Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.250 Feeds RSS JSON llms.txt

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

Capture

One read of Claude Documentation

4 pages moved out of 216 read.

corpus-hash claude-docs-20260822T183713Z

claude-tag/concepts/how-it-works Changed · +5 / -3 lines

from line 8
 
 Claude Tag is Claude, working inside your team's Slack channels. An organization Owner gives it its own accounts to the tools your team uses, so it arrives already able to act, and anyone in a channel can tag it into a problem without setting anything up.
 
-When someone tags Claude in with a task, a working session starts for that thread. Claude works through the task and posts the result back into the conversation. It runs in an ephemeral cloud sandbox that Anthropic hosts, not on your local machine or inside your network.
+When someone tags Claude in at a channel's top level, the channel's own [session](/docs/claude-tag/concepts/glossary#session) picks the message up. A task that needs investigation, tools, or a longer exchange gets a working session in a thread under the message, and that thread binds to its own session from then on. Claude works through the task and posts the result back into the conversation. The work runs in an ephemeral cloud sandbox that Anthropic hosts, not on your local machine or inside your network.
 
 This page covers:
 
from line 148
 
 Every session, in any channel, follows the same five-step loop.
 
-1. **The session starts.** Someone tags `@Claude` with a task, or a [scheduled routine](/docs/claude-tag/users/proactivity) runs.
+1. **The session starts.** Someone tags `@Claude` with a task that needs a working session, or a [scheduled routine](/docs/claude-tag/users/proactivity) runs. At a channel's top level, the channel's own session picks the message up and starts the thread's session.
 2. **A sandbox builds.** Anthropic builds an isolated working environment for this thread.
 3. **The working loop runs.** Claude works through the task with the channel's access, editing its checklist in place.
 4. **The result lands in the thread.** An answer, a doc, a chart, or a pull request.
from line 164
 
 Two threads in the same channel are two separate sessions with separate sandboxes; sessions don't share state directly.
 
+A channel where Claude works at the top level, outside threads, also carries one session for the channel itself, separate from every thread's. That session reads the channel's top-level messages and handles top-level @-mentions, so context carries across separate top-level asks in the same channel; [What survives between replies](#what-survives-between-replies) covers how long it lives. For a task that needs investigation, tools, or a longer exchange, it starts a dedicated session in a thread under the message. At the channel's top level, [`!restart`](/docs/claude-tag/users/commands#restart-a-stuck-or-wrong-context-session) replaces the channel's session.
+
 Even with nothing connected, every session starts from the same baseline.
 
 * It reads its own thread and the channel's history, including pinned items
from line 209
 
 ### One-off and scheduled tasks
 
-A session starts the same way whether a person triggers it or a schedule does. A mention starts a session for that one task, and the sandbox is released once it finishes. A routine runs the same loop on a schedule, a channel watch, or a repository event, with the channel's connections, so a recurring digest or watcher gets the same access a typed request would. See [set up routines](/docs/claude-tag/users/proactivity).
+A session starts the same way whether a person triggers it or a schedule does. A tagged task runs in its thread's session, and the sandbox is released once the work finishes. A routine runs the same loop on a schedule, a channel watch, or a repository event, with the channel's connections, so a recurring digest or watcher gets the same access a typed request would. See [set up routines](/docs/claude-tag/users/proactivity).
 
 ## Session context and memory
 

claude-tag/concepts/agent-identity Changed · +1 / -1 lines

from line 32
 
 <Steps>
   <Step title="Tag Claude in a channel">
-    A user asks Claude to chart last week's signups or fix a deploy test. The request starts a new session.
+    A user asks Claude to chart last week's signups or fix a deploy test. The task gets a session in a thread under the message.
   </Step>
 
   <Step title="The session sandbox starts">

claude-tag/users/when-claude-responds Changed · +1 / -1 lines

from line 19
 | A channel, top-level                | Sometimes. [What Claude does with a channel message](#what-claude-does-with-a-channel-message) describes how it decides. Include `@Claude` to guarantee a reply, or [turn unprompted replies off](#quiet-the-whole-channel)         |
 | A message another app or bot posted | No guaranteed reply. Claude reads it as context. `@Claude` in a bot's message doesn't wake a quiet channel; in an active channel Claude may pick it up. See [Messages from other apps and bots](#messages-from-other-apps-and-bots) |
 
-When you @-mention Claude in a channel, it reacts to your message with an emoji within a few seconds to show that it picked the message up. It then answers in a thread under your message, or starts a [working session](/docs/claude-tag/concepts/how-it-works) in that thread when the request needs investigation, tools, or a longer exchange. Once a working session starts, Claude shows an "is thinking…" line under your message. A reaction with no line under it means Claude picked your message up and is either still deciding or answering directly in the thread, not that it missed you.
+When you @-mention Claude in a channel, it reacts to your message with an emoji within a few seconds to show that it picked the message up. The message goes to the channel's own [session](/docs/claude-tag/concepts/glossary#session), the session Claude works from at the channel's top level. It then answers in a thread under your message, or starts a [working session](/docs/claude-tag/concepts/how-it-works) in that thread when the request needs investigation, tools, or a longer exchange. Once a working session starts, Claude shows an "is thinking…" line under your message. A reaction with no line under it means Claude picked your message up and is either still deciding or answering directly in the thread, not that it missed you.
 
 You can change how much Claude replies on its own. You can [quiet a single thread](#quiet-one-conversation), [turn unprompted replies off for a whole channel](#turn-automatic-replies-on-or-off), or [tell Claude which kinds of untagged messages to answer](#what-claude-does-with-a-channel-message).
 

claude-tag/admins/setup-overview Changed · +1 / -0 lines

from line 198
 ## Related resources
 
 * [Network requirements](/docs/claude-tag/admins/network-requirements): what your services must allowlist so Claude can reach them
+* [Claude Tag in production at Anthropic](https://claude.com/blog/ai-ci-cd-on-call): how Anthropic runs Claude Tag as its first responder for CI/CD failures