Think of Claude as a friendly, hard-working addition to your team - speak to it naturally and give it very specific instructions about exactly what you’d like it to do. It can help with summarization, creative and collaborative writing, Q&A, and more. Claude will remember your entire Slack thread and can iterate on the task at hand, just like an engaged employee.
Tag @Claude in your message. Claude will respond in a thread that anyone in the channel or group DM can see. Follow-up requests can be made by again mentioning @Claude in the thread.
Interact with Claude by simply messaging it. Claude will respond right in the top level of the DM, just like messaging a coworker!
For a quick tutorial on how to interact with Claude, and what you can use it for, see our Tutorial.
FAQs
The Claude app will ask for permissions to view messages and content for those channels and direct messages it has been added to. This allows Claude’s responses to take into account the full history of the conversation, not just the latest message. It can also view users and channel names and descriptions, which helps it engage in multi-person threads and use the channel description as context for the conversations.
Claude will not be able to see the content of other channels and DMs that it is not in, unless explicitly invited.
We do not use your conversations with Claude to train models. We will retain data for a limited period to understand how the bot is being used and plan our roadmap. Data is only collected in DMs and in threads in which you have tagged Claude.
- 🎭 Claude is “playing a role” as a helpful assistant. It will often incorrectly report its own abilities, or claim to be “updating its memory”, when in fact it does not have any memory of prior conversations!
- ➗ Claude will often make mistakes with complicated arithmetic and reasoning, and sometimes with more basic tasks. If given a long list of instructions it will often make mistakes when attempting to comply with all of them.
- 👻 Claude still sometimes hallucinates or makes up information and details. It will occasionally fill in information from its memory that isn’t present in long documents it’s presented with when asked questions.
- 🌐 Claude has read a lot on the internet, so it knows things about the real world, but it does not have internet access.
- ⏳ Claude was trained on data that can be up to 2 years out of date.
- 📅 Similarly, Claude does not know today’s date, nor does it know about current events.
- 🔨 It cannot (yet!) take actions in the real world — but it can suggest actions to take.
- 📇 It cannot (yet!) look things up — but it can suggest what to look up.
Thank you for helping us improve Claude! Please send feedback and bugs to support@anthropic.com.