Anthropic launches Claude Code routines for automated AI tasks with 5-25 daily execution limit
Anthropic has launched a cloud service called routines that allows Claude Code users to run automated AI tasks on company infrastructure. Daily limits range from 5 routines for Pro users to 25 for Team/Enterprise customers.
Anthropic launches Claude Code routines for automated AI tasks with 5-25 daily execution limit
Anthropic introduced routines on April 14, 2026, a cloud service that runs Claude Code automations on company infrastructure without requiring autonomous agent software.
A routine consists of a saved Claude Code configuration: a prompt, one or more repositories, and connectors that execute automatically on Anthropic-managed cloud infrastructure. According to Anthropic's documentation, routines continue running when a user's laptop is closed.
How routines differ from existing automation
Routines occupy a middle ground between traditional scheduled tasks and AI agents. Unlike cron jobs or GitHub Actions that run set scripts at predetermined times, Claude Code routines prompt an AI model on a schedule or webhook trigger and take different actions based on encountered context and available connectors.
An AI agent maintains ongoing state and involves continuous model interactions with tools and data sources. Routines function as dynamic cron jobs or trigger-driven, short-lived agents.
Availability and usage limits
The service is available to Claude Code users on Pro, Max, Team, and Enterprise plans with Claude Code on web enabled. Daily limits are:
- Pro: 5 routines per day
- Max: 15 routines per day
- Team/Enterprise: 25 routines per day
Usage counts against subscription limits. Customers with extra usage enabled can purchase additional routines as metered overage.
Anthropic suggests use cases including verifying software deployments where the model scans CI/CD output for errors and posts reports, or triaging alert messages.
Redesigned desktop app
Anthropic also announced a revision of its Claude Code desktop app on April 14. The Electron-based application now includes an integrated terminal, in-app file editor, faster diff viewer, and expanded preview area.
The redesign aims to keep developers within Anthropic's interface rather than using VS Code plugins or third-party tools like OpenCode, which Anthropic previously excluded from subsidized subscription usage.
What this means
Routines represent Anthropic's attempt to capture scheduled automation workflows without requiring customers to build full agent systems or rely on third-party orchestration tools. The restrictive daily limits—even Enterprise customers get only 25 runs per day—suggest either infrastructure constraints or Anthropic's concern about token consumption from parallel automation tasks. The simultaneous desktop app redesign reveals Anthropic's strategy to control the developer interface layer and prevent customers from accessing Claude through competing platforms.
Related Articles
Anthropic launches cloud-based code routines for automated bug fixes and PR reviews
Anthropic has released routines for Claude Code, allowing automated bug fixes, code reviews, and deployment monitoring to run on cloud infrastructure without requiring users' local machines. The feature is available in research preview with daily limits of 5-25 runs depending on subscription tier.
Anthropic adds scheduled routines to Claude Code, runs on cloud infrastructure without local machine
Anthropic launched repeatable routines for Claude Code in research preview, allowing developers to schedule automated tasks that run on cloud infrastructure without requiring their local machine to be online. Pro users get 5 daily routines, Max users get 15, and Team/Enterprise users get 25.
UK AI Safety Institute confirms Claude Mythos finds more exploits as token spend increases
The UK's AI Safety Institute published an independent evaluation confirming Anthropic's Claude Mythos is highly effective at finding security vulnerabilities. The evaluation revealed a linear relationship: more tokens spent equals more exploits discovered, transforming security into an economic arms race.
Anthropic marks Claude 4 Sonnet and Opus as deprecated in Python SDK v0.95.0
Anthropic released Python SDK v0.95.0 on April 14, 2026, marking Claude 4 Sonnet and Opus models as deprecated. The update also includes Bedrock authentication improvements for AWS deployments.
Comments
Loading...