Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We improved our agents' web search recall from 59% to 95% while reducing cost per correct answer by 64%. Instead of asking an LLM to read and process pages one by one, we let it write code that programmatically parses, filters, and processes web data. We published the approach,... show more

Nimble

4,180 subscribers

18,941 views • 28 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

If you’re building one of these, we should talk: - AI search that answers from live web pages - RAG pipelines that go stale between crawls - Agents that need to see a page the way a person in that country sees it Teneo’s Live Web Data API loaded 97.7% of 150,000 test pages, including online shops and job boards. Free 7-day pilot. DMs open.

If you’re building one of these, we should talk: - AI search that answers from live web pages - RAG pipelines that go stale between crawls - Agents that need to see a page the way a person in that country sees it Teneo’s Live Web Data API loaded 97.7% of 150,000 test pages, including online shops and job boards. Free 7-day pilot. DMs open.

Teneo Protocol

15,331 views • 22 days ago

Introducing exa-code, a big step towards eliminating LLM code hallucination. We indexed 1B+ docs pages, Github repos, StackOverflow posts, and more. Given a query, exa-code initiates a hybrid search over this data, chunks it, and returns a concatenated, token-efficient string. In our code hallucination eval, exa-code outperforms every popular web search tool (including Exa!). Available for free: How we built it:

Introducing exa-code, a big step towards eliminating LLM code hallucination. We indexed 1B+ docs pages, Github repos, StackOverflow posts, and more. Given a query, exa-code initiates a hybrid search over this data, chunks it, and returns a concatenated, token-efficient string. In our code hallucination eval, exa-code outperforms every popular web search tool (including Exa!). Available for free: How we built it:

Exa

207,147 views • 1 year ago

Search across your chats just got faster and more powerful 🔎 From the sidebar, you can search chats, projects, images, and documents in one place across web, iOS, and Android. Use filters to narrow results, then select anything to open it directly in ChatGPT.

Search across your chats just got faster and more powerful 🔎 From the sidebar, you can search chats, projects, images, and documents in one place across web, iOS, and Android. Use filters to narrow results, then select anything to open it directly in ChatGPT.

ChatGPT

152,865 views • 3 months ago

AI code reviews with Macroscope use Parallel's Search and Task APIs to retrieve the latest docs and discussions from the web, reducing false positives that would otherwise occur as a result of LLMs with outdated knowledge. Read the case 👇

AI code reviews with Macroscope use Parallel's Search and Task APIs to retrieve the latest docs and discussions from the web, reducing false positives that would otherwise occur as a result of LLMs with outdated knowledge. Read the case 👇

Parallel Web Systems

19,702 views • 1 year ago

Introducing the official Firecrawl connector for Claude 🔥 Add state-of-the-art web search to your AI agents (94.7% on SimpleQA). Powered by our live indexes for fresher results across research, the open web, and more. Live in the Anthropic connector directory now!

Introducing the official Firecrawl connector for Claude 🔥 Add state-of-the-art web search to your AI agents (94.7% on SimpleQA). Powered by our live indexes for fresher results across research, the open web, and more. Live in the Anthropic connector directory now!

Firecrawl

91,014 views • 2 months ago

We made Valentine's Vectors, an AI app that finds people similar to you from the web :) Uses Exa search, try it here -

We made Valentine's Vectors, an AI app that finds people similar to you from the web :) Uses Exa search, try it here -

Jeffrey Wang

47,523 views • 8 months ago

Claude Code Weekly Roundup This week we rolled out a new promo for free credits on Claude Code on the web along with beautiful diffs and support for skills. In the CLI we improved fuzzy search, did a slew of bug fixes & improved triggering for interactive questions.

Claude Code Weekly Roundup This week we rolled out a new promo for free credits on Claude Code on the web along with beautiful diffs and support for skills. In the CLI we improved fuzzy search, did a slew of bug fixes & improved triggering for interactive questions.

Thariq

29,412 views • 1 year ago

This ◉ ʜᴜᴍᴀɴ ○ ᴍᴀᴄʜɪɴᴇ toggle by Parallel Web Systems is brilliant. It's a beautiful illustration of what the web will "look like" to agents. It will look like a whole lotta markdown 😄 Incidentally, we just made it such that links automatically render as markdown when agents consume it (we do the same for /𝚍𝚘𝚌𝚜). Page went from 500kb to 2kb. The web for agents will be very efficient! Try: curl -H 'accept: text/markdown'

This ◉ ʜᴜᴍᴀɴ ○ ᴍᴀᴄʜɪɴᴇ toggle by Parallel Web Systems is brilliant. It's a beautiful illustration of what the web will "look like" to agents. It will look like a whole lotta markdown 😄 Incidentally, we just made it such that links automatically render as markdown when agents consume it (we do the same for /𝚍𝚘𝚌𝚜). Page went from 500kb to 2kb. The web for agents will be very efficient! Try: curl -H 'accept: text/markdown'

Guillermo Rauch

187,645 views • 9 months ago

🌐 Agentic Browser Tools (Experimental) in Visual Studio Code! Agents can now open pages, read content, click elements, and verify changes directly in the integrated browser while building your web app. Enable ⚙️ workbench.browser.enableChatTools to try it out. Learn mode:

🌐 Agentic Browser Tools (Experimental) in Visual Studio Code! Agents can now open pages, read content, click elements, and verify changes directly in the integrated browser while building your web app. Enable ⚙️ workbench.browser.enableChatTools to try it out. Learn mode:

Visual Studio Code

211,497 views • 7 months ago

Tavily Agent Skills are now here ⚡ Your agents can now: search the live web pull fresh docs & pages research markets, competitors and products cite sources all without leaving the terminal. We also shipped tavily-best-practices. A skill that teaches agents how to build production-ready web-connected AI built on real-world lessons from builders like you. Works wherever you’re building agents: Claude · Cursor · Google Antigravity Install now with one line.

Tavily Agent Skills are now here ⚡ Your agents can now: search the live web pull fresh docs & pages research markets, competitors and products cite sources all without leaving the terminal. We also shipped tavily-best-practices. A skill that teaches agents how to build production-ready web-connected AI built on real-world lessons from builders like you. Works wherever you’re building agents: Claude · Cursor · Google Antigravity Install now with one line.

Tavily

15,287 views • 9 months ago

Maestro was rebuilt around agents. Not as an AI company. We don’t sell AI products. Maestro Machina is the operating layer underneath the business: -How we write software -Run departments -Keep every product detail, client conversation, and decision in one shared knowledge base Builder agents watch code quality and deployments in a loop that improves itself. Product agents sit inside design, sales, onboarding, and research. Knowledge agents make the company’s memory available to both. Humans still set the intent. Agents industrialize the work. One system. One mission. Build a financial system backed by energy and anchored by Bitcoin.

Maestro was rebuilt around agents. Not as an AI company. We don’t sell AI products. Maestro Machina is the operating layer underneath the business: -How we write software -Run departments -Keep every product detail, client conversation, and decision in one shared knowledge base Builder agents watch code quality and deployments in a loop that improves itself. Product agents sit inside design, sales, onboarding, and research. Knowledge agents make the company’s memory available to both. Humans still set the intent. Agents industrialize the work. One system. One mission. Build a financial system backed by energy and anchored by Bitcoin.

Maestro

11,384 views • 1 month ago

Introducing our most accurate /search yet. We trained a model to return the excerpts that best answer your query, giving agents highly relevant context from each result. It's SOTA on SimpleQA while using 10x fewer tokens than processing full pages. Now on by default for free.

Introducing our most accurate /search yet. We trained a model to return the excerpts that best answer your query, giving agents highly relevant context from each result. It's SOTA on SimpleQA while using 10x fewer tokens than processing full pages. Now on by default for free.

Firecrawl

37,432 views • 3 months ago

Across the open web, vast unstructured data is generated 24/7. From text and images to videos and streams. In a world of AI agents that create content or analyze markets, nearly all depend on one essential ingredient: fresh, live, unfiltered data from the open web. Teneo Protocol delivers exactly that. Provides the infrastructure others build on.

Across the open web, vast unstructured data is generated 24/7. From text and images to videos and streams. In a world of AI agents that create content or analyze markets, nearly all depend on one essential ingredient: fresh, live, unfiltered data from the open web. Teneo Protocol delivers exactly that. Provides the infrastructure others build on.

Teneo Protocol

78,886 views • 1 year ago

10,000 installs and counting! 📈 We created Modern Web Guidance to bring web platform expertise right into your agent workflows. Have you tried pairing these skills with Chrome DevTools for agents to audit performance and automatically fix code? Check it out and join 10K+ web developers who are coding smarter →

10,000 installs and counting! 📈 We created Modern Web Guidance to bring web platform expertise right into your agent workflows. Have you tried pairing these skills with Chrome DevTools for agents to audit performance and automatically fix code? Check it out and join 10K+ web developers who are coding smarter →

Chrome for Developers

76,265 views • 1 month ago

Trump: We are the ones saving health care. One of the things we're doing is we are going to be reducing the cost of medicines by 100%, 200, 300, 500%, even more.

Trump: We are the ones saving health care. One of the things we're doing is we are going to be reducing the cost of medicines by 100%, 200, 300, 500%, even more.

Acyn

678,034 views • 1 year ago

Cancel your $200/mo Ahrefs subscription 🤯 Claude Code can now run your SEO for you. Point it at your Search Console and it finds the wins, writes the fixes, and renders a live dashboard off your own data. All inside Claude Code. Perfect for DTC brands and agencies sitting on months of Search Console data nobody has time to read. Here's what it does: → Connects to your Search Console and GA4 through one guided setup that routes around Google's auth landmines → Finds the keywords sitting at positions 4 to 20 and scores them by the clicks you're leaving on the table → Ships the fix instead of naming it, with the rewritten title, the headings, and paste-ready content → Turns redirect chains, broken canonicals, and slow pages into dev tickets ranked by traffic at risk → Maps every query into hub-and-spoke clusters and flags where your own pages compete with each other → Drops a Monday report with week-over-week movement and exactly 3 priorities What you get: → 9 skills in one plugin, from the Google setup through to the Monday report → A live SEO dashboard with a 0 to 100 health score, rendered as one self-contained HTML file → Orphan pages and money-page link gaps, listed paste-ready → Content drafted from your own search data instead of a keyword tool's guesses Built 100% in Claude Code on your Search Console and GA4 data. 📌 Get the free plugin here:

Cancel your $200/mo Ahrefs subscription 🤯 Claude Code can now run your SEO for you. Point it at your Search Console and it finds the wins, writes the fixes, and renders a live dashboard off your own data. All inside Claude Code. Perfect for DTC brands and agencies sitting on months of Search Console data nobody has time to read. Here's what it does: → Connects to your Search Console and GA4 through one guided setup that routes around Google's auth landmines → Finds the keywords sitting at positions 4 to 20 and scores them by the clicks you're leaving on the table → Ships the fix instead of naming it, with the rewritten title, the headings, and paste-ready content → Turns redirect chains, broken canonicals, and slow pages into dev tickets ranked by traffic at risk → Maps every query into hub-and-spoke clusters and flags where your own pages compete with each other → Drops a Monday report with week-over-week movement and exactly 3 priorities What you get: → 9 skills in one plugin, from the Google setup through to the Monday report → A live SEO dashboard with a 0 to 100 health score, rendered as one self-contained HTML file → Orphan pages and money-page link gaps, listed paste-ready → Content drafted from your own search data instead of a keyword tool's guesses Built 100% in Claude Code on your Search Console and GA4 data. 📌 Get the free plugin here:

Mike Futia

22,780 views • 2 months ago

Claude Code Weekly Roundup Last week we added support for Azure, let you use "&" in the CLI to send tasks to the background, added image upload to Claude Code Web, improved Claude Code's ability to look up its docs and we're continuing to make hooks and subagents more powerful.

Claude Code Weekly Roundup Last week we added support for Azure, let you use "&" in the CLI to send tasks to the background, added image upload to Claude Code Web, improved Claude Code's ability to look up its docs and we're continuing to make hooks and subagents more powerful.

Thariq

70,840 views • 11 months ago

We built high-throughput materials labs in Menlo Park to create a loop between experiments and models. The labs generate fresh data, the models learn from it, and then help us decide what to try next. Using only 1,300 H200s, plus months of our experimental data, we mid-trained and RL’d an open-source model to surpass GPT-6 Astra on our analysis benchmark. We call it Neon. This is real footage from our lab. We’re focusing first on hard problems in materials science, including superconductors, magnets, and semiconductor materials. Read our blog posts below.

We built high-throughput materials labs in Menlo Park to create a loop between experiments and models. The labs generate fresh data, the models learn from it, and then help us decide what to try next. Using only 1,300 H200s, plus months of our experimental data, we mid-trained and RL’d an open-source model to surpass GPT-6 Astra on our analysis benchmark. We call it Neon. This is real footage from our lab. We’re focusing first on hard problems in materials science, including superconductors, magnets, and semiconductor materials. Read our blog posts below.

Liam Fedus

1,670,945 views • 1 month ago

Johnson: We are going to continue to reduce the cost of healthcare. We’ll continue reducing prices and the cost of living

Johnson: We are going to continue to reduce the cost of healthcare. We’ll continue reducing prices and the cost of living

Acyn

477,475 views • 11 months ago