
building @floolabs engineering @youdotcom @caltech baseball alum
New York, USA
Joined January 2018
- Tweets1.4K
- Following1.4K
- Followers310
- Likes219
Patrick Donohoe retweeted
Introducing Extract API.
Fetch and parse any web page or PDF. 80% higher PDF accuracy on ParseBench-2.
→ Structured Tables, charts, forms, and scans
→ Try on web pages, no API key required to start
→ ZDR available for sensitive docs
Try it at you.com/platform/playground/…
Patrick Donohoe retweeted
stumbled into this awesome @SpaceXSI event w @patrickdonohoe
Thank you @Nasdaq for lighting up Times Square to celebrate the launch of $SMNG, the xETFs Samsung Group ETF.
We’re grateful for Nasdaq’s support and partnership in bringing SMNG to market, and proud to have Nasdaq as its listing home.
More Samsung. One ticker.
To learn more about the fund, current holdings, risks of investing, and prospectus, visit xetfs.com/smng
Patrick Donohoe retweeted
Introducing Inference Router: enterprise-grade inference on demand.
Kimi K3, GLM 5.3, DeepSeek V4.1 Flash, Qwen3.8 Flash, Muse Spark 1.3, Mercury 3 and more, available with an uptime SLA of at least 99.9%. US hosting and web search built in.
you.com/router
Patrick Donohoe retweeted
Jev is a huge power-up for research agents!
@edwardirby built a @youdotcom agent that monitors business risks, and compared Jev to an ordinary LLM judge.
• Same report quality
• But the LLM flip-flopped: 0.35 -> 0.68 -> 0.50 on the same threat
• the LLM missed 5 of 11 investigations. Jev missed none.
• Jev was 250x cheaper, 3-6x faster
Write-up 👇
How to build a reliable risk agent without a frontier model ($0.02/sweep):
• @youdotcom search
• @typesafeai Jev for typed judgments
• @QwenDevs for proposals & synthesis
• MCP for integration
Full architecture & cost breakdown below 👇
Patrick Donohoe retweeted
How to build a reliable risk agent without a frontier model ($0.02/sweep):
• @youdotcom search
• @typesafeai Jev for typed judgments
• @QwenDevs for proposals & synthesis
• MCP for integration
Full architecture & cost breakdown below 👇
Patrick Donohoe retweeted
3x fewer tokens. 84% accuracy on the Vertical RTK benchmark.
That’s what we got using Jev through @OpenRouter as a reranking layer for Knowledge, which we recently launched in the Web Search API.
Knowledge returns structured, real-time data from authoritative sources across domains like stocks, sports, and more. For many queries, that data answers the question directly, so much of the retrieved web context is unnecessary for the synthesis model.
Jev sits between retrieval and synthesis, selecting only the most relevant results to pass downstream.
Patrick Donohoe retweeted
Thrilled to launch Knowledge: extending our capabilities to data beyond the web. Stock prices, crypto, sports, weather, prediction markets, and more.
All available now through our web search API at ZERO additional cost, and just +140ms higher latency. Try it out and let us know what you think!
Introducing Knowledge: the first web search API that returns licensed real-time data alongside web results.
Prices, rates, odds, weather, scores, company and government info. The data that lives behind licensed feeds and databases instead of on crawlable pages.
Now available through @youdotcom Web Search at ZERO additional cost.
Patrick Donohoe retweeted
New: Web Search with Highlights. 95.17% on SimpleQA. Same $5 CPM. Independently verified by @braintrust: 35% cheaper than Claude's built-in search, 11% cheaper than OpenAI's.
Some questions demand the most accurate answers. @youdotcom built its Answer API to help users get grounded, cited answers to search queries in real time.
We're proud to power the inference behind it, helping You.com lower costs by 30% and match closed-source frontier model accuracy with open-weight models.
Full story here: baseten.co/resources/custome…
Patrick Donohoe retweeted
Replying to @Ryanair
@Ryanair I was just harassed by one of your gate agents at Dublin Airport. My bag (standard school backpack) clearly fit into the container. He did not let me take out a sweatshirt to put on. He immediately threatened to throw me off the flight. He was a bully and complete jerk.
Patrick Donohoe retweeted
Looking to connect with a few exceptional open source contributors.
If you've built a strong track record in OSS and are interested in working on some exciting dev infrastructure and AI projects, I'd love to chat.
Know someone? Tag them 👇
Patrick Donohoe retweeted
A few of us traded keyboards for stadium seats Monday night—Yankees vs. Tigers. ⚾
Team culture goes beyond surveys and offsites. Hanging out outside of work makes building AI infrastructure together that much more fun. Don't forget, you can't spell "happiness" without "API."
@AlexTriplett @patrickdonohoe @WallensteinTom @seherdholakia
Patrick Donohoe retweeted
🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸
🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸
🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸
🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸
🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸
Patrick Donohoe retweeted
Building a real-time intelligence app used to mean weeks of work.
Not anymore.
Remy x @YoudotCom — live web intelligence is now baked into every app Remy generates. Zero setup, zero retrieval wiring.
Search. News. Research. Page extraction. Financial data.
Describe the product. Ship the app. 🚀
👇 Read more in the comments.
Patrick Donohoe retweeted
Finally got agent pilled and set up Hermes agent on Opus, you.com for search, connected to whatsapp, told it to install Gstack on itself. Feels like I'm playing Productivity(TM): The Video Game. I'm addicted.
Patrick Donohoe retweeted
Getting a working agent is one problem. Getting a good one is a different kind of problem. You.com built an automated pipeline that lets the agent improve its own implementation through a structured feedback loop. you.com/resources/building-a… #ai #agent ✨ shout out @patrickdonohoe
Patrick Donohoe retweeted
Multi-agent swarms underperform a single well-scaled agent at the same compute budget. 🧵
We built around that finding—and hit SOTA on DeepSearchQA: 83.67% accuracy, 10M tokens, 1,000 turns.
🔗 hubs.ly/Q04cL1sr0























