The AI Assistant lets your users ask a question in their own words and get a written answer, drawn from the Userlane content you have published, without leaving the application they are working in. Instead of searching through a list of Guides or articles, a user describes what they need, and the Assistant replies, points them to the next step, and connects them to support when it cannot help.
This page explains what your users experience when they use the AI Assistant. To turn it on and set it up, see Configuring the AI Assistant. To get the best answers from it, see How to optimize content for the Userlane AI Assistant.
How it works
When a user opens the Assistant and asks a question:
The Assistant looks across the Userlane content you have published for that application, your Guides, Announcements, and any connected knowledge base, and writes a short answer from what it finds.
The answer shows the source it used, so the user can see where it came from and open it.
Where it helps, the Assistant offers a next step. It can start a Guide, open an Announcement, or open a linked document.
It suggests a follow-up question the user might want to ask next.
If it cannot answer from your content, it points the user to the support contact you have set.
What your users can do
Ask in their own words. Users type a question the way they would ask a colleague, in their own language, and the Assistant replies in the same language.
Get an answer with its source. Each answer shows the Guide, Announcement, or article it drew on, so users can check it and read more.
Take the next step. From an answer, a user can start a Guide, open an Announcement, or open a linked document without leaving their task.
Ask a follow-up. The Assistant keeps the thread of the conversation, so users can refine or build on the previous answer.
Start a new chat, or return to a recent one. Users can start a fresh conversation at any time, and pick up a recent conversation later.
Reach support. When the Assistant cannot help, it surfaces the support contact you have set, so a user is never left at a dead end.
How the Assistant decides what to answer
It answers from your content first. The Assistant is grounded in the content you have published. It does not invent answers about your application.
General knowledge is optional. If a question is not covered by your content, the Assistant can fall back to general knowledge, and those answers are labeled as coming from general knowledge. You can switch this off for applications that should only ever answer from your own content (see Configuring the AI Assistant).
It stays off topics you restrict. You can tell the Assistant which topics it should not answer on. On those topics it declines, and where relevant points the user to support.
It answers in the user's language. The Assistant replies in the user's language, based on their Userlane language settings.
What you can configure
As a manager you control how the Assistant behaves for your users: whether it is on and who sees it, its name and welcome message, its tone, the topics it will not answer on, whether it can use general knowledge, and the support contact it hands off to. See Configuring the AI Assistant for the full list and steps.
Getting the best answers
The quality of the Assistant's answers depends on the content behind it. See How to optimize content for the Userlane AI Assistant for how to write and structure your content so the Assistant can answer well.
Good to know
The Assistant keeps recent conversations, so a user can return to a chat and pick up where they left off.
The Assistant only draws on content the user already has access to. It does not surface anything a user could not otherwise see.
Answers are generated by AI and should be checked for accuracy.
Related Articles
Configuring the AI Assistant
