Mathew Varughese retweeted
Trillions are pouring into the race to build the first general superintelligence, but leveraging your own specialized know-it-all is now possible as of today.
I built the knowledge systems at @stripe and @uber. Then I helped Anthropic, Metronome, and Graphite build a killer developer experience. Everyone wants Stripe-level quality, but that bar is too low.
Falconer gives you and your customers complete, specialized intelligence: an internal knowledge base and external documentation in one beautiful package. Falconer is the ultimate trust engine to manage your context: self-driving, observable, and agent-friendly.
I co-founded @falconer_ai with @mbenedetto212 and assembled a team of know-it-all builders. We're backed by fellow know-it-alls @thegp, @BoxGroup, @svangel, @karimatiyeh, @benln, @zachlloydtweets, @CeciStalls, @MerrillLutsky, @scottmac, @malthe, and @adamjstevenson, with angels from Anthropic, Stripe, Meta, Cursor, Replit, and more.
Frontier intelligence companies like @FireworksAI_HQ and @⬛⬛⬛⬛⬛⬛; fintech companies like @payabli and @vori; and healthtech companies like @thatch_ai use @falconer_ai because they all share the same vision as us: the knowledge you earn should belong to you.
Now you can know everything, so you can build anything.
Mathew Varughese retweeted
My first project as a new grad at @stripe was a service to turn chargeback evidence submitted through our API into PDFs and fax them to our banking partners. I'd never seen a fax in my life.
It was nobody's dream project, and I was sure I'd get fired, so I went deep. I learned how much complexity we could hide behind a simple API, even when our banking partners still relied on paper faxes. Two years later, I got to build the first version of Stripe Radar to stop fraudulent chargebacks in the first place.
You often don't get to choose where you start, but going deep, becoming the expert, and earning the trust to take bigger swings is still a great way to build a career. AI has changed how we work, but I don't think it's changed that playbook.
@vikrams039 wrote the guide I wish I'd had as a new grad: vikramsingh.me/increase-your…
How it works under the hood: stripe.dev/blog/how-api-chan….
Mathew Varughese retweeted
For teams who move at the speed of agents, knowledge becomes fragmented, lost to the void, and out of date as fast as its created.
We built Falconer to solve that.
Mathew Varughese retweeted
Craft and beauty are finally coming to internal docs. Today we're previewing Falconer: the single source of truth for company knowledge.
We're still working through our waitlist, but are now excited to take on more demo requests.
Engineers spend way too much time answering repeated questions and searching for outdated information. We experienced these problems during hypergrowth at Uber and Stripe and thought, "What if we applied external docs treatment to our internal docs?"
That simple approach achieved pretty remarkable results for productivity. And now Falconer is building the AI-native version of those platforms for everyone.
With Falconer, your internal docs are:
- In one place
- Always up to date
- Easy to find
- Synced with your data
Coding agents allow us to generate more code faster than ever...but that code is poorly understood and out of step with the company's crown jewels: business context and tribal knowledge.
Falconer's mission is to connect teams and agents with a shared memory system—always available and always accurate. We're working on it, and will have much more to share soon.
Mathew Varughese retweeted
In-depth technical details on how we built @stripe's AI assistant for VS Code, including retrieval, evals, measurement, and how we embedded Q&A data from our Discord channel: stripe.dev/blog/stripes-ai-a…
Mathew Varughese retweeted
We’ve added /llms.txt and Markdown to @stripe docs: docs.stripe.com/llms.txt
Use the .md pages to quickly move Stripe knowledge into your LLM of choice. 📄
My friend Andrew and I are gonna run/bike to every @CrunchGym in NYC today and do workout at each. Will prob regret this by gym #2
varughese.notion.site/Crunch…
Bonus #20, back at Bowery where we started, 13 hours later. Thanks for following along, see you again next year















