
Claude Tag embeds Anthropic's AI in Slack, already writes 65 percent of internal code, company says
Quick Answer
Claude Tag integrates Anthropic's AI into Slack, allowing teams to assign tasks via @Claude.
Quick Take
This tool is already responsible for generating 65% of the internal code for Anthropic's product team.
Key Points
- Claude Tag allows task assignment in Slack using @Claude.
- The tool generates 65% of the internal code for Anthropic's product team.
- Integration enhances productivity and collaboration within teams.
- Anthropic leverages AI to streamline coding processes.
📖 Reader Mode
~2 min readClaude Tag lets teams bring Anthropic's AI into Slack by tagging @Claude in any channel and assigning it tasks. Internally, the tool already generates 65 percent of the code on Anthropic's product team, the company says.
Anthropic has introduced Claude Tag, a new way to embed its AI directly into Slack. Admins grant the model access to selected channels and connect it to tools, data, and codebases. From there, anyone in the channel can tag @Claude and describe a task in plain language. The model breaks it into steps, works through them using the available tools, and reports back in a Slack thread.
Anthropic positions Claude Tag as an evolution of Claude Code. Tagging @Claude is already a core workflow inside the company: 65 percent of the code on the product team comes from an internal version, Anthropic says. Teams outside engineering use it too - for tracking product metrics, handling support tickets, and diagnosing bugs.
One shared Claude per channel instead of individual chats
Compared to a traditional one-on-one chat, Anthropic highlights a few key differences. Each channel gets a single Claude that interacts with everyone. All members can see what the model is working on and pick up a conversation where someone else left off. Over time, the model builds context by following what happens in the channel. With the right permissions, it can also learn from other channels and data sources. It won't share anything from private channels, according to Anthropic.
When "ambient" mode is turned on, @Claude proactively surfaces relevant information and follows up on stalled threads or tasks. The model also works asynchronously: it can schedule tasks for itself and track a project on its own over hours or days. Through direct messages, it responds privately using each user's personally configured tools and connectors.
For enterprise use, admins define which tools and data the model can access in each channel. This creates separate Claude identities for different purposes, with memories limited to their respective channels. A Claude set up for sales won't share its memories with engineering. Admins can set token limits and review a full log of every action, including who triggered it.
Claude Tag is available now in beta for Claude Enterprise and Team customers. It replaces the older "Claude in Slack" app - admins have 30 days to migrate. The tool runs on Opus 4.8.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.

