Andy Chen

building @Rene_HQ among other things

[Rene @Rene_HQ]

Coming soon: the best contact in your phone.
Get your invite →

[Andy Chen @andy_429z]

@ponpon_app looks sick!!

[Andy Chen @andy_429z]

fable 5 spawning opus 4.8 minions and getting stuff done like an army is honestly such a vibe

[Andy Chen @andy_429z]

this reminds us to start treating agents as actual human beings.

a tech lead won’t be as productive and worth the money if u keep asking it to center a div

being smart about orchestration and delegation will become a key skill set very soon

[Vincent van der Meulen @vinvan]

fable produced 60+ (!) ready to merge prs for @mainframe overnight.

here's how you can set up a software factory using fable as an orchestrator. prompt included!

1. narrate your *entire* todo list — everything that's top of mind — using dictation. i used @usemonologue and my prompt was ~10K words! you have to use voice because we want excruciating levels of detail.

2. locally, tell fable to plan all the work and put it in @linear. the goal is to make it such that a dumb model dropped in linear knows *exactly* what to do. aka all issues should have a clear DAG, plan, and optimize for max. parallelizability.

i recommend running fable on high and having it fan out to codex subagents on xhigh (using the cc codex plugin.) to save usage. just make sure that fable itself is doing the architecture for the hardest issues!

3. now switch to @DevinAI. we'll use devin to run our factory because our orchestrator needs to be a cloud agent (it's going to run for a long time!), and be able to spin up other cloud subagents.

4. hook up the @linear @SlackHQ mcps. this will let your agents read the fable planned work, and communicate with you/your teammates. e.g. it can talk to your coworkers to make sure it's not stepping on anyone's feet!

5. a good feedback loop is *crucial.* before starting, make sure you have a bug bot (we use @cursor_ai.) and that your agents can test all its changes. e.g. we use the fantastic @limrun to make sure our agents can do ios development e2e.

6. create a devin ultra (fable) agent — this will be your orchestrator or 'middle manager.' we're going to tell it to look at linear and dispatch subagents for all tasks.

the middle manager's goal is to keep spinning up subagents with the right level of intelligence until all the work is done. and keep all agents unblocked while you're sleeping, hanging out in the park, whatever!

the reason the middle manager is able to orchestrate all of this is because fable planned everything in linear. and because the middle manager itself is also fable (contrary to most of its subagents.)

7. to prompt your middle manager, attach the middle manager prompt i'll post in the comments, modified for your repo.

it's important that we *attach* the middle manager's prompt to our conversation vs. typing it out, so it never gets compacted.

the middle manager's context window is holy. so our prompt tells it to spin up subagents — instead of doing things itself — for pretty much everything.

8. the prompt has some other cool, non-obvious details. firstly, every agent is told to keep working until it's met the burden of proof.

in our case that's a (self)-review, bug bot being green, bug bot fixes being elegant, and a recording. we tell our middle manager to enforce this.

secondly, we ask the middle manager to make sure linear stays up to date and communicate via the slack mcp. specifically, it should tag coworkers in slack whenever it has a question and post heartbeat updates in the eng channel.

9. your software factory is ready to go! in our case, it worked for 12+ hours without getting blocked. and produced extremely high quality prs.

addendum: all of this is possible because with @AnthropicAI fable, models are finally smart enough to orchestrate/navigate large sets of work and their dependencies. and fable is a great software architect!

now of course the 'downside' is that you're now review bottlenecked. we have 60+ PRs to review! but i think as an industry we should be able to come up with some innovation there. we'll certainly try our best to help here with @mainframe too!

hope this is helpful! happy to answer any qs.

[Andy Chen @andy_429z]

@benjitaylor impressive

[Rene @Rene_HQ]

Sneak peek 👀 Rene can shop groceries for you on @Instacart 🍎
Send Rene a list → It finds a store near you, loads up the cart, and gives you a link ready for checkout.

[Andy Chen @andy_429z]

something personal coming right up

[Andy Chen @andy_429z]

true

[Andy Chen @andy_429z]

and this actually gives wings to those great with the content

those that get paid to manage people are becoming irrelevant very quick

[Boris Cherny @bcherny]

As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes:

1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship
2. Builder: quickly turns a prototype/idea into production-grade product/infra
3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance
4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit
5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales

Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS.

A healthy team needs a mix of these, depending on the product:

- A product that is new and pre-PMF needs people that are strong at 1+2+3
- A product that is growing and has found PMF needs 2+3+4 and some 5
- A product that has strong PMF needs 3+4+5 and some 2

Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?

[Andy Chen @andy_429z]

coming very soon 🙌

[Andy Chen @andy_429z]

man rip my ghostty

[am.will @LLMJunky]

I'll bet you didnt know you could do this with Claude Code

[Andy Chen @andy_429z]

interesting

[Azeem Azhar @azeem]

The GenAI economy has generated $110 billion in sales over the past 12 months. It is growing fast. On an annualized basis, the revenue run rate exceeds $175 billion.

These numbers took us several months to construct, and as far as we know, it’s the first bottom-up, deduplicated measure of consumer and enterprise AI spending across the full stack.

We are releasing this research today in our first The State of the AI Economy report.

https://t.co/cJwZb0T99C

[Andy Chen @andy_429z]

i actually find it harder to build a good product with vibe coding, making that judgement of what NOT to build is so painful when it's so easy to just pack everything in

[Andy Chen @andy_429z]

this is pretty neat

[Andy Chen @andy_429z]

not bad

[Garry Tan @garrytan]

Jarvis-core is the new most powerful launch video meme

[Andy Chen @andy_429z]

do the right things and do things right

[Andy Chen @andy_429z]

@ponpon_app def had a similar dream like this before

[Andy Chen @andy_429z]

but what if the next time i dont have to ask at all?

[Jakub Krehel @jakubkrehel]

It’s incredible that /make-interfaces-feel-better has already been installed more than 30,000 times.

It contains a lot of tips that make interfaces feel better, across UI, animations, performance and more.

npx skills add jakubkrehel/make-interfaces-feel-better

[Andy Chen @andy_429z]

stay true to yourself, find a problem you think is worth solving and solve it well

[Calvin Chen @calvinchen]

https://t.co/KBzJKTs6Xb