Claude Tag
Claude Tag is a team-oriented agent product from Anthropic that places Claude inside Slack as a shared AI agent. A channel member can mention @Claude with a task, after which Claude works in a hosted sandbox, uses the tools assigned to that channel, and returns its result in the same Slack thread. Unlike a private chatbot conversation, a channel session is visible to the team and can be steered by anyone in the channel.[1][2]
Anthropic announced Claude Tag on June 23, 2026 and released it in beta for Claude Team and Enterprise customers. The launch documentation described Slack as the first supported team platform and said Anthropic intended to bring the product to other work environments later. The launch version used Claude Opus 4.8.[1][2] The launch materials distinguish Claude Tag from its underlying model: they identify Claude Opus 4.8 as the launch model and describe Claude Tag as a Slack-based product that runs channel work in hosted sandboxes.[1][3]
| Field | Details |
|---|---|
| Developer | Anthropic[1] |
| Product type | Shared workplace agent[1][2] |
| Announced | June 23, 2026[1] |
| Initial status | Beta[1] |
| Initial platform | Slack[1] |
| Eligible plans | Claude Team and Enterprise[1][4] |
| Model at launch | Claude Opus 4.8[1] |
| Channel execution | Anthropic-hosted sandbox, one working session per Slack thread[3] |
| Identity in channels | Organization-provisioned service accounts[4][6] |
| Identity in direct messages | The individual user's Claude account[2][6] |
| Billing | Organization usage for channel work; individual account usage for direct messages[2][4][6] |
Release and product positioning
Claude Tag extended an earlier Claude in Slack experience from conversational assistance into longer-running agent work. In a help-center snapshot captured on July 20, 2026, Anthropic said the older Claude in Slack experience would switch to Claude Tag on August 3, 2026. The new system retained channel mentions, direct messages, and the Slack assistant panel, but added organization-owned identity, shared memory, scheduled work, proactive follow-ups, and access to organization tools.[2]
Anthropic described the product as the start of an evolution of Claude Code. The company said its internal version created 65 percent of the code produced by its product team, a figure reported as Anthropic's own measurement rather than an independent audit. It also described internal use for product metrics, support tickets, data analysis, and debugging.[1][10]
Anthropic styles the product name as "Claude Tag" and uses @Claude for the Slack identity that participants mention.[1][2]
How a channel session works
Mentioning @Claude with a request starts a working session for that Slack thread. Anthropic creates an isolated cloud sandbox for the session. Claude reads the thread and channel context, builds a checklist for longer tasks, calls tools that the channel is permitted to use, and posts the result back into the thread. Results can include a Slack reply, file, chart, document, hosted page, or draft pull request.[3]
The sandbox is temporary, while the Slack thread is durable. When activity stops, Anthropic releases the sandbox. A later reply rebuilds a new sandbox and resumes from the thread context. Files that existed only inside the earlier sandbox do not survive, so durable work must be posted to Slack, pushed to a repository, or saved in another connected system.[3][5]
Each thread has a separate session and sandbox. Two threads in the same channel do not share their active filesystem state, although they can use the same channel tools and shared memory. The execution engine is the same managed system used by Claude Code on the web. This allows Claude Tag to run code and produce working artifacts without giving it access to a user's local computer.[3]
Shared team behavior
Claude Tag treats a channel thread as a shared task rather than a private exchange. Anyone who can participate in the channel can see the work, reply with more context, redirect the approach, or continue work started by someone else. Once a session is active, a reply in the thread is sufficient; another @Claude mention is not required.[3]
Edits and deletions behave differently from new replies. Claude receives a note when an earlier message is edited but does not treat the edit as a new instruction. It receives no notice when a Slack message is deleted and may retain the version it already read. A participant who needs to correct the task must add a new reply.[3]
Anthropic also introduced proactive and asynchronous behavior. A channel can use routines triggered by a schedule, a channel watch, or a repository event. If ambient behavior is enabled, Claude may surface information from permitted channels and tools, report that work finished, or follow up when a thread has stalled. Scheduled work uses the same channel identity and access as a task started by a person.[1][3]
Channels, direct messages, and the assistant panel
Claude Tag is available through three Slack surfaces, but they do not all use the same identity or data access.[2]
| Surface | Identity and access | Visibility | Typical use |
|---|---|---|---|
| Channel mention | Claude's provisioned service accounts and the channel's configured connections | Everyone in the channel can see and steer the thread | Shared work the team should see and steer[2][3][6] |
| Direct message | The user's Claude account and personal connectors | One-to-one conversation | Personal tasks using the user's own data[2][3][6] |
| Slack assistant panel | The user's Claude account and enabled personal capabilities | A panel opened in the user's Slack window | Access to Claude from elsewhere in Slack[2] |
Direct messages are separate from the organization's channel agent. Work in a DM is attributed to the individual, and the organization-provisioned service accounts do not apply. Group direct messages are not supported. Organization owners can disable direct messages for the deployment.[6][8]
This separation also distinguishes Claude Tag from Claude Cowork. Anthropic's documentation positions Tag for shared work that a team should see and steer, Cowork for personal research and drafting in a Claude chat, and Claude Code for hands-on programming in a terminal or integrated development environment. Claude Tag uses the same type of managed agent execution as Claude Code on the web, but channel sessions use team-assigned service accounts rather than a developer's local credentials and filesystem.[3]
Identity, permissions, and administration
In a channel, Claude acts through accounts created for the agent rather than impersonating the person who made the request. Slack posts come from the Claude app. On GitHub, commits and pull requests created through the official integration are attributed to the Claude GitHub App. Other connected services use a service account provisioned for Claude.[4][6]
Only a Claude organization Primary Owner or Owner can configure Claude Tag access and channels; the Claude Admin role can view some settings but cannot complete setup. Pairing the app also requires a Slack workspace administrator. Setup links the Slack workspace, provisions Claude's identity, grants selected repositories and tools, sets an organization spending limit, and tests the agent in a channel.[2][4]
Access can be assigned at organization, workspace, and private-channel levels. Workspace permissions apply to public channels in that Slack workspace, while a private channel can receive additional credentials or repositories. Each narrower scope inherits access from the levels above it. This means that a private-channel grant should add only the access needed by that group, while the organization-wide baseline remains limited.[2][4]
Member controls differ by plan. A Team organization can leave the agent open to anyone in the connected Slack workspace or restrict it to Slack users who also belong to the Claude organization. Enterprise adds role-based access control through custom roles. These restrictions cover both channel requests and direct messages.[2][8]
Credential and network security
Channel work runs on Anthropic's infrastructure, not inside the customer's local network. The sandbox does not hold connected-service credentials. An Agent Proxy retrieves a credential from a separate store and injects it only when an outbound request matches an allowed rule. Network egress is denied by default except for hosts allowed by a connection or an access bundle.[5]
An owner can narrow a connection to a host, a path prefix, or read-only request methods. The external service sees Claude's own account, which makes actions attributable in that service's logs. Anthropic also provides an organization audit view for one-time and scheduled tasks and for network calls made through the agent identity.[2][5]
Claude has no access to external business systems until an owner adds connections. Within Slack, however, it can read and post in channels where it has been added and can search public workspace channels by keyword under Slack's normal search permissions, even when the app is not a member of every public channel. Workspace search is unavailable in channels that contain guests. Claude is disabled by default in guest-containing channels and does not operate in Slack Connect channels; organization Owners can configure guest handling, member access, and the scopes where the agent is enabled.[3][5][8]
Memory and data handling
Claude Tag keeps memory by place rather than by individual user. Notes learned in public channels can become workspace memory available to other public channels. A private channel can read the shared workspace memory, but facts learned in that private channel are saved only to its private store. Direct messages and other Slack workspaces remain separate.[7]
Channel members can ask Claude what it remembers, correct an entry, or tell it to forget an entry.[7] Anthropic's archived permission wording was inconsistent: a June 28 archive of the memory guide said an organization Admin could view a scope's memory files but only an Owner could edit or delete them, while a July 20 Help Center archive said admins could view, edit, and delete memory.[2][7] The memory is a curated set of notes, not a full transcript search. Claude can read past session transcripts when asked, but the user should identify a topic or timeframe because it cannot run full-text search across all earlier sessions.[7]
Slack conversations with Claude remain separate from conversations in the Claude web app. Slack-originated conversations do not appear in Claude chat history, and Claude web conversations are not exposed in Slack. If the integration is disconnected or uninstalled, Anthropic says it deletes the associated Claude-side conversation data within 30 days. Copies retained in Slack continue to follow the organization's Slack retention policy.[2]
Claude Tag retains channel memory and session transcripts so that work can continue across tasks. For that reason, it is not available to organizations using Anthropic's Zero Data Retention setting.[4][5]
Supported workflows
The product can perform a task only when its channel has the required context and connections. Anthropic documents both Slack-only workflows and tasks that act in outside systems.[1][3][9]
| Workflow | What Claude Tag can do | Required access |
|---|---|---|
| Channel catch-up | Summarize discussions, identify unresolved items, and assemble a status update[1][3] | Slack channel context |
| Documents and tickets | Turn a thread into a decision document, customer reply, planning outline, hosted page, or issue-tracker ticket[3][9] | Slack alone for drafts; an issue-tracker connection to file tickets |
| Data questions | Analyze permitted data, run code, and return a table or chart[1][3] | Access to the relevant data source and approved network access[1][5] |
| Support triage | Work through support tickets, draft responses, and report unresolved items[1][9] | A support or ticketing connection when action outside Slack is required[1][9] |
| Monitoring | Run a scheduled task, watch a channel, or respond to a repository event, then report the result[1][3] | A routine plus the relevant channel or repository access[3] |
| Software work | Read a granted repository, answer code questions, investigate a bug, make changes, and open a draft pull request[1][3][6] | A granted source-code repository[3] |
For repository tasks, Claude clones repositories granted to the channel into the hosted sandbox. It can inspect and edit code, push changes to a branch, and return a draft pull request under the Claude GitHub App.[3][6]
Thread-to-artifact tasks can work without an external connector when Slack already contains the needed information. If an organization connects an issue tracker such as Jira, Linear, or Asana, Claude can turn the same discussion into a filed ticket and post the link. Hosted pages are published on Claude's service and use channel-based access.[3][9]
Availability, billing, and prerequisites
Anthropic's launch announcement and a June 29 setup archive limited the beta to its first-party Claude Team and Enterprise plans. They excluded Pro and Free plans, third-party Claude deployments, and organizations using Zero Data Retention.[1][4]
Channel work is consumption-based and billed to the organization's usage balance rather than to each person who invokes it. Owners can set organization-wide and per-channel spending limits, receive threshold alerts, and review usage by channel. Work that would exceed a limit is declined. Direct-message work is billed to the individual's Claude account instead.[2][4]
The deployment depends on several administrators and external accounts. A Claude Owner must configure access, a Slack administrator must approve and pair the app, and each connected service needs a provisioned service account or official app installation for Claude.[3][4] The archived documentation gave two instructions about connections added after a thread started. A July 19 concepts archive said a new connection is checked on each request and can work in the running thread when the service is named; a June 29 setup archive told administrators to start a fresh thread because connections applied only to new threads. The July 19 archive also said a new thread picks up every kind of configuration change.[3][4]
Limitations
Anthropic's launch and help-center documents described Slack as the first supported team platform. They named no dates or platforms for the planned expansion.[1][2]
The launch and setup documentation excluded Pro and Free plans, third-party deployments, and Zero Data Retention organizations. Direct messages were one-to-one, with no group-DM support.[1][4][6]
Context is bounded. When Claude is mentioned partway through an existing Slack thread, the session receives up to 50 messages from the start of that thread after filtering replies from other bots. In a long thread, recent messages immediately before the mention may be outside that window, so critical details need to be restated. The working filesystem is also temporary, and unsaved sandbox files disappear when the session is released.[3]
All participants in an allowed channel work with the same agent permissions, regardless of their personal access to connected systems. Anyone in the channel can also steer the active task and manage its channel memory. Organizations therefore control the product through channel membership, scoped service accounts, network rules, member restrictions, spend limits, and audit logs rather than through the requester's individual credentials.[5][7][8]
References
- ^Anthropic, "Introducing Claude Tag," June 23, 2026, archived July 24, 2026
- ^Claude Help Center, "What is Claude Tag?," archived July 20, 2026
- ^Claude Documentation, "How Claude Tag works," archived July 19, 2026
- ^Claude Documentation, "Set up Claude Tag," archived June 29, 2026
- ^Claude Documentation, "Security and data handling," archived June 24, 2026
- ^Claude Documentation, "How agent identity works," archived June 28, 2026
- ^Claude Documentation, "What Claude Tag remembers," archived June 28, 2026
- ^Claude Documentation, "Restrict where Claude Tag operates," archived June 29, 2026
- ^Claude Documentation, "Turn threads into docs and tickets," archived June 24, 2026
- ^Ross Kelly, "Meet Claude Tag, Anthropic's new AI teammate that works in Slack," IT Pro, June 24, 2026, archived July 6, 2026
Improve this article
Add missing citations, update stale details, or suggest a clearer explanation. Every suggestion is reviewed for sourcing before it goes live.
1 revision by 1 contributors · v2 · 2,577 words · full history
Fact-checks are independent of edits: a reviewer re-verifies the article against its sources and stamps the date. How we verify
Reviewer note: Independent review using nine official sources and one independent report archived on or before July 24, 2026 (evidence cutoff July 28): product, plan, model, identity, billing, security, memory, workflow, and limitation claims checked; conflicting provider instructions on connection visibility and memory-role permissions are stated in the article.