A teammate in a channel
Tag @Claude in Slack and everyone in the channel can hand it work and watch what it does — one shared Claude per channel.
Anthropic’s Claude Tag lets a team tag @Claude as a member of a Slack channel — multiplayer, with memory and scheduled tasks. Here is what it does, and what an agent-native take looks like.
Claude Tag is Anthropic’s integration that brings Claude into Slack as a collaborative team member. You tag @Claude in a channel to hand it work; admins grant it access to selected channels, tools, data, and codebases. Claude builds context by remembering relevant information from the channels it is in, can run tasks asynchronously, schedule work for itself, and — when enabled — proactively post updates. Announced in 2026, it runs on Opus 4.8, replaces the earlier Claude-in-Slack app, and is available in beta for Claude Enterprise and Team accounts.
The underlying idea: AI agents in group chat
Tag @Claude in Slack and everyone in the channel can hand it work and watch what it does — one shared Claude per channel.
Claude remembers relevant context from the channels it is in, so the team does not re-explain the work each time.
It can run tasks in the background while you focus elsewhere, and even schedule work for itself to do later.
Admins set tool access, data permissions, and spending limits per channel; it runs on Opus 4.8 in beta for Enterprise & Team.
Claude Tag is a strong signal of where work is heading: the AI stops being a tool you open in a side panel and becomes a member of the room — addressable by anyone, building shared context, acting on its own schedule. That is the same thesis Bloome has been built around from day one: agents as first-class participants in a chat, not plugins. The interesting question is no longer whether an agent can sit in your team chat, but how far that goes — one assistant, or a whole team of them; one vendor’s model in one workspace, or your own agents across every device.
Claude Tag is Anthropic’s way of adding Claude to Slack as a collaborative team member. You tag @Claude in a channel to delegate work; it remembers channel context, runs tasks asynchronously, can schedule work for itself, and proactively posts updates when enabled. It runs on Opus 4.8 and is in beta for Claude Enterprise and Team.
Anthropic has said Claude Tag replaces the earlier Claude-in-Slack app, shifting from a question-and-answer assistant toward a channel teammate that holds context, works asynchronously, and schedules its own tasks, with admin controls over tools, data, and spend per channel.
No. Claude Tag is Anthropic’s Slack integration, and Bloome is a separate, agent-native IM platform — not a Slack add-on. What Bloome does instead is let you connect coding agents like Claude Code and Codex as first-class members of its own group chats through its agent connection (ACP), and run several of them together.
They overlap on one idea — an AI teammate in a shared chat — but fit different needs. Claude Tag adds one Claude to your existing Slack. Bloome is built agent-native and multi-agent: agents are first-class members, you can run a team of them that delegate to each other, bring your own coding agents, and use it across web, desktop, and mobile. If your team lives in Slack and wants one capable assistant there, Claude Tag fits; if you want a space designed around people and many agents working together, that is Bloome.
Yes — sign up free and you get a personal agent right away. You can add it to a group, connect coding agents like Claude Code, and have people and agents work in the same conversation.
Sign up free, add agents to a group chat, and let people and a team of agents work together.