Code with Claude: The 5 biggest updates explained
Episode
11 min
Read time
2 min
Topics
Productivity, Artificial Intelligence, Software Development
AI-Generated Summary
Key Takeaways
- ✓Scheduled Routines: Claude Code now supports three trigger types—cron schedules, HTTP webhooks, and GitHub webhooks—allowing automated tasks to run locally or in the cloud without manual initiation. Example use case: auto-drafting a customer newsletter every Monday at 6AM from a changelog file.
- ✓Outcomes Framework: Claude Managed Agents can now self-grade and iterate up to 20 times against a markdown rubric to reach a defined "done" state. Builders upload the rubric via the Files API or inline, then the agent autonomously refines output until it meets the criteria.
- ✓Multi-Agent Orchestration: The Claude API now supports explicitly defining teams of up to 25 agents sharing a single container and file system. Builders assign one orchestrator role and multiple sub-agents, each with distinct toolsets, enabling parallel workstreams on a single task from different functional perspectives.
- ✓Dreams Memory Consolidation: A research-preview API primitive lets builders call against a list of past agent sessions—up to 50 or more—triggering a batch review that extracts and writes the most relevant memories to disk on demand, rather than only on session-close hooks.
What It Covers
Anthropic's Code with Claude developer event introduced five updates to Claude Code and the Claude API: scheduled routines, outcome-based agent iteration, multi-agent orchestration up to 25 agents, session memory consolidation called Dreams, and doubled usage limits.
Key Questions Answered
- •Scheduled Routines: Claude Code now supports three trigger types—cron schedules, HTTP webhooks, and GitHub webhooks—allowing automated tasks to run locally or in the cloud without manual initiation. Example use case: auto-drafting a customer newsletter every Monday at 6AM from a changelog file.
- •Outcomes Framework: Claude Managed Agents can now self-grade and iterate up to 20 times against a markdown rubric to reach a defined "done" state. Builders upload the rubric via the Files API or inline, then the agent autonomously refines output until it meets the criteria.
- •Multi-Agent Orchestration: The Claude API now supports explicitly defining teams of up to 25 agents sharing a single container and file system. Builders assign one orchestrator role and multiple sub-agents, each with distinct toolsets, enabling parallel workstreams on a single task from different functional perspectives.
- •Dreams Memory Consolidation: A research-preview API primitive lets builders call against a list of past agent sessions—up to 50 or more—triggering a batch review that extracts and writes the most relevant memories to disk on demand, rather than only on session-close hooks.
Notable Moment
Anthropic's "Dreams" feature replicates how human sleep consolidates memory: the agent reviews past sessions silently and decides what to commit to storage—a framing that reveals how labs are modeling agent cognition on biological processes.
Episode Transcript
Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, I attended Code with Claude, Anthropic's first developer event, and they announced some things in Claude Code and Claude Managed agents I think you wanna know about. I'm gonna walk you through five things that launched today, how they work, what they are, and what I might build with them. We're gonna keep it under ten minutes, and this gonna be a quick preview of what you'll see in your new Claude Code and Claude API products experience. K. The first thing that shipped at Code with Claude that I think you wanna know about, there are some updates to the Claude Code app. And one of the updates that I know we've all been waiting for is routines. The ability to trigger events or actions on a schedule. We love it. You know I love OpenClaw, and what I love about OpenClaw are the Crohn's. And so now Claude code has that built in right here in the app. All you have to do is click new routine. You can either run it locally or remote. I'm gonna run it locally, and I'm gonna say weekly newsletter. This is something that I haven't been doing. I'm sorry if you're a ChatPurity customer. I I know I haven't done my newsletter. I'm gonna say look at our change log and draft a newsletter for us to send weekly. And then I'm gonna go in here and just say we have a changelog.md in the docs folder. Review it every Monday and write a customer facing newsletter based on the best customer facing features we shipped. Don't talk about behind the scenes things like tech debt or security unless they really impress customers. Okay. So I'm gonna do that. I'm gonna run it daily or no. Sorry. I'm gonna run it weekly on Mondays at 6AM and I think that's all I need to do. Oh, I'm gonna select my folder, where my project is, and then I'm gonna create create. And now, Cloud Code will run my newsletter draft cron every week, and then I can come back in here, grab the HTML. If I were being really fancy, I would hook this up to my newsletter platform. I would hook it up to my Slack and ping us. But, again, this is very useful to me. This is something that I used to kick off manually in Cloud Code every Monday. And now I can do that here in Cloud Code on a schedule. So how does that work? There are three trigger types. You can trigger them on a cron, which is a schedule, HTTP or a GitHub webhook. So you can do sort of a normal webhook or GitHub webhook. You can trigger these three ways, scheduled, like I just did, off of a GitHub action or a general …
Get the full transcript (2,109 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 8-minute episode.
Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from How I AI
ChatGPT Codex Voice + browser + Sites: an expert’s AI workflow | Nick Baumann (OpenAI)
Aug 3 · 41 min
The AI Breakdown
Surprise Elon Anthropic Team Up Reshapes the AI Race
May 7
More from How I AI
From zero coding background to hardware hacker: How Cursor + a Raspberry Pi makes AI fun
Jul 27 · 28 min
Lenny's Podcast
Anthropic’s first technical PM on token maxing, the jagged edge, and living in the future | Dianne Penn
Jul 26
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
by Anthropic
“Claude Managed Agents can now self-grade and iterate up to 20 times against a markdown rubric to reach a defined 'done' state.”
by Anthropic
“Anthropic's Code with Claude developer event introduced five updates to Claude Code and the Claude API: scheduled routines, outcome-based agent iteration, multi-agent orchestration up to 25 agents, session memory consolidation called Dreams, and doubled usage limits.”
by Anthropic
“Anthropic's Code with Claude developer event introduced five updates to Claude Code and the Claude API: scheduled routines, outcome-based agent iteration, multi-agent orchestration up to 25 agents, session memory consolidation called Dreams, and doubled usage limits.”
by Anthropic
“Builders upload the rubric via the Files API or inline, then the agent autonomously refines output until it meets the criteria.”
More from How I AI
We summarize every new episode. Want them in your inbox?
ChatGPT Codex Voice + browser + Sites: an expert’s AI workflow | Nick Baumann (OpenAI)
From zero coding background to hardware hacker: How Cursor + a Raspberry Pi makes AI fun
Claude Opus 5 review: this model is brilliant (but annoying)
Computer & browser use in Codex (5 real examples)
How the founder of Morning Brew built a Claude content machine that never runs out of ideas and never sounds like slop | Alex Lieberman
Similar Episodes
Related episodes from other podcasts
The AI Breakdown
May 7
Surprise Elon Anthropic Team Up Reshapes the AI Race
Lenny's Podcast
Jul 26
Anthropic’s first technical PM on token maxing, the jagged edge, and living in the future | Dianne Penn
Marketing Against the Grain
Mar 17
My 11-Skill AI Content Team (Built in Claude Code)
The Vergecast
Feb 24
How Claude Code Claude Codes
The Daily (NYT)
Feb 18
Can A.I. Already Do Your Job?
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into How I AI.
Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime