Anthropic launches Claude Code in Slack
Users tag @Claude in a Slack thread to start a full coding session; the agent reads the surrounding conversation to find the right repository.
- Models & capabilities
- Minor
Anthropic brought Claude Code, its command-line coding agent, into Slack as a research preview. Tagging @Claude in a channel or thread starts a coding session grounded in that conversation: the agent reads recent messages — a bug report, a feature request — to infer which repository and task are meant, works the task, posts progress updates back into the thread, and shares a link to review the resulting pull request.
The feature extended Claude Code beyond lightweight uses such as generating snippets or explaining errors toward delegating complete coding workflows without leaving a chat client. Anthropic gave no rollout timeline beyond the beta and disclosed no pricing changes.
The move was read in the trade press less as a model advance than a distribution one: with the underlying capability of frontier coding agents converging across vendors, positioning them inside the tools developers already have open — chat, issue trackers, CI — was framed as the more consequential competitive ground than incremental gains on coding benchmarks. It followed a broader pattern through late 2025 of coding agents from OpenAI, Google and Anthropic being wired directly into IDEs, terminals and now team chat, rather than shipped as standalone products.
In the commentary
What people were saying around this time — external links, from the record's commentary rail.