When you pass @RobinNYC on your long run Saturday. West side highway. Get it! Iykyk 🙌🏃🏽♀️🏃
🙌 @Haystack_AI agents!
🌐 Building an AI agent that needs web intelligence?
@youdotcom brings semantic web search and real-time retrieval directly into your Haystack agents!
Add YoucomWebSearch to your agent (or your pipeline), configure your You.com API credentials, and your agent can search the live web mid-run, pulling in content, snippets, and metadata that provide enough ground for downstream tasks.
Think of an agent that researches a topic in real time instead of working off its index.
🐍 pip install youcom-haystack
🔗 haystack.deepset.ai/integrat…
Super collaboration hill climbing with @NVIDIAAI and @CoreWeave ! Great inference and great web search make a difference in RL
Web search is now part of how open-weight models get trained.
Partnering with with @NVIDIAAI and @CoreWeave, we've built a training stack that brings live web search into reinforcement learning, starting with @nvidia Nemotron 3.5 Lightning.
More to come as we open this up.
Call us old fashioned, better product same price. We’ve always been driven to provide knowledge and accuracy to our customers. The marraige of the best data from the web with the best licensed data not found on the web is a beautiful thing.
Nothing to connect to. No shapely math. Just knowledge delivered at low latency. Try it today 🙌
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.
Love this @FactoryAI
excited to partner with @baseten
great inference + great search maxxs open-weight effectiveness, which optimizes token costs while you pill ✨
We're partnering with @baseten to make the case for open-weight models.
Paired with @youdotcom web search, they're a real alternative to closed models at a fraction of the price.
Already calling Baseten's Chat Completions endpoint? Add one line to your tools array:
tools=[{"type": "baseten__you__search"}]
Same model, same request. No search vendor to wire up, no retry path, no resending a growing context every turn.
power users of @AnthropicAI and love to collab by boosting our Cowork agents with the best web search from @youdotcom
what more and more builders are starting to realize is the power of unbundling the tool stack and optimizing each part of you. Web search was under appreciated for awhile, no longer. We started life bundling UI, multi model LLM reasoning and web search. A few years ago the enterprise pulled us into unbundling and just taking web search. Absolutely the right direction.
Replying to @youdotcom
@youdotcom now runs inside @claudeai.
Connector in Claude Desktop. Plugin in Claude Code.
Ground your Claude chats in what happened today: real-time web search, page content, and cited research, right inside Claude.
Setup takes under a minute 🧵
Boom, proud of the team launching Web Search with Highlights today. SOTA, built for Agentic search, no additional cost
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.
love to increase accuracy with lower TCO
Imagine doing your job without ever looking anything up on the internet. That's an agent without web search.
Giving agents the web changed what they can do, especially on anything recent that isn't reflected in training data. But agents don't search like people, so optimizing their performance is a new challenge.
There's a lot of great research out there on search behavior, but we wanted to answer a more operational question: when should search be on, and how should you configure it?
We evaluated 1,329 current events questions across 4 models and 14 conditions, comparing @youdotcom, provider built-in search, and no search. We found that:
- Search reduced the gap between models from 47.9 points to 5.6
- Retrieval gain declined with event age, from ~45 points for recent events to ~24 for the oldest
- Runs with 5+ searches scored 19–49%. A fifth query was associated with lower performance
Read the research → braintrustdata.link/web-sear…
We've been at the forefront of powering AI Agents with the best web search infrastructure
Sat down with @GemmaAllenSays on theCUBE + NYSE Wired to talk about why smart enterprises are unbundling web search from their LLM. ZDR, model flexibility, lower cost.
Thanks also to @theCUBE @Furrier @bjbaumann2014
🎥👇 Linked below
its a game of measurements and we are proud to sit in first place
No web search API returns more accurate results faster than @youdotcom Web Search with Highlights.
Artificial Analysis benchmarked 14 search APIs across three evals. We score 74 on their Search Index in 18 seconds per task.
No other provider beats this accuracy without doubling your user’s wait.
hubs.ly/Q04vddqs0
@ArtificialAnlys @mrdbourke
An under appreciated layer in AI is the fresh knowledge layer, distinct from trained knowledge, this is fresh information from search, typically searching the web. Agents like Hermes are amazing, Models as core intelligence and reasoning engines are amazing, but without fresh web intelligence they risk falling flat. Web search APIs compliment and fill this gap!
Richard Socher had the brilliant idea 5 years ago to hook an LLM to the web, a culmination of 15 years of considering how to find super intelligence. Excited to see what @NousResearch + You.com do together, the team is pretty pilled internally ✨💊
❤️
📓 Founders Bay Journal — The Thing I Can't Think About | Jun 17 newsletter.foundersbay.com/p…
It’s pronounced Bing, Bong!
Gotta have the pause. @nyknicks win, as a fan since ‘91, still feels unreal morning after. #newyorkforever
BING BONG - KNICKS ARE THE NBA CHAMPS
ORANGE AND BLUE LIGHTS ALL NIGHT
SEE THE LIGHTS LIVE: esbo.nyc/ecx
Just watched the Dark Wizard, incredible documentary. Thank you @Finsterbone Peter Mortimer and @SenderFilms wow
Dean Potter, untethered.
From directors Peter Mortimer and Nick Rosen comes an unflinching portrait of Dean Potter, the world’s most influential and controversial climber, BASE jumper and highline walker. #TheDarkWizard premieres April 14 on @hbomax.
Proud to support @marianebekker and women in tech. As a girl dad it makes me so happy to see so many women leaders, builders and innovators in tech #womenintech
Yesterday, our Head of Dev Rel @MarianeBekker spoke at @she_TO with engineering leaders from @mongoDB, @Salesforce, and @Disneyplus.
When women are given a seat at the table, the whole industry builds better products. 💪
#womeninSTEM