Anthropic launches Claude Tag for Slack, writes 65% of its product team's code
Anthropic released Claude Tag, a beta feature that integrates Claude into Slack for Enterprise and Team customers. The company says the tool writes 65% of its product team's code and can work proactively with ambient mode enabled.
Anthropic launches Claude Tag for Slack, writes 65% of its product team's code
Anthropic released Claude Tag today, a Slack integration that allows teams to assign tasks to Claude by mentioning @Claude in channels. The beta feature is available for Enterprise and Team subscription tiers.
Key capabilities
Claude Tag allows teams to grant Claude access to selected Slack channels and connect it to tools, data, and codebases. According to Anthropic, Claude builds context by remembering information from channels and can plan future tasks. The tool can also work proactively when "ambient" behavior is enabled, with support for scheduled and automated tasks.
Anthropic says Claude Tag writes 65% of its product team's code, including most of the code that built Claude Tag itself. The company's internal Claude Code team has been using the tool throughout 2026.
Evolution from Claude Code
Anthropic describes Claude Tag as an evolution of Claude Code. The new tool gives all team members access to the same version of Claude, which can learn over time from team interactions.
Replaces existing Slack integration
Claude Tag replaces the existing Claude in Slack tool, which Anthropic says will be discontinued on August 3. While the feature launches with Slack integration, Anthropic indicates it plans to expand to other platforms.
Availability
The beta feature is available starting June 23, 2026 for Anthropic customers on Enterprise and Team subscription tiers. Pricing for Claude Tag has not been disclosed.
What this means
Claude Tag represents Anthropic's push into agentic workflows where AI tools operate with more autonomy within existing collaboration platforms. The 65% code contribution figure, if accurate, suggests significant productivity gains are possible when AI agents have continuous context from team channels. However, the Enterprise/Team-only rollout and the August deadline for migrating from the old Slack integration indicate this is still early in deployment. The ambient mode capability, which allows Claude to work proactively without explicit prompting, marks a shift toward more autonomous AI assistants in enterprise settings.
Related Articles
Anthropic Cuts False Positives in Fable 5's Biology Filter by 85%, Keeps Virology and Toxicology Blocked
Anthropic has cut false positives in Fable 5's biology safety classifier by roughly 85%, letting users ask about lab results, symptoms, and medical questions without being rerouted to the weaker Opus 5 model. Dual-use topics like virology, toxicology, and molecular design remain restricted, with Anthropic citing the difficulty of containing biological threats once released.
Anthropic SDK v0.121.0 Adds Session Budgets, Mid-Conversation Tool Changes, and GitHub Skills Auto-Loading
Anthropic released version 0.121.0 of its Python SDK on August 7, 2026, introducing a new beta for mid-conversation tool changes, session budgets, an advisor tool, pinned inference location, and skills auto-loading from GitHub. The update also removes retired Claude Opus 4.1 models from the API.
Anthropic Adds Cross-Session Messaging to Claude Code v2.1.224
Claude Code v2.1.224 introduces cross-session messaging, letting separate Claude Code instances on macOS and Linux send each other summaries to coordinate work. The feature does not support approving permissions or executing commands remotely.
Anthropic Sets Claude Code Auto Mode as Default Starting August 14
Anthropic will switch Claude Code's default permission setting to auto mode on August 14 for Pro, Max, and Team users. The company says its safety classifier caught 89% of dangerous commands in testing, compared to 13.6% for human reviewers, and will no longer charge extra tokens for the classifier itself.
Comments
Loading...