Follow Discord
Sweep 03 Nov 2026 · 22:27Z Build v2.1.318 536 read Stable v2.1.311 Latest v2.1.318 Next v2.1.318 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Documentation 4 Nov 2026
One change · claude-docs

How Claude Tag works changedclaude-tag/concepts/how-it-works

Nearest release: v2.1.318, published 2 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Upstream edited this page at 4 Nov 2026 00:53 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 4 Nov 2026 01:07 UTC.

Upstream edited
Recorded here
Lines+3added
Lines−3removed
From line 101 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits26to this page, all time

The whole hunk

from line 101, old and new numbered
/
lines
from line 101
101101| | Claude Tag | Cowork | Claude Code |
102102| :- | :- | :- | :- |
103103| Where | Slack channels | claude.ai chat | Your terminal or IDE |
104| Whose access | The team's: service-account credentials an admin sets per channel | Yours: your personal OAuth connectors | Yours: your local credentials and filesystem |
104| Whose access | The team's: service-account credentials an admin sets per channel, plus your [personal connectors](https://claude.com/docs/claude-tag/concepts/personal-connectors.md) for your own tasks, with your approval | Yours: your personal OAuth connectors | Yours: your local credentials and filesystem |
105105| Who sees the work | Everyone in the channel | Just you | Just you |
106106| Best for | Shared work the team should see and steer | Personal research and drafting | Hands-on coding in your own checkout |
107107 
108The short version: **team work → Claude Tag; personal work → Cowork or Claude Code.** Claude Tag's connections authenticate the agent itself with service accounts, not any person. Personal connectors apply in a one-to-one Claude Tag DM, which runs on your own claude.ai account, the same way Cowork does.
108Claude Tag connectors authenticate the agent itself with service accounts, not any person. Personal connectors apply in a one-to-one Claude Tag DM, which runs on your own claude.ai account. Claude can also [use them in a channel](https://claude.com/docs/claude-tag/concepts/personal-connectors.md) for your own tasks, after you allow it.
109109 
110110## Key concepts
111111 
112112Three ideas recur across this page and the rest of these docs.
113113 
114* **Agent identity**: in channels, Claude acts under its own service accounts that an admin provisions, not as the person who asked. What it can reach is set per channel, so everyone in a channel works with the same access. See [How agent identity works](https://claude.com/docs/claude-tag/concepts/agent-identity.md).
114* **Agent identity**: in channels, Claude acts under its own service accounts that an admin provisions, not as the person who asked. What it can reach is set per channel, so everyone in a channel works with the same access. Claude can also [use your personal connectors](https://claude.com/docs/claude-tag/concepts/personal-connectors.md) there for your own tasks, after you allow it. See [How agent identity works](https://claude.com/docs/claude-tag/concepts/agent-identity.md).
115115* **Scheduling and long-running work**: a task can run on a schedule, follow a pull request and act when it changes, or keep going across many turns in one thread. The same channel access applies whether a person or a schedule started it. See [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md).
116116* **Memory**: Claude keeps notes for each channel, and the workspace notes it saves from public channels are read in every channel in the workspace. See [What Claude remembers](https://claude.com/docs/claude-tag/users/memory.md).
117117 
Feedback