Category: Release notes

When creating a user group, the Workspace Administrator decides whether that group is visible to members of the workspace. A visible group can be granted access when sharing content. A non-visible group is restricted to administrators.

The generated meeting minutes now have three visibility levels: Private, Groups, and Workspace. The Workspace Administrator creates user groups. Users can then keep their meeting minutes private or share them with a group of which they are members. Three levels of visibility Visibility Who can see it Private Creator Groups User who is a member…

The Analytics app has a new Conversations page that shows, on a single screen and side by side, how the Chatbot and Studio channels are used over the period you choose.  Benefits What the page contains The page is split into two columns: Chatbot on the left (purple) and Studio on the right (yellow). Each…

Administrators now have a new app, Analytics, that shows, month by month and on a single screen, how their organisation uses Deeplink: chatbots, Studio, audio transcription, agents and users.  Benefits –> Find the comprehensive Handbook

You can now create expert sub-agents. A main agent receives the user’s request and automatically routes it to the expert sub-agent for the relevant domain. Each expert sub-agent answers only based on its own instructions and the tools available to it. Your users ask their questions from their Studio or from a chatbot. What’s new…

Deeplink Events can now produce ready-to-use Word documents (.docx) that follow your organisation’s format. You no longer need to copy AI output into a separate document and reformat it by hand. The agent writes the content straight into your branded template.  What’s new How to get started

While the assistant is working, you now see a brief description of what it’s doing, instead of just a loading indicator. When a request triggers tool calls—such as reading a document, searching your knowledge base, or browsing the web… the interface displays these intermediate steps in real time (e.g., “Searching documents…,” “Reading your_doc.pdf…,” “Searching the…

Conversations now open faster. Instead of loading every source upfront, the assistant returns its answer immediately and sources are fetched only when you actually click to see them. Ranking is computed on demand, so you no longer wait on source loading to read a response. You can now browse a fuller history of sources than…

You can now choose to configure the crawler to stay within the sub-page it’s given so it no longer crawls back to the home page. If you point it at a sub-page, it won’t follow links leading back to the home page or a previous page.