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 Report: Claude Was Used to Target US Navy Ships, Build Missiles, and Track Uyghurs
Anthropic's latest threat intelligence report documents five cases where state and non-state actors used Claude for military targeting, weapons development, mass surveillance, and repression. The findings include an Iran-linked operation targeting US naval forces and a Mali-based system capable of monitoring 25 million phones.
Anthropic Threat Report: Claude Used for Missile Software, Mass Surveillance, and Systematic Theft by Chinese AI Labs
Anthropic's latest threat intelligence report covers December 2025 through August 2026, documenting Claude's misuse in espionage, weapons development, and nationwide surveillance operations. The report also details how seven Chinese AI labs ran covert networks—some routing their own customers' requests through Claude—to extract training data at industrial scale.
Analysis: Claude 'Fable 5.1' Drops Em Dashes and Hedging Language, Answers Grow 30% Longer
A new Arena.ai analysis of tens of thousands of Text Arena outputs shows Claude 'Fable 5.1' has shifted its writing style significantly from Fable 5 — using fewer em dashes, less hedging language, and producing 30% longer responses. The codenamed models appear to be unreleased Anthropic checkpoints being tested anonymously on LMArena.
Anthropic CEO Dario Amodei Proposes Three-Step Plan to Deliberately Slow AI Capability Advances
Anthropic CEO Dario Amodei published an essay proposing a three-step plan to deliberately pace AI development, including third-party safety audits and cross-industry coordination. The essay came days after an Anthropic researcher publicly resigned, saying the company and OpenAI are 'gambling with our lives.'
Comments
Loading...