Apply to any job in 15 seconds (or less):
• Tailored resume & cover letter
• No tabs, no copy-paste
• Works on any job page
Click and done, with @ATSZero Copilot.
Land the roles you want, not just the ones you have time for.
Live at: https://t.co/op60kwiKCA 🚀
You might not really understand who you are.
As an exercise in introspection, I took 14 months of my own transactions, clustered them, and mapped the result as a 3D force graph. Then I did the same with 3,000+ iCloud photos; CLIP embeddings, UMAP, HDBSCAN clustering, vision model labeling. Then I cross-referenced both.
The goal of this experiment wasn't a budget breakdown but an answer to a different question: what kind of person am I really, according to my own data?
The answer was uncomfortable.
My food delivery spending tracks my financial confidence with a two-week lag, it drops before I consciously feel worried, and takes two weeks to return even after the money does. I now realize I don't trust good news quickly. I had no idea until the data showed me. Which raises an unsettling question: how much of what we call "personality" is actually just a pattern we've never seen plotted?
My gaming increases during stress but drops during illness. Two different kinds of bad, and my spending distinguishes them before I do. We talk about coping mechanisms like they're choices. The data suggests they're closer to reflexes, they’re automatic and legible in hindsight but invisible in the moment.
My mum adjusts how much she sends me each month without being told anything. The amounts are a seismograph of my financial state. There's an entire theory of love buried in transaction metadata. The people who pay attention to you through what they do, not just what they say, and whose care becomes immensely visible at scale.
The most interesting part was where the photo clusters diverged from the transactions. The drawing photos stopped weeks before the last art supply purchase. I was already done before I knew I was done. The gym selfies only appeared on some days, even though payments showed twice-three-times-a-week visits meaning some sessions fueled by results, others by discipline. And during the month I spent the least money all year, my camera roll was the fullest it had ever been. Mostly food I was teaching myself to make. You photograph the things you’re proud of, the things you had to fight to learn.
I think the data reveals that identity is what you repeat not what you declare. The things you never stop paying for even in your worst month, even when you can't afford them, are structural. Everything else is performance. We spend enormous energy narrating ourselves to other people, and almost none examining what our own behavior, at scale, quietly says back.
There's a version of self-knowledge that comes from introspection (the stories you tell at dinner). And there's a version that comes from the evidence of what you spend time and money on repeatedly, across months. Those two versions dont always agree but the second one doesn't lie.
Demo (synthetic data, real engine):
https://t.co/cGkIJvslKg
Repo(if you want to try this out yourself):
https://t.co/6xqZLrk6E3
Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online.
Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people.
With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway.
Stop waiting on integrations, build agents that can browse and interact with the web just like humans.