agent versions for this week, enabling admins to get latest experience in the dashboard.

May 24, 2024

Improvements

May 10, 2024

Features

  • New: AI Agent users dashboard https://copilots.rapidflare.ai for non-admin users to access just the AI Agent, their personal past conversations and other related features.
    • Login the same way as you do to dashboard.
    • User guide documented at /product-overview/dashboard
    • Coming soon - full screen AI Agent experience.
    • Going forward, this what's new page will list updates to both the AI Agent users dashboard as well as the Rapidflare admin dashboard https://dashboard.rapidflare.ai.
  • Update to AI Agent version 1.5.1 (includes 1.4.2, 1.4.0, 1.3.0, 1.2.7)
    • AI Agent now streams responses by default
    • Properly indicate existence of message feedback in conversation history
    • Support advanced models and streaming responses
    • Better link sharing behavior
    • Expanded and expandable input box for typing multi line questions
    • Conversation history logs origin of conversations (e.g. slack, host URL)

Improvements

  • Rapidflare docs are now linked off the website providing convenient access.
  • Testflight now renders more margin at the bottom of the AI Agent screen to make it easier to access the bottom parts of the widget.

Bug Fixes

  • light and dark themes are now sticky and remember choice on the same browser correctly.
  • Improved behavior when conversation history has zero conversations in the time range being looked at.
  • Additional guidance length is expanded to 1500 characters
  • More robust handling of starter prompt reference specification. Just type each reference on its own line, or use commas (spaces don't cause issue) -- your choice.

Apr 26, 2024

Features

  • Conversation history can now be exported as markdown, HTML or JSON formats.

Improvements

  • User sessions are now longer running minimizing need to relogin. Sessions automtically refresh and last up to 7 days.
  • Deep links to dashboard are maintained when needing to pass through a login step.

Bug Fixes

  • Fix internal error when exporting conversations
Next
Core Platform