Use case · Products
Agents inside your app.
An assistant inside your product helps each user get things done in plain words.
Users find answers and finish tasks without leaving your app. The assistant can only do what that user is allowed to do.
How it works
Step by step.
Press play, or click through it yourself. Try the switch above the drawing.
Try it · The user wants to
your appyour dataassistantagentyour user
01Your app, with an assistant built into a panel.
01 / 06
Where it's used
One idea, many industries.
- 01Project tools“Which of my tasks are late?” gets answered from the user's own projects.
- 02Online shopsShoppers ask about orders and returns in the shop's own chat.
- 03IntranetsStaff ask for a policy and get the paragraph that answers it.
- 04Analytics productsUsers ask a question in plain words and get the chart.
How Promptise makes it work
Built on the agent and interface.
In code
A peek at the code.
- 01One call per message from your app.
- 02The session keeps the conversation.
- 03Another user can't open Maya's session.
assistant.pypython
from promptise.conversations import generate_session_id session = generate_session_id() reply = await agent.chat( "Which of my tasks are late?", session_id=session, user_id="maya", # this chat belongs to Maya, and only Maya)