Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Thariq Profile picture
Thariq
@trq212
Claude Code @anthropicai. prev YC W20, @southpkcommons, @medialab
Apr 8 • 7 tweets • 3 min read
Managed Agents is the first 'agent in the cloud' API that has the right mix of simplicity and complexity.

Implementation details like how you manage a sandbox are abstracted, but you have a lot of control over the actual execution of the model. You can create environments with specific packages, networking access, etc.

platform.claude.com/docs/en/manage…Image
Mar 21 • 8 tweets • 2 min read
I put a lot of heart into my technical writing, I hope it's useful to you all.

📌 Here's a pinned thread of everything I've written.

(much of this will be posted on the Claude blog soon as well) skills are the abstraction that all agents will build on

Mar 14 • 6 tweets • 2 min read
A few end of week ships:

You can now set effort to 'max' which reasons for longer and uses as many tokens as needed. This will spend your usage limits more quickly so you have to activate it per session.

Hit /effort to try it. You can now start new sessions from Remote Control

Jan 21 • 6 tweets • 2 min read
Our fix to remove flickering is rolled out again to everyone on Claude Code.

Why did we roll it back? If Claude is so good, why were there bugs to begin with? Why was it so complex? 🧵 Most people's mental model of Claude Code is that "it's just a TUI" but it should really be closer to "a small game engine".

For each frame our pipeline constructs a scene graph with React then
-> layouts elements
-> rasterizes them to a 2d screen
-> diffs that against the previous screen
-> finally uses the diff to generate ANSI sequences to draw

We have a ~16ms frame budget so we have roughly ~5ms to go from the React scene graph to ANSI written.
Jan 9 • 5 tweets • 1 min read
Yesterday we tightened our safeguards against spoofing the Claude Code harness after accounts were banned for triggering abuse filters from third-party harnesses using Claude subscriptions. Third-party harnesses using Claude subscriptions create problems for users and are prohibited by our Terms of Service.

They generate unusual traffic patterns without any of the usual telemetry that the Claude Code harness provides, making it really hard for us to help debug when they have questions about rate limit usage or account bans and they don’t have any other avenue for this support.
Jan 4 • 7 tweets • 2 min read
If you started using Claude Code over the holidays, you might be curious about how AI actually works, the benefits and risks, and where it's headed.

Here are some of my favorite papers on alignment, interpretability, and societal impacts 🧵 First Dario's essay on Machines of Loving Grace.

Why is it worth building AI, despite the risks? Because if we do it right the future can be radically good.

darioamodei.com/essay/machines…
Dec 17, 2025 • 9 tweets • 2 min read
We’ve rewritten Claude Code’s terminal rendering system to reduce flickering by roughly 85%.

We wanted to share more about why this was so difficult, how the fix works and how we used Claude Code to fix it 🧵 When rendering in a terminal there are two regions: the viewport at the bottom and the scrollback buffer above it.

When content exceeds the viewport height, the top row gets pushed into scrollback and some of the rendering happens offscreen. Image
Nov 13, 2025 • 4 tweets • 2 min read
We've released a new frontend-design plugin for Claude Code.

Here's Claude's output for: "use the frontend design skill. Create a music player app." To get started add our marketplace in Claude Code:

/plugin marketplace add anthropics/claude-code

and then install the plugin:

/plugin install frontend-design@claude-code-pluginsImage
Nov 12, 2025 • 5 tweets • 2 min read
We built a Deep Research demo for the Claude Agent SDK!

It's one our most requested use cases: spawn multiple AI agents to research a topic in parallel, then synthesize their findings into a report.

🧵 on how it works: Image At a high level:
- the main agent breaks your request into 2-4 subtopics
- it spawns researcher subagents in parallel to search the web
- each researcher saves findings to files/research_notes
- the main agent then spawns report-writer to create final report in files/reports
Nov 11, 2025 • 5 tweets • 2 min read
🧵 Making Proactive Agents with Code Generation

Last week we shared about how you can use code generation to compose tools.

But code generation can also give your agents new capabilities- like proactively acting on your behalf. In this case, I want to make an email agent that processes my emails.

Running an agent on every email I receive would be slow & unpredictable, so instead I'm allowing the user to generate callbacks that are called when I get an email.

Here's an example generated function: Image
Nov 1, 2025 • 5 tweets • 2 min read
Claude Code Weekly Round Up

This week we made subagents resumable, added a Plan subagent, introduced prompt based stop hooks, fixed several high priority bugs & much more across the CLI, web and SDK.

We're also replacing output styles with with more powerful alternatives:Image Next week, we're replacing output styles in Claude Code.

We found in practice that less than 1% of users actively used output styles, and they can be recreated through other extension points via plugins.
Oct 29, 2025 • 6 tweets • 2 min read
Every Agent is a Coding Agent

The best way to make your agent more adaptable & powerful is using code generation.

🧵 Here’s how I’m using it for my open source email agent built on the Claude Agent SDK.Image I want my agent to handle requests like:

“Every day at 11am, email me the most urgent tasks in my inbox”

“When I get an email from my boss, send me a notification”

The most common way people do this is that they invent a JSON schema or DSL to represent every action like so Image
Oct 27, 2025 • 7 tweets • 2 min read
Why even non-coding agents need bash

I've done dozens of calls with companies making general agents over the past few weeks and my advice generally boils down to: "use the bash tool more"

Here's a concrete example from my email agent:Image The user asks: "How much did I spend on ride sharing this week?"

With tool calls, you have to fetch emails and then have the model figure it out from there. You might have fetched ~100 emails and it will be hard for the model to find this data.
Oct 18, 2025 • 4 tweets • 2 min read
Claude Code Weekly Round Up

A big week for shipping!

Besides Haiku 4.5, we added support for Claude Skills, gave Claude a new tool for asking interactive questions, added an ‘Explore’ subagent, auto-background long running tasks and fixed several bugs.Image in case you missed it, launch posts for Haiku:
Sep 22, 2025 • 6 tweets • 3 min read
Your Agent should use a File System

This is a hill I will die on. Every agent can use a file system.

The file system is an elegant way of representing state that your agent could read into context & allowing it to verify its work.

🧵on why and examplesImage Claude Code was what proved this to me.

Before CC, people though context windows would get long enough that you could just fit a codebase into context.

But that is not how programming works. You don't need to remember everything, you just need to know how to find it.
Sep 17, 2025 • 7 tweets • 3 min read
Making an Email Agent using the Claude Code SDK

If I wasn’t at Anthropic, I would be making agents using the Claude Code SDK.

But doing > talking. So I’m building in public and open sourcing a local email agent.

This is part one on agentic search. First, why the Claude Code SDK?

Whenever I’ve built an agent in the past I ended up hand rolling the same patterns that are now just way easier to use the Claude Code SDK.

In this example I’m using it for subagents, context management, the file system & code generation.
Aug 7, 2025 • 6 tweets • 2 min read
It's maddening that we're creating real time AI game engines, but there aren't any actual AI games.

🧵 here's my take as an ex-gaming founder on why People don't want generative slop.

The edge that games have over other media is achievement.

As Tiktok increasingly offers the best ratio of effort to dopamine, games need to lean into achievement and mastery.

In an infinitely generated world, where do you find the mastery?
Jul 22, 2025 • 6 tweets • 4 min read
Use Claude Code as your Video Editor

Believe it or not, every video you see below was vibe coded by Claude Code.

🧵 here’s how you can do it too:


 The UI videos are all powered by Remotion ()- a library for creating videos using React.

And Claude Code is great at writing code for Remotion! remotion.dev
Jul 14, 2025 • 8 tweets • 4 min read
Claude Code is All You Need

When I first joined Anthropic I was surprised to learn that lots of the team used Claude Code as a general agent, not just for code.

I’ve since become a convert! I use Claude Code to help me with almost all the work I do now, here’s how: Why?

In Claude Code Everything is a File, and it knows how to use your computer like you do.

Name your files well, and CC will be able to search them like you would.

This lets you make custom setups for memory, todos, journals, screenshots and more.
Mar 13, 2025 • 4 tweets • 2 min read
✨ New AI Interfaces powered by Interpretability

I'm excited to share LatentLit, the result of my applied AI research fellowship with @GoodfireAI

Mechanistic interpretability isn’t just important for AI safety, it also gives us new ways to steer and interact with LLMs. In LatentLit, you write stories by like a DJ might make music, adjusting knobs and dials using steering and seeing what effect they have. You might call it Vibe Writing.

Try it out here!

latentlit.goodfire.aiImage