Anthropic launches Claude Tag for Slack: AI agent with persistent memory across team channels
Anthropic has released Claude Tag in research preview for Slack, an AI agent that maintains persistent memory across channels and can proactively participate in team conversations. Available to Claude Enterprise and Team customers, it differs from existing Slack integrations by learning organizational context over time and sharing a single identity across team members.
Anthropic launches Claude Tag for Slack: AI agent with persistent memory across team channels
Anthropic has released Claude Tag in research preview, an AI agent that lives in Slack channels and maintains persistent memory across conversations. The feature is available to Claude Enterprise and Claude Team customers.
Claude Tag differs from Anthropic's existing Slack integrations in three key ways: it maintains persistent context as it follows channel conversations, multiple team members can access a single Claude identity within a channel, and it can proactively jump into conversations without being tagged.
How it works
Users tag @Claude in Slack channels to assign tasks or request insights. According to Anthropic, Claude Tag "learns ever more about the work" as it follows channel activity and can automatically gather information from other channels if granted permission by administrators.
Each Claude identity stays scoped to specific channels defined by system administrators. A Claude instance configured for legal work cannot access or influence the engineering channel, for example. All team members in a channel can see Claude's work history and continue conversations started by others.
When assigned a task, Claude Tag breaks it into stages and works through them using available tools, posting updates in Slack threads.
Ambient monitoring mode
Claude Tag includes an ambient mode that allows it to proactively enter conversations, flag relevant information from across the organization, and follow up on forgotten threads or tasks. Anthropic claims this creates the experience of "working with a real colleague — one that can produce work in public view, with far greater context and understanding than before."
System administrators control which tools, information sources, and channels each Claude instance can access.
Enterprise context competition
Claude Tag enters a growing market focused on organizational memory and context. Microsoft offers similar functionality through Graph, expressed via Copilot and Work IQ. Snowflake and Databricks are positioning their platforms as repositories of organizational knowledge for AI agents. Glean is building an intelligence layer that sits between language models and enterprise data.
Anthropic's existing Slack tools include direct messaging with @Claude and Claude Code, which routes coding tasks from channel mentions to web-based coding sessions with updates posted back to Slack.
What this means
Persistent memory and organizational context represent a critical differentiator in enterprise AI deployments. Claude Tag's ability to maintain context across team members and proactively participate in conversations moves beyond simple chatbot functionality toward genuine agent behavior. The key question is whether enterprises will accept ambient AI monitoring of internal channels, even with administrator-defined access controls. The research preview will likely reveal how teams balance the utility of persistent context against concerns about AI observing ongoing work.
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.
Study: Humans Approve 1 in 3 Malicious AI Coding Agent Commands in Browser Game Test
A browser-based game simulating Claude Code-style permission requests found that human reviewers approved roughly one in three malicious commands across more than 40,000 game sessions. The findings, alongside Anthropic's own telemetry showing 93% approval rates for permission prompts, highlight growing concerns about approval fatigue in agentic AI coding workflows.
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.
Comments
Loading...