How Mantle fits together
When to use a chat, channel, direct message, canvas, agent, or task.
Written By Katja Danilina
Last updated About 1 month ago
Mantle brings team communication and AI work into the same workspace. Use this guide to pick the right place for each kind of work.
Choose where to work
Ask AI a question or develop an idea: start an AI chat.
Discuss a project with your team: use a channel.
Talk to one teammate: send a direct message.
Keep a side discussion next to one message: reply in a thread.
Write a plan or document together: create a canvas.
Give every AI chat the same company context: add workspace knowledge.
Reuse the same AI role and instructions: create an agent.
Repeat an agent job: create a task.
Let an agent work with another app: connect an integration.
Talk live: start a huddle.
Chats, channels, and direct messages
All three hold messages, but each starts with different people in mind:
Chat starts with an AI model or agent. Use it to ask questions, draft, research, or analyze files. Teammates with access to the workspace can open the chat and continue it.
Channel starts with the team. Use it for updates, decisions, files, and discussion. Mention an AI model or agent when you want its help.
Direct message starts with one teammate. Use it for a private one-to-one conversation inside your organization.
If the main participant is AI, choose a chat. If it's a group of people, choose a channel. If it's just you and one teammate, choose a direct message.
Select the + beside the workspace selector to create a chat, channel, canvas, or direct message. Agents and Tasks have their own + buttons in the left rail.
AI work can be shared
An AI chat doesn't have to end with one person. In a team workspace, other members can open it, see the context, and ask a follow-up question. You can also mention a model or agent inside a channel so its answer becomes part of the team discussion.
Knowledge stays close to the conversation
Canvases are living documents that people edit together.
Workspace context holds instructions, files, and selected canvases that AI can use across the workspace.
Agents can have their own smaller set of knowledge for a specific job.
Agents do repeatable work
An agent combines a model with a job description, knowledge, and optional connected tools. A task tells that agent what to do, when to run, and which channel should receive the result. For example, a support agent could read new feedback from a connected app every morning and post a digest in the customer-feedback channel.
Full guide: https://docs.mantle.chat/features/overview
Was this helpful?
More in Getting Started
What is Mantle Chat?Still need help? Ask the team