Anthropic launches a repeatable routines feature for Claude Code as a research preview, allowing developers to schedule and automate software development tasks
Anthropic has been extending Claude from a coding assistant into a broader work environment: Cowork was introduced as a Claude Code-based research preview, later expanded with computer use, and then made available across paid plans with enterprise-oriented additions.
Repeatable routines add persistence and scheduling to that arc. Rather than asking Claude to act only in a prompted session, developers can define recurring software-development work for Claude Code to run as an ongoing workflow.
First-order effects
Developers in the Claude Code research preview can schedule repeatable software-development tasks instead of manually initiating each run.
Anthropic gains another automation layer atop Claude Code, while keeping the capability in preview as it evaluates the workflow.
Second-order effects
Teams using Claude Code can shift suitable recurring engineering chores into standardized routines, increasing the importance of review, permissions, and monitoring around automated output.
Competing coding assistants and developer-tool vendors face pressure to pair interactive code generation with recurring, workflow-level automation rather than treating chat or one-off agent sessions as the product boundary.
Third-order effects
If such previews become dependable and broadly available, the competitive unit in AI coding may move from the individual coding interaction to the managed software-delivery workflow.
The expansion from Cowork to computer use and scheduled routines points toward assistants becoming operational work surfaces; adoption will hinge on whether organizations can safely govern autonomous actions across their tools and processes.
The trend: AI coding products are evolving from prompt-driven assistants into agentic work surfaces that can carry out recurring tasks across a developer’s workflow.
Claude Code Routines are here! In addition to a schedule, you can now trigger templated agents via GitHub event or API - with our infra & your MCP+repos They've changed how we do docs, backlog maintenance and more internally at Anthropic Get started at https://claude.ai/... [vide…
@claudeai
Claude on x
Now in research preview: routines in Claude Code. Configure a routine once (a prompt, a repo, and your connectors), and it can run on a schedule, from an API call, or in response to an event. Routines run on our web infrastructure, so you don't have to keep your laptop open. [ima…
@thekitze
@thekitze on x
closedclaw
@daniel_mac8
Dan McAteer on x
Did Anthropic just kill all SaaS again? What is SaaS besides routines running in the cloud?
@cryptopunk7213
@cryptopunk7213 on x
claude now runs autonomously with your computer turned off. 24/7 coding agent. this replaces $10,000's of engineering time and competes directly with Pager Duty's $500M val it works while you sleep. reviews code, builds new features - ready for you to click publish when you [imag…
@exm7777
Machina on x
that's it, they've done it, Anthropic's version of Openclaw is now reality [video]
@dani_avila7
Daniel San on x
I love this 👏👏👏 Moving my complex GitHub actions into these routines I think, the best part is they connect with the MCPs I already have set up
@eptwts
@eptwts on x
there's really no point in building a general use agent bc if you get a little bit of motion the frontier labs are gonna come for your money... brutal tbh
@rasmic
Micky on x
One thing Anthropic is good at is renaming things Instead of cron jobs... call them routines
@tekbog
@tekbog on x
cron job but it runs on the unreliable anthropic api [image]
@chrissyfarr
Christina Farr on x
Anthropic is really pushing hard into life sciences https://x.com/...