Release Notes

August 2026

OpenDialog 4.0

OpenDialog 4.0 is here! This is our first release under a new, regular major-version cadence with clearly communicated support windows: the current major release is fully supported, and when a new major ships the previous one receives a three-month transition period of security and critical fixes. 4.0 also moves the platform onto PHP 8.5, keeping OpenDialog on the latest fully supported runtime.

Deprecations and removals

As part of 4.0 we are clearing out long-deprecated components. The following are removed in 4.0:

• The legacy webchat. New scenarios have used the new webchat for some time. If you still have a scenario on the legacy webchat you can move it yourself — see Converting a scenario to the Chat UI below. The legacy message delivery acknowledgement endpoint (POST /acknowledge) goes with it; the Chat UI has no equivalent and does not need one.
• The Voice/Alexa module, including the Alexa platform, the Alexa interpreter and skill synchronisation.
• The legacy NLU interpreters: Microsoft LUIS, Microsoft QnA Maker, Rasa, Amazon Lex and Google Dialogflow.
• The Azure Custom QA interpreter.
• The Conversation Analysis interpreter.
• The Google PaLM language model, which has been discontinued by Google.

The following are deprecated in 4.0 and will be removed in 5.0:

• The OpenAI interpreter — replaced by Language Services backed by language model configurations.
• The OpenAI language processor — likewise replaced by Language Services.

Deprecated components are frozen: existing configurations keep working and stay editable, but you can no longer create new ones. This includes importing or duplicating a scenario that carries one, which will now fail.

Any scenario using a component on either list shows a warning icon on its card in the scenario list. Hover the icon to see which components are affected and which release removes them.

Converting a scenario to the Chat UI

Scenarios still on the legacy webchat can be moved to the Chat UI from the scenario list. Open the scenario’s ⋮ menu and choose Convert to Chat UI — the option only appears on scenarios that are still using the legacy webchat.

The scenario is converted in place. It keeps its ID, app key, aliases and publish state, and your existing settings are carried over wherever the Chat UI supports them. There is no need to recreate the scenario or re-point anything that refers to it by ID.

When the conversion finishes you are shown a short report covering:

• Any settings sections that were removed because the Chat UI does not support them. The Comments section is removed for every conversion.
• Any settings the Chat UI does not recognise. These are kept but no longer have any effect.
• Your original settings, which you can expand and copy for your records.

One step is left to do yourself: update the embed code on your site so it loads the Chat UI script. Your scenario ID and app key have not changed, so only the script source needs to change. You can copy the new snippet from the scenario’s Interface settings page.

If you have any questions about migrating away from a deprecated component, you can get help via our support form - https://opendialog.ai/support.

Improvements

• Fixed single action-run CSV downloads being truncated, and export filenames now include the scenario name
• Fixed Knowledge Service topic search returning no results beyond the first page
• Raised the static knowledge source limit to 300,000 characters
• Refreshed the Dynamic Attributes admin screen to align with the OpenDialog design system
• Continued webchat accessibility work, including improved screen reader support
• Hardened webchat asset delivery and error handling for more resilient embeds

July 2026

Faster conversations

We’ve completed a significant round of performance work on the conversation engine, substantially reducing the processing time for each chat message. Your users should notice snappier responses across the board.

Accessibility improvements in webchat

We’ve made a major investment in webchat accessibility. Automated WCAG compliance checks now run as part of every webchat release, and this month’s releases include improvements to keyboard navigation, focus management and screen reader support.

Selma and Analytics SDKs

The first versioned releases of the Selma embeddable assistant SDK and the OpenDialog analytics capture SDK are now available, delivered as versioned assets alongside webchat.

Improvements

• Buttons can now be displayed alongside the input field in the mini webchat layout
• Message log CSV exports are now processed in the background and delivered by email, so large exports no longer time out
• Replaced Google reCAPTCHA with Cloudflare Turnstile on registration for a smoother, more privacy-friendly sign-up
• Fixed an issue where embedding webchat in an iframe could be blocked by the browser
• Upgraded the underlying application framework to the latest major version, bringing many security and stability improvements

June 2026

Advanced Configuration for LLM actions

LLM actions now persist their full Advanced Configuration, giving you complete control over the model parameters used by your actions.

Improvements

• Log exports now include a date-range picker, so you can export exactly the period you need
• Started a programme of conversation engine performance improvements, with detailed per-turn latency monitoring
• Clearer behaviour when no response intent matches, and fixed the preview log refresh
• Webchat styles are now isolated from host page styles, preventing conflicts on embedded sites
• Fixed webchat handling of empty messages
• Cleaned up duplicated dynamic attributes

May 2026

Data Insights foundations

We are building a new Data Insights capability to give you richer reporting on how users interact with your AI agents. This month we laid the foundations: a dedicated reporting datastore and a new GraphQL API for querying interaction data, along with the aggregation pipeline that will power upcoming insights reporting. Watch this space!

Improvements

• API rate limits are now configurable per environment
• Raised the static knowledge source limit to 200,000 characters
• Re-engineered large CSV exports to stream their data, fixing failures on very large exports
• Fixed search result navigation in the search modal
• Fixed a CSRF issue affecting scenario aliases
• Strengthened session security, including signing key rotation for anonymous webchat sessions
• Various security and stability improvements

April 2026

Analytics data export

You can now export your analytics data for use in your own reporting tools. A new Analytics export page supports detailed and aggregated CSV exports with filtering by scenario, and a new public Analytics Data Export API gives you programmatic access to the same data. Export downloads are delivered via secure temporary links rather than email attachments.

For more information, see our Public APIs documentation.

Secret attributes and contexts

Store sensitive values such as API keys as secrets and reference them from your configurations, including language model configurations. Secret values are encrypted at rest and masked in the interface.

For more information, see our Secret Context documentation.

Improvements

• Added a minimum-similarity topic filter for finer control over knowledge retrieval relevance
• Added metadata fields to Topics and Topic Sources
• LLM actions using function calls can now force the model to call a function
• Added support for the “Powered by OpenDialog” badge in webchat interface settings
• Fixed creating a new attribute from a webhook response mapping
• Fixed message feedback settings being overridden at workspace level
• Fixed message ordering and text selection issues in webchat
• Various security updates, including an out-of-band patch release for a dependency vulnerability

March 2026

More control for Webhook V2 integrations

We’ve added several improvements to Webhook V2 to make integrations more flexible and reliable:

• Increased timeout for webhook calls
• New json_decode function in JMESPath mappings for response transformation
• mTLS authentication support for stronger secure integrations. Learn more in Mutual TLS (mTLS) Authentication
• Better testing panel support for @-syntax filter parameters

For more information, see our Webhook action documentation.

Improvements

• Fixed an issue where workspace list in the sidebar could be incomplete
• Fixed an issue where “Link opens in a new tab” only worked for the first image block in webchat
• Improved chat history query performance for faster history loading
• Fixed RAG vectorisation failure for certain cases
• Included additional security hardening and infrastructure stability improvements

February 2026

Updates to public API authentication

We’ve updated our internal authentication mechanism. You can now create more than one token and manage them on a centralized screen. Tokens have a limited, configured lifetime, and if the token has expired, that will be shown in this dashboard.

For more information, see our Public APIs documentation.

Expandable messages for better user experience

Introducing expandable messages in webchat! You can now configure text messages to display with an “See more..” option, allowing users to see a preview initially and then expand to read the full content when needed. This is particularly useful for longer messages, helping keep your chat interface clean while still providing access to detailed information when users need it.

For more information, see our Text Message page.

Enhanced webhook authentication

We’ve significantly enhanced our webhook action security with new authentication capabilities:

• Header-based authentication methods: Support for variable authentication headers. For example, you can construct HMAC signing
• Flexible filters: New filters available to support your header building

These improvements give you more control over how OpenDialog securely communicates with your external services.

Check our documentation on attribute filters for newly available filters.

Improvements

• Added ability to duplicate old webhook actions as new Webhook V2 format
• Fixed file re-upload issue for LLM actions when using files with the same name
• Improved webhook handling for empty request bodies
• Various performance and stability improvements throughout the platform

January 2026

Improved file support for LLM Actions

We are kick-starting the new year with improved support for file usage in your LLM actions! You can now use this feature with Azure OpenAI, Gemini, and Claude as well.

Small note that you can use any type of file with Gemini. For Claude and OpenAI you can use:

• Images: *.jpg, *.png, *gif;
• PDF files: *.pdf;

In addition, we’ve added nice UI to our testing panel to make file upload experience even more smoother.

Note: For file upload in LLM actions, contact us at hello@opendialog.ai to enable this feature on demand.

Improvements

This new release includes numerous technical improvements to ensure OpenDialog operates more smoothly. Additionally, the following updates have been made:

• Cleaned up console warnings for webchat.
• Made description fields for the knowledge service optional.
• Restricted the file attribute field on LLM actions to only use the FileCollection attribute.
• Implemented many security and stability enhancements.

November & December 2025

Updates to LLM actions

We are delighted to share many new and exciting developments regarding our LLM actions!

We’ve added support for the GPT-5 model and a new configuration for reasoning effort. You might notice slight differences in advanced configurations: we’ve updated them to reflect corresponding changes in OpenAI requirements. Old actions still work and appear as before.

We have added support for files in our LLM Actions! Simply specify a file collection attribute using the new “File Attribute” selector.

For more information, look at our documentation here.

Note: For file upload in LLM actions, contact us at hello@opendialog.ai to enable this feature on demand.

Exposing Knowledge Service API

Interact with Knowledge Services programmatically. Manage resources, batch upload documents, or build any other automation effortlessly. We’ve got you covered.

Read more in our docs here.

Static topics for knowledge service

We’ve introduced a new type for a topic in knowledge service: static. Ever wanted to query all available text from your source? Static topics let you do that. You can upload your text file or simply paste any text source you have, then query it all with the syntax %% service_name.topic_name %% without any query parameters.

For more details - check out our documentation.

Improvements

• Detailed and aggregated log export actions will now be delivered to you asynchronously via email.
• The value field on the global contexts page is now multiline.
• Fixed the popup for LLM actions prompt when it occasionally became unusable.
• Various security and stability improvements.

October 2025

New webhook action

New Features and Updates

Our brand new integration method with external resources is out! You can now:

• Utilize a variety of HTTP verbs.
• Use OD attribute syntax within URL-queries, path segments, or header values.
• Construct free-form JSON requests with inline values or OD attributes.
• Employ flexible syntax for mapping your JSON responses to OD output attributes.
• Save entire responses as strings.
• Access a new testing panel for this action.
• View action logs and aggregate information.

Contact us via email at hello@opendialog.ai if you want this feature enabled for your workspace. Otherwise, it will become the default setting starting with the next release. Existing webhook actions remain unchanged, but creating new ones will not be possible in the future.

Additionally, we’ve made several improvements to the actions page:

• The card’s header now displays the action name instead of the action type.
• All actions now have an optional description that will be displayed as a subtitle; if not provided, the action type will be shown.
• New webhook actions have an extra chip at the bottom indicating the HTTP verb used.

Check out more in our documentation.

July 2025

Role-based access

You can now manage user access with greater precision by assigning specific roles to users within your workspace. This ensures each user has access only to the functionality they need to perform their job. There are five available roles:

• Admin: Access to everything, including user management. Assign it to your power users who are responsible for the OD platform within your organisation.
• Editor: Has access to all features except user management. Ideal for builders and team members responsible for creating agents.
• Analyse Guest: Access to all scenario analytics. Assign it to stakeholders who are interested in monitoring your application’s performance and extracting business insights.
• Preview Guest: Access to all scenarios previews. Assign it to your QA team and people who need to interact with the bot during development.
• Preview & Analyse Guest: Access to both preview and analyse within all scenarios. Useful for users whose role might require both testing and monitoring your agent.

For more information, look at our documentation here.

Improvements

• Resolved issue with fixed intent selection being hindered by the custom message editor.
• Fixed message ordering issue in WhatsApp.
• Implemented various improvements to the performance and security of our platform.

June 2025

Security section in the Interface Settings

We now have a brand new security tab for webchat interface settings which allows you to fine-tune your security requirements to validate anonymous access to the webchat, CSRF settings and specify authorized domains from which webchat should be accessible.

Whatsapp and SMS integration

We are happy to announce that you can plug in OpenDialog conversations into WhatsApp or SMS so users can have more ways to interact with your OD application.

Use the conversation designer to configure channel-specific messages like WhatsApp quick replies, cards, and carousels. Go to Analyze to see interaction logs from various channels.

Note: currently this feature is available on-demand, so if you want to try it out, reach out to our team via email hello@opendialog.ai.

Improvements

• Removed extra confirmation toast when saving LLM Action with moderation off;
• Fixed header wrapping issue on a Webhook action;
• Fixed accessibility issue for minimize icon;
• Fixed issue where Analyze does not show Selected App intent information;
• Fixed download chat transcript functionality for SDK usage;

Important deprecation notice

Just a reminder that from this month onward, the following endpoints are no longer supported:

• /incoming/chatApi
• /chatApi-config
• /user/{user_id}/history
• /user/{user_id}/history/file

If you have any issues regarding the above, you can get help via our support form - https://opendialog.ai/support.

May 2025

Important deprecation notice

We’ve been undertaking a number of technical enhancements to streamline OpenDialog’s internal systems, boosting performance, reliability, and security. As part of this work, the next major release will deprecate the following API endpoints

• /incoming/chatApi
• /chatApi-config
• /user/{user_id}/history
• /user/{user_id}/history/file

Don’t worry - you don’t need to do anything from your side if you are using chat embed code or SDK!

However, if you are calling these endpoints directly from application code, you will have one month to align with the new API structure. Please refer to the detailed upgrade guide to find out what steps are.

Refreshed look for scenario visualizer in preview

We made our scenario visualizer in preview and analyse a bit more convenient and useful when it comes to debugging your conversation:

• We added icons in section headings for better visual feedback;
• More information about run actions;
• Actions and conditions are now clickable and take you to where they are defined

Improvements

• Fixed Chatwoot integration when unable to send multiple messages in one go;
  • Also corrected Chatwoo client returning the wrong inbox source_id when contact has more than one inbox attachment;
• Fixed actions indicator component for USER intent card;
• Fixed interpreter confirmation popup shows even if no changes;
• Improved anti-brute force mechanisms and account locking;
• Fixed Z-index issue with attribute value sliding drawer on LLM Action page;
• Fixed missing “Download LLM action log” in scenario visualizer;
• Various important security patches;
• Few minor fixes on “My account” page.

April 2025

Visible actions and conditions on intent cards

To enhance clarity regarding conditions and actions tied to specific intent within Conversation Designer, we are rolling out an update that will visibly mark intent cards when they contain associated action or condition. Additionally, we’ve incorporated straightforward edit links directly on the interface of each intent card for immediate access to thisi elements:

Security updates

This release includes several important security updates. One of them being a stricter password policy. If your current password does not meet new strength criteria, upon next login you’ll be prompted to reset it in accordance with these updated guidelines:

Improvements

• Fixed bug with empty bubble causing stalled conversation due to empty message;
• iframe option now has no effect when using SDK;
• Fixed intent links in conversation preview;
• Fixed bug for priority interpreter not set upon scene creation;
• Appearance improved and adjusted the wording to be clearer: “View all” button appears;
• Correctly on Language Services sidebar even with an overloaded interface;
• Clarity of status indicators enhanced across Knowledge Service topics page.

March 2025

“Tutorials” sidebar menu item

The first update for this month is a new sidebar item “Tutorials” featuring various how-to guides. We’ve added this enhancement to improve your learning experience, allowing you to access our learning videos, documentation links, and additional resources all in one convenient place.

API for pre-populating user context for full-page webchat

The second one is a new API endpoint you can use for pre-populating user context for a conversation in full-page webchat. You send us initial attribute values for a given user, and in return, you’ll get a link for a full-page webchat for this user with this data ready to go. More information is available in our docs.

Improvements

• Fixed carousel slider styles;
• Fixed language switching in webchat via 3-dots menu;
• Removed redundant condition operator when there is only one condition;
• Added better feedback for webhook action failure so you can debug more effectively;
• Added links to language services in interpreter dropdown;
• Fixed default styles for tables and numbered lists in markdown messages;

February 2025

This month, we have released a significant update to the preview page and made several general improvements to the system.

We reflected on our preview page and redesigned it to make testing your conversations more efficient.

The preview console now takes up the full right side of the screen, featuring two tabs: “Conversation Logs” and “Attributes”. This layout allows you to see incoming and outgoing intents more clearly, with the considered and selected paths easily accessible.

In the “Attributes” tab, you’ll find an enhanced search function and filters. Additionally, custom attributes are clickable and will take you directly to their management page.

Setting custom attributes to test specific paths of your conversation has also become a lot easier, as you can now set multiple attributes.

For more information, please see the docs.

Improvements

• Fixed issue when Chatwoot integration is inactive by default
• Improved spacing for code blocks in markdown messages
• Made conversation intents clickable within considered and selected path panels
• Resolved bug with conditions during initial scene creation
• Moved the banner for quickstart AI agent to the Dashboard.

January 2025

Happy New Year! To start the year off with a bang, we wanted to give our messages even more flexibility. Which is why, in this release, we are happy to introduce markdown support for our text messages. In addition, we have been busy making improvements throughout the product, to make the usability of our product even smoother.

Markdown support in text messages

Our text messages now support markdown. You can create bullet lists, bold/italic text, headings, links, images, code blocks, and tables using standard markdown syntax, and they will be rendered in webchat. For more information, please see the docs.

Improvements

• Fixed the double-scroll bar issue on the preview page;
• Fixed leading and trailing whitespaces in webhook action headers;
• Fixed sidebar overlapping with incoming intents in preview;
• Improved messaging for the semantic classifier test panel when no intents matched.

December 2024

We are wrapping up this year with some user experience improvements and clearing some small flaws from our platform.

Better visibility for your vectorisation queue quotas

We are delighted to present a tracker for your vectorisation usage restrictions. Each Topic page now features a progress bar that shows the number of jobs currently in progress and updates each time you add new items to the queue until you reach the quota. This should help you better understand how many jobs you can have per topic at any given time.

Capacity tracker for vectorisation quotas

Improvements

• Order list of available actions in conversation designer side panel alphabetically;
• Fix visibility issue for existing conditions on message card in message editor;
• Fix reCAPTCHA resubmission issue;
• Improve performance for dashboard page.

November 2024

After all the significant changes we made in October, we’ve taken some time to further improve our existing features and improve usability across the platform, for you and your users.

Improved user experience

Does it sometimes feel like it takes ages for the AI Agent to reply and you are worried that your users might feel something went wrong, or simply give up? We’ve got you covered!

Introducing…OpenDialog’s interactive wait time indicator.

OpenDialog’s interactive wait time indicator

Using our interactive wait time indicator, will :

• Keep users engaged without causing anxiety that something might be broken
• Enhance the sense of immediacy of the AI Agent’s reply
• Provide agent ‘presence’ while the user is waiting
• Improve interaction quality and trust in your AI Agent

Give it a try in your scenario’s Interface Settings and immediately notice the difference between occupied and unoccupied time!

New Features

Improved indication in the navigation sidebar

We have made improvements to the navigation sidebar for language services and workspaces, as well as indicative labels for the different language service types.

Ability to duplicate actions

In the three-dot menu for any action, you can now find a new option to duplicate this action so you don’t need to start from scratch every time.

Condition Operators

So far, conditions in OpenDialog inherently were considered as using the ‘AND’ operator. We have now added the possibility for you to combine conditions differently, by letting you choose the operator that controls them : AND or OR.

Improvements

• Performance improvements for webchat
• Fixed date picker message broken in some cases
• Improved messaging for when the vectorization queue is busy
• Fixed appearance of the page with aliases
• Ability to expand the semantic classifier prompt field
• Fixed long strings breaking the formatting of a list message
• Fixed data mismatch between the analysis page and API data export
• Fixed embed code button visibility

October 2024

This month, we’ve got a LOT for you! Both things that please the eye and improve the quality of life on our platform!

New Features

New designs for login and registration screens

We’ve got a much better and slicker design for some of our pages, such as Login, Registration, and Reset Password.

New sidebar

Our new navigation pattern makes it easier for you to navigate the platform and accomplish your tasks more quickly. We’ve also uncovered some hidden gems like user management and attribute dashboard in case you knew it was there but were going to them via direct URL 👀

New way of creating scenarios

Say goodbye to the snake animation (my favorite) on the scenario creation screen and behold a brand new one with an updated “Start from scratch” template, the ability to import scenarios, and visual updates to this one

Improvements

So many improvements await you in this release, worth highlighting these ones:

• Allowed for different date/time formats via attribute filters.
• Updated the interface settings page to the latest relevant state.
• Added a setting in URL-source vectorization to omit HTML tags.
• New pop-up for prompt editing.
• Fixed the preview dropdown z-index.
• Fixed the “add scene/turn” button always showing the wrong sidebar on the first click.
• Fixed LLM Action output attributes not enforcing unique attribute names.
• Fixed the Card component being cut in half when the screen resolution is low.
• Fixed Activation toggles sitting outside of the Card component in LLM Actions.
• Fixed the confirmation popup when deleting an action.
• Activation toggles are now on by default on all system components.
• Unified the behavior of description fields.

September 2024

A significant milestone in OpenDialog’s evolution, bringing you an even more powerful way of building AI Agents!

New Features

Semantic Intent Classifier

Remember our intent classifiers? Imagine a world where you can define a simple list of intents and a short description for each, and thats it. No example phrases, nothing! Any semantically matching user utterances will be classified as you want. Guess what? We did it! With our brand new semantic classifier you can do just this - specify an intent name, give it a description, choose an LLM engine which will be used to perform classification and use it in your scenario.

For more details check out our documentation here.

RAG services

We now have our very own support for Retrieval-Augmented Generation (RAG) which gives you the ability to generate contextually relevant responses, based on a semantic search over a vectorised knowledge base. You can now use your data to feed into your AI agents and use this knowledge to drive conversations. Want your users to be able to ask questions about where to find a parking spot at your facility? No problem. You have complicated policy document and you want your AI agent to answer questions about its content? In OpenDialog, it has become as easy as ABC. With our RAG service you can use any custom URL, pdf, .csv, docx. xlsx file or just simply drop raw text and our RAG service will take it from there.

More in our docs here.

Improvements

• Fixed issue with processing composite JSON object an output attribute from wehbook action
• Fixed unexpected behaviour when no-matching / escalation
• Fixed override input field in new webchat causes blocking error
• Removed character limit for webhook action URL
• Removed ability to create outdated interpreters such as LUIS, QnA and RASA. Existing scenarios which uses them will still work
• Added soft wrap for long component names
• Fixed stretched cards on dashbaord
• Added new “step” property to number input
• Added ability to map attributes from another attributes in “Set Attributes” action

August 2024

New Features

LLM Actions

We’ve been working hard to bring you an exciting new way to interact with LLMs, called LLM Actions! It’s like a usual action which you can attach to an intent but which will leverage LLMs to perform a task. Give it a system prompt, specify output attributes, configure moderation - and make your AI agent respond with dynamic messages, extract specific information from user utterance, format request to upstream webhook and much more. Check out documentation for detailed usage.

Improvements

We didn’t forget to do some housekeeping in our product so we did a few fixes, such as:

• Fixed akward minimize/maximize webchat behaviour
• Fixed download chat link with iphone not working
• Fixed lower options are hidden in dropdown menu
• New gpt-4o-mini model support

July 2024

We’ve been busy tidying up our product and making a lot of improvements and bugfixes, including:

• Fix for message history is not consistently ordered
• Allow free input for standart autocomplete
• Support for cancel functionality for different message types

And much more 🎉

June 2024

New Features

• Added address autocomplete message
• Added new location attribute
• Added support for GPT-4o model

Plus various bugfixes and improvements 🎉

May 2024

New Features

Message Design: Introducing further support via the Message Editor to use the different message types that were introduced during the Proxima release. You can learn more on how to use these new message types here:

Message Types

Improvements

We also made some improvements & bug fixes throughout the core product, as well as webchat.

Some of the updates include :

• We have added GPT-4o to the managed available Language Services model
• We have added links in the Message Editor to the different message types for easy access
• We have updated the scrolling positioning when a message is served in webchat

April 2024

New Features

Accessibility :

Webchat is now compliant with WCAG 2.2 standard 🎉 It consist of many little pieces like:

• Changed color contrast
• Highlighted focused elements
• Improved visual validation feedback on forms
• Font sizes using Em instead of pixels
• Keyboard navigation
• Screenreaders can read webchat
• Semantic changes to webchat HTML
• and many more…

Improvements

We’ve made various improvements and bug fixes to the core product, including :

• Support for regex validation in form messages
• UI fixes to a set of webchat messages

March 2024

New Features

Interpreter Orchestration: By integrating Interpreter Orchestration into your workflow, it will allow for you to set highest priorities and be able to create smoother, more efficient running conversations with OpenDialog.

Note

Interpreter orchestration is a feature that is available ON DEMAND. If you would like to use this feature, please reach out to support@opendialog.ai.

Improvements

We also made some improvements & bug fixes throughout the product.

Some of the updates:

• Message Editor : Button message now defaults to not allow continued interactions
• Message Editor : You can now change the order of your message blocks using drag and drop

February 2024

New Features

• Attribute management: By integrating Attribute Management into your workflow, you can streamline the process of personalising conversations. Whether you’re modifying existing attributes or introducing new ones on the fly, this feature simplifies the customisation process, enhancing the efficiency of your interactions.

Improvements

A significant number of improvements & bug fixes have been made throughout the product to improve the conversation design experience.

Notable updates:

• Allow designers to add placeholder text to form messages
• Cancel button is now configurable in the message editor for form messages
• Fixed the OpenAI OD-managed language service to return results
• Fix to alias embed code to support nu-webchat scenarios

December 2023 - Proxima

New Features

• Language Services: Thanks to OpenDialog Language Services, you can easily manage your language model directly within the tool. This feature is now generally available (previously in Beta)
• Aliases : OpenDialog Aliases allows you to create a single point of reference for your Web Chat application. This functionality enables you to alternate different scenarios at any given time.
• NEW WEBCHAT!
  • OpenDialog webchat becomes more intuitive and highly customizable to adapt your branding through advanced Interface settings, theming, and custom messages.
  • Thanks to the integration with Speech-to-Text, users can now input their information and queries by voice.
  • Existing messages have been given a new look and feel, and a new set of custom messages has been introduced in new webchat as part of this release, and will continue to be updated in upcoming releases.

Improvements

OpenDialog Integrate has been enhanced with integrations that offer the possibility to send end-user requests through a ticketing system, to a live agent or trigger an e-mail.

September 2023

New Features

• Set Attributes to Value on Intents: You can now design intents to set a value against a certain attribute based on the fact that this intent gets triggered. As an example : you can add the value ‘done’ to an attribute ‘welcome’ based on whether or not the WelcomeIntent was triggered. This allows you to set up even more varied conversational flows determined by whether a user has ‘visited’ a certain intent, or segment a user by the fact that certain intents were triggered.
• Autosaving intents: With this release, we are introducing an Autosave functionality to the Intent settings in the Conversation Designer. You no longer have to remember to Save or Update your settings with every edit you make to your intents, we will do it for you - saving you time and headspace!

Improvements

• We have fixed a persistent bug in the product related to the description boxes for the different components in the Conversation Designer. All updates to these descriptions will now get saved and updated seamlessly.

July 2023

New Features

• Language Services: OpenDialog introduces Language Services, a centralized no-code interface for integrating, managing, and training your language models directly in OpenDialog. Available language services currently include : OpenDialog default intent classification, OpenAI-powered intent classification. Further language services will become available soon, including embeddings-powered Q&A.

Note

This feature is currently in beta release and available on demand. If you want to access Language Services, get in touch via support@opendialog.ai

• Send to Email: You can now trigger an e-mail to be sent during a user’s conversation with your application, personalizing its content with variables from the context.
• Microsoft Conversation Analysis Interpreter: OpenDialog allows you to integrate with your own language models via our Interpreter feature. Our Interpreter feature now also supports integration with the Microsoft Conversation Analysis service.
• Microsoft Question Answering Interpreter: OpenDialog allows you to integrate with your own language models via our Interpreter feature. Our Interpreter feature now also supports integration with the Microsoft Question Answering service.
• Webhook interpreter: In July, we also added a webhook interpreter to integrate with external language models without direct OD integration through webhooks.

Improvements

• We have added two new actions to the Action Library: storing the state of the conversation in the user context and returning to that state during the conversation.
• Persistence of the user context when using virtual intents
• Performance fixes

June 2023

New Features

• Freshdesk integration: The Freshdesk action lets you set up a connection between OpenDialog and your Freshdesk ticketing system, which you can then use within your conversation design.
• Conversation hand-off: OpenDialog now allows you to set up a seamless handover to a human agent without interrupting the conversation.

Improvements

• Improvements to Translate
• Performance fixes for Analyze