Code with Claude: The 5 biggest updates explained

May 7, 2026

AI Summary

5 min read

Claire V from How I AI recaps five practical updates announced at Anthropic's Code with Claude developer event, focusing on enhancements to Claude Code and the Claude API for building agentic products. These include scheduling tools, agent iteration mechanisms, team structures, memory handling, and higher limits, with examples tied to real workflows like product development.

Routines for Scheduled and Triggered Tasks

Claude Code now supports routines, which automate actions on schedules or triggers. Users create a routine by selecting a project folder and defining a prompt, such as reviewing a changelog.md file weekly on Mondays at 6 a.m. to draft a customer-facing newsletter highlighting key features while skipping internal details like tech debt. Routines run locally on the user's laptop or remotely in the cloud.

Triggers include cron schedules, HTTP webhooks, or GitHub webhooks, with integration via connectors like Slack and GitHub. For instance, a routine could check PRDs modified that week against a rubric and post summaries to a team channel. This mirrors cron jobs in tools like OpenClaw, reducing manual kicks-offs for repetitive tasks.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

What you'll learn

1 (00:04) **Welcome and Event Intro** - Host Claire introduces Code with Claude developer event and outlines 5 key updates for Claude Code and API.
2 (00:34) **Update 1: Routines in Claude Code** - New scheduling feature with cron, HTTP, or GitHub webhook triggers for automated tasks.
3 (03:25) **Update 2: Outcomes in Claude API** - Agents self-grade and iterate up to 20 times against a rubric to achieve defined success.
4 (05:27) **Update 3: Multi-Agent Framework** - API support for teams of up to 25 agents with orchestrator hierarchy and custom tools per agent.
5 (07:13) **Update 4: Dreams for Agent Memory** - Research preview tool consolidates key memories from multiple sessions into markdown files.
6 (09:35) **Update 5: Increased Usage Limits** - Doubled 5-hour limits across plans; peak hours removed for Pro/Max; higher API rates for Opus.
7 (10:03) **Event Recap and Closing Thoughts** - Summarizes 5 practical updates positioning Anthropic as agent platform for builders.

+ Full timestamped outline available in the app

Show Notes

Claire breaks down the biggest announcements from Anthropic’s “Code with Claude” event and what they actually mean for builders shipping AI products today. From scheduled AI routines to outcome-based agents, multi-agent orchestration, and new memory systems, Claire walks through the features she’s most excited to use immediately—and how they could reshape the future of agentic software.

What you’ll learn:

How Claude Code routines let you automate recurring workflows on schedules or webhooks
What “Outcomes” are and how rubric-based agent grading works
How multi-agent orchestration enables specialized AI teams with different roles and tools
Why Anthropic’s new “Dreams” memory system matters for long-term agent behavior
Why increased Claude Code usage limits are a bigger deal than they sound
How Claire thinks about building practical agentic products today

—

Resources:

• Code with Claude: https://claude.com/code-with-claude

• Claude Code Routines Docs: https://code.claude.com/docs/en/routines

• Define Outcomes Docs: https://platform.claude.com/docs/en/managed-agents/define-outcomes

• Dreams Docs: https://platform.claude.com/docs/en/managed-agents/dreams

• Multi-Agent Docs: https://platform.claude.com/docs/en/managed-agents/multi-agent

• Managed Agent Webhooks Docs: https://platform.claude.com/docs/en/managed-agents/webhooks#supported-event-types

• Codex (OpenAI): https://openai.com/codex

• GitHub: https://github.com

—

Where to find Claire Vo: