Sid

Super excited to finally share Dynamic Workflows in Claude Code!! We built this a couple months ago, and it has slowly become a daily driver for a bunch of people at Anthropic. A few tips for getting the most out of it 🧵 x.com/ClaudeDevs/sta…

@Wimbledon Legend

Cricket royalty returns to the Royal Box 👑 Welcome back to Wimbledon, Sachin Tendulkar 🏏

Most people on seeing dynamic workflows: "Let's run some adversarial reviews and hunt for bugs" Jarred: "Let's rewrite Bun in Rust"

We're extending access to Claude Fable 5 on all paid plans through July 12.

@Schyz @ClaudeDevs It is available in the desktop app

Artifacts in Claude Code are now also available on Pro and Max plans. Ask for an artifact, Claude writes the code, publishes it live to claude.a‍i, and updates it in real time while it keeps working. Pages are private to your account and fully self-contained.

@danshipper have you tried cc artifacts? it's available to use for pro/max plans as of today and i've been using this heavily to understand code better x.com/sidbid/status/…

this is great i feel this a LOT right now with fable, where it can go off for hours at a time and then comes back with a 2 paragraph explanation of what it did we need better ways for AI to tell us stories

@thelifeofrishi yes these are private claude will sometimes create this proactively if it thinks it'll be helpful. you can switch this off in /config

@sidbid it built artifacts even when i didn't ask it 😅 for a moment i though it was a harness then i check the url, btw these are private artifacts, right?

Claude Code artifacts are now available for pro and max subscribers! Ask Claude to create an artifact to walk you through a PR or architecture for your project, create data dashboards, mock up UIs and anything else that requires rich html. Just ask Claude to "create an artifact" Works especially well with Fable because I can let it run for hours at a time and just ask for an artifact to catch me up and eli5 Try it out and let us know what you think! Lots more coming soon :)

PR reviews, code walk throughs and architecture diagrams with Artifacts are now a part of my daily workflow. Especially as the models start doing more autonomously, a high fidelity render of it's approach really helps get up to speed quickly

Here's an example of data visualization using artifacts. I can get 80% of my dashboarding needs met by this today. If you're on a Teams on Enterprise plan you can even share this with your team

Now that Fable 5 is ready to build (again), we've reset everyone's 5-hour and weekly rate limits.

Fable is back on the menu!

going into the weekend like

Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.

“this could’ve been an e̶m̶a̶i̶l̶ artifact”

I've been using Artifacts in Claude Code for everything: visual explanations of tricky code, system diagrams, quick previews of a few animation options, data analyses and dashboards I share with the team. They are a game changer for how I work with Claude. Can't wait to hear what you think!

@varadh @cnnrjcbsn Ask fable to build you smaller workflows if your task allows it. You can also ask it to use fable as orchestrator and opus for information gathering tasks

@cnnrjcbsn Funnily enough yes. Fable + Dynamic workflows cc: @sidbid bro send help

i've managed to spend $200 on Fable in an hour or so this morning need to go touch grass

@dexhorthy Cool! Now if you distill the learnings from your session into a skill and create a dynamic workflow to comb through your entire codebase, I bet you'll get incredible results

fable 5 did a +5k/-5k refactor on our oldest messiest react code, detangling a lot of stuff. Overall I'm very pleased and will be doing more of this, and in more parts of the stack. The diff appears to have no regressions, but still exploring w/ a mix of manual testing and browser automation. I like about 80% of the decisions fable made (you can see in the prompt chain below where i added more steering). Some of the decisions I think made the code worse and more complex: - introducing react-context - hides complexity but actually makes the program harder to reason about - did some clever hacks like ...spreads to reduce the total line count without actually reducing/simplifying any tramp data It did not have the taste to do some things until i explicitly steered it. - reduce prop drilling patterns - remove effects Aside: i'm noticing a trend where folks like me that lean quite backend-heavy, are finally having to learn a LOT about what good frontend code means (thanks @0xblacklight ). My only only guess is that this is due to the fact that its easier to vibe code frontend because you can see it. That means code quality deteriorates much faster, and regressions creep into your poorly-factored codebase. React is DECEPTIVELY complex - easy to work with, easy to get started, but the actual mental model you need to have to do it well is INCREDIBLY deep, and most people are just beginning this journey. Prompts - this was during a ~2hr session where I queued the following messages in order, each line is a separate queued message, usually added more every ~20 minutes as i skimmed the diffs, keeping a queue of ~5-7 messages until the end. refactor the $sessionId page / root component until its clean and under 500 lines /compact refactor the $taskId page / root component until its clean and under 500 lines /compact make it cleaner /compact make it cleaner /compact /no-use-effect (our skill to read the react docs and remove unnecessary use effects) /compact /no-use-effect /compact Remove some prop drilling. There's too much prop drilling. Why is all the state being threaded down from the top? Most of these things can own their own state workflow. It is absolutely fine to refactor the UI components to use children or to pull the UI components out of packages/ui and remove the pure wired split. More important to limit the amount of prop drilling. Let's see what we can do there on the pages we've touched so far and if you need to move storybook stories over, you can do that too. /compact Remove some prop drilling. There's too much prop drilling. Why is all the state being threaded down from the top? Most of these things can own their own state workflow. It is absolutely fine to refactor the UI components to use children or to pull the UI components out of packages/ui and remove the pure wired split. More important to limit the amount of prop drilling. Let's see what we can do there on the pages we've touched so far and if you need to move storybook stories over, you can do that too. remove more prop drilling we have hooks for all this shit, push state down, use stores, make the code good remove more prop drilling we have hooks for all this shit, push state down, use liveQueries and tanstack db, use stores, make the code good remove more prop drilling we have hooks for all this shit, push state down, use liveQueries and tanstack db, use stores, make the code good please create a giant html canvas with collapsible sub nodes that walks through this refactor step by step in a top-down hierarchical manner, it is to be optimized for human consumption

maximum intelligence

@ubernion right now it's a combination of strategy + unhobbling the model as best as i can but if you join the dots on the graph for model intelligence and extrapolate, that's when things start getting weird

@sidbid where do you see your place now ?

Within a few hours of using Fable it was clear that this model is on a different level. It has since changed the way I work, but more importantly it has changed the way I view the world and my place in it. - A large variety of tasks are now 1 shottable - It can debug large distributed systems BETTER than I can. Not just faster. Better. - Hard software design is now largely solved Don’t believe me. Try it for yourself

Happy Fable Day!