An infrastructure issue is causing a partial outage across Claude Code, the API, and We're working on it but don't have an ETA yet. We'll post here when that changes, and quickest place for updates is always
Show more
Personal agent setup and personal website now both have embedded Claude Managed Agents with access to the codebase so I can ask them to edit themselves and push PRs that I can review.
Still a missing piece I'm excited to share more about it in a blog post I'm cooking up. 🐌
Show more
Second time today I've seen teams using Claude Managed Agents for issue / bug triage.
The other was using github actions to kick off managed agent sessions.
Been working on automating our bug triage process with Claude Managed Agents. It auto-fixed two bugs first day on the job 🤩
Slack/Anthropic Webhooks + Hono on CloudRun + Managed Agent w/ memory
Show more
Love these little explainers that Claude makes. 😍
New in Claude Console: playground.
Explore the Messages API by using it! Every parameter (including betas), an editable code view for your programming language of choice, and tokens, cost, and caching shown on every run.
Start from templates for code execution, web search, and the advisor tool, then copy the code when it works.
Show more
Anthropic Python SDK v1.0 is out!
‼️HTTP layer moved from `httpx` to `httpx2`
Use `/claude-api upgrade` in Claude Code
The Box Agent is expanding its document generation capabilities through our integration with the newly released @AnthropicAI Skills API.
With a single query, Box Agent will be able to turn your content into polished PowerPoint presentations, Excel spreadsheets, Word documents, and PDFs—without manual formatting or context switching. Everything stays in Box.
Coming soon for Box users.
Show more
tons of great claude code content on here, go watch! 🍿
Computer use is GA on the Claude API. Stellar production writeup by @davilocatelli13 at Asteroid: agents driving EHRs and payer portals, human steering down from 8.9% of runs to 0% since April.
Show more
The personal software that we can build is getting so wild. The upper bound is really your imagination, now.
Would love to hear and see... what personal software you're working on right now?
I take heart medication. Most workout apps don’t consider this. So I built my own. First as a web app and now Claude ported it to a native iOS app. Every week Claude creates a workout based on my available equipment, my medication, my Calendar, my Oura data. It’s pretty good
Show more
You can now set Claude Code's output style to Concise.
Claude leads with the result, keeps responses short, and still gives full detail when you ask.
Turn it on in /config → Output style, or set "outputStyle": "Concise" in settings.json.
Show more
Lots of great new knobs and UX in the Claude Platform console for viewing sessions.
I have a ton of agents that I use directly through the console, or driven by Claude Code with the ant CLI.
Spun up a team of QA agents with different personas, today to help dogfood!
Show more
Finally, we've redesigned the Console session viewer for multi-agent sessions.
It now has a minimap with one lane per agent, a streaming transcript grouped by agent iteration, and an inspector with cost in dollars per thread and per session.
Live now:
Show more
The EnvironmentWorker in the SDKs that help bridge to self-hosted sandboxes now mount memory stores for you.
The memory store files are loaded into the sandbox at session create and the helpers sync the agent’s edits back.
Show more
We shipped three updates to Claude Managed Agents.
First, we made it easier to use memory with Self-Hosted Sandboxes.
Any work done in a Self-Hosted Sandbox can be saved to memory.
Show more
Workbench is out, Playground is in! 🛝
My favorite feature is being able to toggle to see the code for an API call (advisor mode, tool calls, structured outputs, etc.) with all of the supported SDKs, then edit the code and see that update the form ✨ fun way to iterate
Play around today 🤽
Show more
btw you can configure auto mode in Claude Code in plain English
the classifier is a separate model that reviews each action, so it just reads these rules when deciding what to allow/block. adding "$defaults" keeps the built-in rules as well!
Show more
Here's a powerful podcast workflow: use Claude Code + the Transistor MCP + @auphonic CLI + FFMPEG + Whispercc to:
- master the audio
- transcribe
- generate MP3 chapters + show notes
- upload and publish the episode automatically.
Show more
Solid 📝
Quick demo of how I use session to session messaging in Claude Code + Ghostty
(Save this and try it in your own workflows)
1- I always start with a regular session and a panel running claude agents
2- The first session becomes the orchestrator. It creates the initial context, then distributes the work across other sessions using forks
3- Each fork starts with that context + a prompt telling it what to work on
4- I rename each session with ctrl + r to keep things organized and make it easy to message them from the main session
5- Using @ I send messages to the sessions that are running and ask them to report their task status back, so the main session always knows what everyone is working on
This way, I only need 2 or 3 panels open and can switch between tasks as needed
The days of opening endless terminal panels and running Claude Code 100 times just to look productive are over!
What we need now is ORCHESTATION
one main session coordinating everything through session messaging + Agent View
And the key is context, build it in the main session first, then fork from there
That’s what makes the entire workflow click
Show more
just Claude writing a MacOS driver for my obscure HP printer built only for Windows support
Inspired by the CloudflareOS announcement I've been exploring the concept of self-edited software a ton.
I've got a Rails app with a Claude Managed Agent that monitors prod/analyics, has MCP server to itself, can make PRs against the code where it lives.
Blog post soon.
Show more
🫰 tip:
Experiment with *effort*. Lower effort is fewer tokens, higher effort is more tokens.
