Linkup

From war zone to your AI agent in 60 seconds. That’s how fast critical @AFP news dispatches now land in Linkup search.

we can't hire technical roles fast enough / Backend Engineers, Senior and Staff level / Data Engineer / Machine Learning Engineer / Full Stack Engineer apply via links below bonus: 5k referral fee if you make the intro not required: keeping eyes open in photos

"retrieval is solved” - said nobody in our office last thursday 30+ researchers and engineers, @cohere, @Sorbonne_Univ_ and Linkup Research arguing about sparse vs dense until the wine ran out which it didn't for at least 6 hours Field Notes #1: On Retrieval. #2 is coming

It's official: we are partnering with AFP to bring verified journalism to AI agents.

Join us in Paris for an evening on Retrieval. Speakers from Linkup Research, @cohere and @Sorbonne_Univ_ , dinner and drinks. 29/10, Linkup Paris HQ RSVP on Luma, link in comments.

One of our early crawl runs hit a test site with no delay between requests. Within minutes it was returning 500s. We’d knocked it offline. Now Mercator, our crawler, visits each site at most once a second. To still read billions of pages a day, going fast meant going wide. Read the full story from our CTO Denis Charrier, link in comments.

We're a tech partner for the @hcompany_ai x @42AI_ Hackathon in Paris, 7–8 November. Brief: build an agent that operates desktop software and completes a real task like a human (or better). Stack: Linkup provides the web search layer: real-time, granular data from authoritative sources, retrieved in one API call. H Company brings their agents and models, payments by @stripe, and @gladia_io for AI voice infra. Prizes: €10,000 in cash, plus credits. More rewards to be announced. Selection is competitive. Apply at link in comments.

Every team evaluating Linkup asks the same first question: how do you perform against LLM native search and the competition? Fair question. On public benchmarks, we lead: SimpleQA and SealQA-0, state of the art. But raw accuracy only tells you so much. That's why we launched verticalized benchmarks that map to real use cases: GTM (People, Company), Legal (RedlineBench), Finance (FinSearchComp). Each links to an open repo with the dataset, queries, and methodology. Re-run it yourself. But what really matters is what works for you. Picking a provider on a public leaderboard alone is how you end up with failures in production: a benchmark measures general performance, not yours. So we go one step further and help you build a custom eval on your own queries and data, guide included. Public benchmarks show who leads in general. A custom eval shows who leads for you.

High-reliability inference needs high-performance retrieval.

The @Linkup_platform team is in London for one of the most exciting builder events of the summer: @unicorn_mafia’s Hardware Hackathon, alongside @AnthropicAI, @ElevenLabs, and @modal.

Introducing the 𝗟𝗶𝗻𝗸𝘂𝗽 𝗖𝗟𝗜. The most intuitive way for agents to access real-time data from the open web - right from the terminal. 𝗦𝗲𝗮𝗿𝗰𝗵 the live web, 𝗳𝗲𝘁𝗰𝗵 any page as clean markdown, run deep 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 on your most complex questions, and return 𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 𝗝𝗦𝗢𝗡 - all with a single command. Perfect for Claude Code, Cursor, Codex, and custom agent workflows. 𝗻𝗽𝗺 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 -g linkup-search-cli Link to the docs in comments.

With Linkup's web search API, @GetArtisanAI gets structured company context, value proposition, market positioning and ICP signals for enrichment and onboarding.

Linkup is heading to @databricks DAI Summit in San Francisco next week (June 15–18).

With the Linkup Startup Program, eligible startups get up to $5,000 in credits to build AI products with reliable real-time web search and data access!