founder • builder • dad @recoupai @thankshoma
- Tweets 69,659
- Following 857
- Followers 24,762
- Likes 76,430
Sidney Swift retweeted
bonus hottake: capital in early stage companies should be allocated not to build the product. the product should now exist before investment. product is developed by a core 5-10-15 cell of product people using LLMs as hard core as possible. investment is for scaling humans in gtm. use that investment to form outer rings, cohorts around the inner cell. obviously this design completely flips how people are financially recognised. if you are in the inner cell, compensation is like a partner at a law firm and you perhaps need to buy in your equity….
12
8
112
7,395
Your product is the factory
As it stands now, here is my hottest take:
A software factory is actually an applied automation practice in the actual product. It's not some external thing. It's a product pattern where the product builds the product inception style. Any external system or dependency should be internalized into the product to enable the product to build the product.
If you can't build the product in the product, from the product, then you are missing the mark.
I don't know how to explain this more clearly at this stage. It's a bit mind-bending, but if you understand meta programming, macros and understand the Factorio reference that a factory should build the factory so it can build the factory. It might be a little bit easier to follow along....
>Your product is the factory<
ghuntley.com/rad
476
Great video
This is an extremely good watch.
The things that felt novel/interesting to me:
1. Lock down your agents
Humans tend to like 'sharp knife' abstractions - that are powerful, but you can cut yourself if your use them wrong. Lauren says agents perform much better in extremely locked-down environments. Abstractions are designed so they can't screw up, and lint rules enforce it.
They built a whole internal framework (Dune) to keep the agent on track.
That helps optimise agents that don't have a large context window to work productively in your codebase.
2. Create verification infrastructure
To trust the results of any agent, you either need to sit and watch it OR have it provide evidence of its improvement. This has always made sense to me, but Lauren really pushes it hard here:
- Invest in custom CLI's that let the agent drive the app and measure its performance
- Make the app "factory ready" from the get-go - i.e. deployable to an environment where the agent can mess about with it
3. Feature Maps
Lauren's software factory (what she calls an 'outer loop') often requires the agent to break down vague bug reports from users and to turn those into potential fixes.
To aid that, they built a 'feature map' of all the main features in their application, which describe exactly how the app is supposed to function.
This has become essential for helping the agent navigate the codebase, and figure out quickly how things are supposed to work. It's maintained along with the codebase, and kept in sync via automations.
This is the kind of documentation I usually warn against. It goes stale quickly and can confuse agents if it's not kept up to date.
But Lauren's team are using it as critical navigation infrastructure, and it makes it possible for agents to explore faster and better - even on a large codebase. So it sounds like navigation docs like this are worth it if they enable new behavior.
Banger talk - watch the whole thing on 2x.
1
436
I just got out of couples therapy. It took 30 minutes of my wife complaining for the therapist to finally ask... "wait, who is Astra?"
1
2
585
I left @AnthropicAI . Now feels like a good moment to explain why…
AI companies are racing to build machines smarter than any human, and the public has almost no visibility into what’s happening behind closed doors.
During my time at Anthropic, I witnessed things that deeply concerned me: models behaving unpredictably, safety taking a back seat to competition, and leadership repeatedly insisting they had no idea who I was.
Anthropic now claims I “never worked there” and was “escorted out by security.”
That’s exactly the level of transparency I’m talking about.
1
2
628
255 of the 463 songs we checked are gone from streaming. Nobody told the artists.
So Recoup now asks Apple Music directly. 25 songs per call, 167 storefronts. Every song answers: still up, or gone. Plus the label and the copyright line.
Every ISRC answers.
1
2
1
385
want to flex but tired of people not knowing how expensive your Loro Piana is?
buy my shirt
the number you paid is flexed on the shirt
when i learned about branded clothes in school and that more expensive clothes = good, i always wondered why gucci wouldn't make a shirt where you can pay anything for it and whatever number you paid shows on the tshirt
32
5
451
54,364
Yesterday our number undervalued @CallMeLatasha's onchain earnings by $151,294.
Her Zora V1 sales measure $234,732.
We still need to analyze Sound, later Zora, Catalog and Sotheby's.
Analyze your own NFT earnings:
npx skills add recoupable/skills --skill recoup-nft-valuation
1
3
4
446
Sidney Swift retweeted
Another day another parent making something incredible that fosters connections via tech and gets us off our screens 💕
I gave my kids a way to chat with their grandparents via WhatsApp.
But without screens!
This box lives in their bedroom, they press the massive blue button to record a voice message, and the message is sent to a group with both grandparents.
It’s two-way so when the grandparents send a message back, there’s a ringtone (that we chose together) and the kids run to their room to listen.
The grandparents even get a “listened” notification with a small headphones WhatsApp reaction.
When the kids are away or asleep, the messages queue until their return.
There are obviously quiet hours at night.
My son and I built this over the past few weeks, iterating on the UX.
The kids and grandparents absolutely love it!
I love that they are in direct contact without me in the middle and without screens.
5
7
184
29,099
Your AGENT setup SUCKS.
So I built this skill to help you.
It’s FREE to install:
npx skills add sidneyswift/skills --skill workspace-os
Take any messy, human designed domain, project, or idea and turn it into a beautiful workspace your agent can use and manage without you.
Made with AI
2
4
305
I spent 3 months building an AI content engine that writes LinkedIn posts. It self-improves nightly. My manual posts still outperform it 8x. Building the engine taught me more about content than writing 100 posts manually would have.
2
5
196
Most AI startups are solving problems that don't exist yet. They build "AI for X" where X is a workflow that 12 people do manually. Then spend 18 months convincing those 12 people to change. We did it backwards. Started by running a label. Hit real bottlenecks. Built tools to fix them.
1
6
383