> For the complete documentation index, see [llms.txt](https://docs.eesel.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.eesel.ai/integrations/communication.md).
# Communication
Communication integrations put your AI agent in Slack, Google Chat, Discord, Gmail, email, Microsoft Teams and Calendly, so it answers your team where they already talk.
Communication integrations put your AI teammate in the places your team already talks, such as Slack, Google Chat, email and Teams. It answers in the thread from the knowledge you have connected, and links the source it used.
From that same thread it does work in your other integrations, such as looking things up and drafting replies, so a question and the work that follows it stay in one conversation.
| App | What your teammate does there | How you set it up | Availability |
| --------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- | --------------------------------------------------------------- |
| [**Slack**](/integrations/communication/slack.md) | Answers @mentions and direct messages in the thread from your knowledge, links the source, and keeps answering follow-ups. It also works your other integrations from that thread. | One **Add to Slack** approval | Self-serve |
| [**Google Chat**](/integrations/communication/google-chat.md) | Answers @mentions and direct messages from your knowledge, in the thread. It also works your other integrations from that thread. | Add the eesel app to a space, then connect it to an agent | Self-serve |
| [**Discord**](/integrations/communication/discord.md) | Answers @mentions in a thread off the message that asked, from your knowledge, and keeps answering follow-ups there. It also works your other integrations from that thread. | One **Add to Discord** approval | Self-serve |
| [**Gmail**](/integrations/communication/gmail.md) | Works one Google mailbox: searches messages, reads threads, drafts or sends replies, and manages labels. | A Google sign-in | Self-serve on most workspaces, ask us if yours shows Contact us |
| [**Email**](/integrations/communication/email.md) | Every agent has its own address. Mail sent to it wakes the agent, and it replies in the thread. It only writes to your workspace members. | Nothing to connect | Every agent |
| [**Microsoft Teams**](/integrations/communication/microsoft-teams.md) | Answers @mentions and direct messages from your knowledge. | A Teams admin uploads the eesel app | Not self-serve yet, contact us to turn it on |
| [**Calendly**](/integrations/communication/calendly.md) | Reads your Calendly bookings: who a meeting is with, who is hosting, when, and whether it is still on. Read-only. | One personal access token | Self-serve |
Not seeing your app? The [integrations overview](/integrations/overview.md) has the full list, and how to ask for one.
## FAQ
Which communication integration should I start with?
Start with where your team already asks questions. Slack is self-serve and is the most complete: your agent answers in the thread and can act in your other apps from there. Email needs no setup at all, since every agent already has its own address.
Can the AI agent reply to customers from these integrations?
From Gmail, yes: it replies as the connected Google account. The Email address only writes to your workspace members, and Slack, Google Chat and Teams answer the people in your own workspace. For a customer queue, connect a [helpdesk](/integrations/helpdesks.md).
Does eesel index my Slack, Google Chat or Teams messages?
No. Nothing from these apps is copied into eesel as knowledge. Your agent reads or searches messages live while it answers, and its answers come from the knowledge sources you have connected.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.eesel.ai/integrations/communication.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.