Claude Just Rolled Out 2 Big New Features

2026-03-13 · Source: Matt Wolfe · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

Anthropic has introduced two new features for coders within Claude Code: scheduled tasks and an enhanced code review system. Scheduled tasks allow users to automate routine coding operations, such as daily dependency audits at 9:00 a.m. or weekly PR triage every Monday at 8:00 a.m., which Claude Code handles automatically in the background. The new code review feature operates as an agent team-based system. When a pull request is opened, it dispatches multiple agents to concurrently identify bugs, verify findings to eliminate false positives, and rank bugs by severity. The consolidated output is then posted directly to the pull request as a high-signal overview comment, supplemented by inline comments for specific issues. Anthropic has reportedly utilized this internal code review system for months.

Key takeaway

For development teams managing pull requests and routine coding tasks, Claude Code's new features offer significant automation. You can schedule recurring tasks like dependency audits or PR triage to free up developer time. The agent-based code review system provides a high-signal, consolidated bug report directly on your pull requests, potentially accelerating review cycles and improving code quality.

Key insights

Claude Code automates routine coding tasks and streamlines code review with an agent-based system.

Principles

• Automate repetitive development tasks
• Parallelize bug detection with agents

Method

The code review system dispatches agents to find bugs in parallel, verifies them to filter false positives, and ranks them by severity, delivering a consolidated report.

In practice

• Schedule daily dependency audits
• Automate weekly PR triage
• Integrate agent-based code review

Topics

• Claude Code
• Scheduled Tasks
• Code Review
• AI Agents
• Pull Request Automation

Best for: Machine Learning Engineer, NLP Engineer, Software Engineer, AI Engineer, MLOps Engineer

Related on AIssential

• Claude Code 2.0 MASSIVE Upgrade! (Game Changer) — Claude Code's latest updates enhance developer productivity through improved scheduling, memory, and multi-agent capabilities.
• Claude Coded My Python Project for 3 Hours Alone — Claude Code operates as an autonomous agent, independently developing and debugging complex Python projects with minimal human intervention.
• How to Effectively Review Claude Code Output — The article highlights a critical shift in software engineering, where the bottleneck has moved from producing code to efficiently reviewing the extensive output generated by coding agents like Claude Code.
• 🤖 AI Agents Weekly: Claude Code Review, AutoHarness, Perplexity Personal Computer, Cloudflare /crawl, Context7 CLI, and More — Multi-agent systems and automated constraint synthesis enhance AI agent performance and reliability.
• Claude Can Make Hundreds of AI Agents Now! 🤯 — Claude Code's workflow automates complex multi-agent development, planning, and rigorous QA testing.
• I hated making this video... — Claude Code innovates AI agent interaction and capability through script execution, modular configuration, and parallel processing.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Matt Wolfe.