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.

I built a free internal linking tool using TypeSafe AI Jev for classifying and selecting the links. BYOK or pay $1 to use mine. It works for up to 500 pages and gives you a CSV or JSON to pass to an LLM to implement.

Ian Nuttall

81,343 subscribers

34,221 views • 4 days ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

30 Comments

Lucas4 days ago

@typesafeai YEAH SURE ILL ENTER MY KEY THERE HAHAHAHAHHA

Jamie Marsland - Head of WordPress YouTube ❤️4 days ago

@typesafeai Great minds...

Iron3 days ago

@typesafeai Mate im literally bookmarking every tweet of yours

Ian Nuttall3 days ago

@typesafeai I would be bookmarking yours if you posted more sauce! Simple Analytics is such a good biz 😍

Iron3 days ago

@typesafeai yeah need to get back into it. felt X was a bit off for a long time

Ian Nuttall3 days ago

@typesafeai It’s better now if they could figure out these bullshit AI replies on every post.

Eduardo Higareda4 days ago

@typesafeai Hey Ian, I’m trying to test the tool, but I’m getting this error. My site definitely has more than 500 pages, so I’m not sure if that’s the reason.

Ian Nuttall4 days ago

@typesafeai Sorry, fixing it now!

Yuri Moreno3 days ago

@typesafeai Can you open source it?

ShadowAguy3 days ago

@typesafeai BYOK or pay $1, and you ship a CSV that an LLM has to turn into actual links. The gap between 'here are the links' and 'they are deployed' is still the whole problem, isn't it?

Stephan Kaag3 days ago

Works!

Matt Oney3 days ago

@typesafeai Really cool that you offer the BYOK option. Thanks dude

Gatien3 days ago

@typesafeai open source?

Rhodri Andrews3 days ago

@typesafeai Thanks for sharing.

Mojow4 days ago

@typesafeai How would one do this with Wordpress with this data?

Ian Nuttall4 days ago

@typesafeai Probably give your agent access to the WordPress MCP

Juraj Ivan @ QikBuild4 days ago

@typesafeai A free internal linking tool that uses Jev to classify and pick links for up to 500 pages is super useful. Catalogued at

Harsh Todi3 days ago

@typesafeai another internal linking tool by JEV. Thinking I should also vibe code one

Elie Habib4 days ago

@typesafeai Always ends with this error - "The connection closed before the report was ready" - before reaching 500 pages

Ian Nuttall4 days ago

@typesafeai Just pushed a fix for this, sorry!

Elie Habib4 days ago

@typesafeai It's working well, thank you. Get me to pay more and remove limits next.

Ian Nuttall4 days ago

@typesafeai Yes definitely bumping it soon I just need a better backend for larger volume clearly 😂

Mojow4 days ago

@typesafeai Typesafe is also full no new registrations so can’t use the tool I paid it breaks 🤷‍♀️

Ian Nuttall4 days ago

@typesafeai Fixing now, if you keep the same URL you got redirected back to you'll be able to run it again in a minute!

Mojow3 days ago

@typesafeai I alrdy paid 👀

Tom Lee3 days ago

@typesafeai Gonna test this now

Hakan Makes3 days ago

@typesafeai Does it work with big enterprise ecom stores?

Saad4 days ago

@typesafeai :( The connection closed before the report was ready. twice... spent 20 cents on it 😭

Ian Nuttall4 days ago

@typesafeai Fixing it now! Send me a Stripe link and I'll pay you back $1

Saad4 days ago

@typesafeai If I had to pay you for everything I have learnt from you, I will be poorer than I am :D this is just feedback coz I wanna use the tool 🫡

Related Videos

jev has changed computer-use forever. i built a computer use tool with jev that costs basically nothing to use, and has sub-second latency. it can even decide what to type, and doesn't need an LLM. open source. link below. no LLM required.

jev has changed computer-use forever. i built a computer use tool with jev that costs basically nothing to use, and has sub-second latency. it can even decide what to type, and doesn't need an LLM. open source. link below. no LLM required.

shiv

168,251 views • 7 days ago

If you are confused about why 𝗝𝗲𝘃 is being called the "Internet" moment for the AI industry. This is 100% worth your time. In fact, you should watch it: It tells LLMs what to do next, in milliseconds & at almost zero cost. If you set it up correctly, you will have the AI engineer’s setup for 2028. How to set up & use Jev (to actually get the 100x): 1. Join the waitlist; it's fairly quick: typesafe .ai. 2. Then go to Claude Code or Codex. 3. Choose Opus 5-Low or Sol-Low. 4. Copy and paste this prompt: "[claude or codex] plugin marketplace add typesafe-ai/skills [claude or codex] plugin install typesafe@typesafe-ai" 5. When you type /typesafe, the skill shows up. 6. Paste your API key once and click "Allow" 7. Start with $5 in free credit. It's hard to spend more. ----- Now, here are the 3 ways to actually use Jev: 1. Jev for Linkedin I have 38,000 connections & invitations on LinkedIn. I have a new company to launch. I need to find a couple of hundred people to message. to do while saving time: > Export your LinkedIn connections and invitations. > Connect Claude to GitHub, Vercel & Apify. > Create an Apify API key to enrich your data. > Go to LinkedIn Settings → Data privacy. > Get a copy. LinkedIn will email you a ZIP file. > Open the file & find the Connections CSVs. > Upload the files to Jev. > Use Jev to classify your contacts. > Review the shortlist. 2. Jev for Gmail To go through all of my Gmail contacts and email the right people. > Go to Google Contacts. Open Other contacts. > Select all contacts. Export them. > Upload the file to Claude Code or Codex. > Use Jev to sort them into: Keep, Review, Remove and Review everything before removing anything. 3. You got lost in Claude Code, GitHub, Vercel, Apify, Jev, Typesafe. I feel you. It is overwhelming. That’s why I included the entire copy-and-paste prompt for each use case in the newsletter: A 45-second TL;DR by Matija Sosic.

If you are confused about why 𝗝𝗲𝘃 is being called the "Internet" moment for the AI industry. This is 100% worth your time. In fact, you should watch it: It tells LLMs what to do next, in milliseconds & at almost zero cost. If you set it up correctly, you will have the AI engineer’s setup for 2028. How to set up & use Jev (to actually get the 100x): 1. Join the waitlist; it's fairly quick: typesafe .ai. 2. Then go to Claude Code or Codex. 3. Choose Opus 5-Low or Sol-Low. 4. Copy and paste this prompt: "[claude or codex] plugin marketplace add typesafe-ai/skills [claude or codex] plugin install typesafe@typesafe-ai" 5. When you type /typesafe, the skill shows up. 6. Paste your API key once and click "Allow" 7. Start with $5 in free credit. It's hard to spend more. ----- Now, here are the 3 ways to actually use Jev: 1. Jev for Linkedin I have 38,000 connections & invitations on LinkedIn. I have a new company to launch. I need to find a couple of hundred people to message. to do while saving time: > Export your LinkedIn connections and invitations. > Connect Claude to GitHub, Vercel & Apify. > Create an Apify API key to enrich your data. > Go to LinkedIn Settings → Data privacy. > Get a copy. LinkedIn will email you a ZIP file. > Open the file & find the Connections CSVs. > Upload the files to Jev. > Use Jev to classify your contacts. > Review the shortlist. 2. Jev for Gmail To go through all of my Gmail contacts and email the right people. > Go to Google Contacts. Open Other contacts. > Select all contacts. Export them. > Upload the file to Claude Code or Codex. > Use Jev to sort them into: Keep, Review, Remove and Review everything before removing anything. 3. You got lost in Claude Code, GitHub, Vercel, Apify, Jev, Typesafe. I feel you. It is overwhelming. That’s why I included the entire copy-and-paste prompt for each use case in the newsletter: A 45-second TL;DR by Matija Sosic.

Ruben Hassid

169,511 views • 5 days ago

I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!

I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!

CJ (Coding Garden)

114,186 views • 8 days ago

Jev made our Slack agent 2x faster ⚡️ Our agent can be quite slow because it needs to read skills and figure out which tools to call. We used TypeSafe AI's new model to speed this up by first passing it the prompt and classifying the best skill, tool and params to use before handing it to the agent

Jev made our Slack agent 2x faster ⚡️ Our agent can be quite slow because it needs to read skills and figure out which tools to call. We used TypeSafe AI's new model to speed this up by first passing it the prompt and classifying the best skill, tool and params to use before handing it to the agent

John Yeo

34,970 views • 8 days ago

Today I’m excited to show you our new harness called AgentRun, built with Pi and TypeSafe AI's Jev. It’s built for an agent to learn how to do a job, code itself a general solution, and then get out of the way.

Today I’m excited to show you our new harness called AgentRun, built with Pi and TypeSafe AI's Jev. It’s built for an agent to learn how to do a job, code itself a general solution, and then get out of the way.

Miguel Ríos Berríos

61,013 views • 7 days ago

I built a tool to help you create Product 1 vs Product 2 content in WordPress 🔥 Watch this video on how to take a product dataset and create a CSV to import using WP All Import (or Multi Page Generator) in two clicks. Then reply 👋 if you want me to release it!

I built a tool to help you create Product 1 vs Product 2 content in WordPress 🔥 Watch this video on how to take a product dataset and create a CSV to import using WP All Import (or Multi Page Generator) in two clicks. Then reply 👋 if you want me to release it!

Ian Nuttall

29,476 views • 3 years ago

Today I'm launching - a tool for creating AI humans to promote any product. I built it as an internal tool for marketing my own apps, instead of hiring and managing hundreds of creators. You can create as many characters as you want and swap them into videos you record or trending tiktoks.

Today I'm launching - a tool for creating AI humans to promote any product. I built it as an internal tool for marketing my own apps, instead of hiring and managing hundreds of creators. You can create as many characters as you want and swap them into videos you record or trending tiktoks.

neer

28,652 views • 7 months ago

I've always wanted a way to talk to my Mac and do things on the go. Until now, it was super slow. So I built Macbrow. Voice-controlled browser and computer-use agent. Built using Gradium Browser Use and TypeSafe AI Still early and a work in progress.

I've always wanted a way to talk to my Mac and do things on the go. Until now, it was super slow. So I built Macbrow. Voice-controlled browser and computer-use agent. Built using Gradium Browser Use and TypeSafe AI Still early and a work in progress.

Pratim Bhosale

54,565 views • 7 days ago

I built a Claude skill that helps you review a report as an analyst. Now, it thinks like a senior analyst for you. The readme file will explain how to use it as a skill on Claude or Copilot or Chatgpt Use & let me how it works. My gift to U

I built a Claude skill that helps you review a report as an analyst. Now, it thinks like a senior analyst for you. The readme file will explain how to use it as a skill on Claude or Copilot or Chatgpt Use & let me how it works. My gift to U

David Abu _

45,698 views • 6 months ago

Tutorial for Nano Banana and annotations. Use a tool like Canva to edit your image with prompts and guidance. Bring this to Freepik or the Gemini app and ask it to follow the instructions. Use AI video tools to bring to life!

Tutorial for Nano Banana and annotations. Use a tool like Canva to edit your image with prompts and guidance. Bring this to Freepik or the Gemini app and ask it to follow the instructions. Use AI video tools to bring to life!

Jerrod Lew

41,283 views • 1 year ago

Jev is going to be a RL beast for games It took me a week worth of work to get a PPO policy trained to clear Super Mario Bros World 1-1. It took me less than 30 minutes to achieve the same result with TypeSafe AI Jev!

Jev is going to be a RL beast for games It took me a week worth of work to get a PPO policy trained to clear Super Mario Bros World 1-1. It took me less than 30 minutes to achieve the same result with TypeSafe AI Jev!

Shantanu Goel

27,556 views • 9 days ago

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

rody

194,422 views • 5 days ago

I built what I believe is the 2025 standard for running traffic using AI. An AI agent trained on private Telegram groups, underground forums, and internal SOPs, it gives you funnel strategies, automation setups, and traffic methods that actually work right now. It works for every niche. Every platform. Comment “ACCESS” & I’ll send you access to it in DMs.

I built what I believe is the 2025 standard for running traffic using AI. An AI agent trained on private Telegram groups, underground forums, and internal SOPs, it gives you funnel strategies, automation setups, and traffic methods that actually work right now. It works for every niche. Every platform. Comment “ACCESS” & I’ll send you access to it in DMs.

casualhyped

37,720 views • 1 year ago

Google AI Studio is absolutely insane… I uploaded a video and asked it to implement the features, and within just 5 minutes it built an AI startup for me

Google AI Studio is absolutely insane… I uploaded a video and asked it to implement the features, and within just 5 minutes it built an AI startup for me

CHOI

74,441 views • 1 year ago

Introducing Jev Model Router for Claude Code This Claude Code Mod lets you use Jev through its direct TypeSafe AI API or Vercel AI Gateway With every request you send to Claude Code, Jev classifies the subagent model, main model (only at session start to avoid breaking the cache), and effort level Install it with one command: npx claude-code-templates@latest --mod productivity/jev-model-router Full Mod details:

Introducing Jev Model Router for Claude Code This Claude Code Mod lets you use Jev through its direct TypeSafe AI API or Vercel AI Gateway With every request you send to Claude Code, Jev classifies the subagent model, main model (only at session start to avoid breaking the cache), and effort level Install it with one command: npx claude-code-templates@latest --mod productivity/jev-model-router Full Mod details:

Daniel San

201,588 views • 7 days ago

You lose customers every time an agent like Codex or Claude Code uses your product and fails to complete a task. At Scope (YC P26) we built a feature to find those errors for you and fix them. Let’s use Vercel as an example to show you how it works! Want us to run a workflow for you? Drop it in the comments below :)

You lose customers every time an agent like Codex or Claude Code uses your product and fails to complete a task. At Scope (YC P26) we built a feature to find those errors for you and fix them. Let’s use Vercel as an example to show you how it works! Want us to run a workflow for you? Drop it in the comments below :)

Lin

16,349 views • 15 days ago

I don't want you to look at my content... And watch it because I made it with AI. AI is a tool, a means to an end, to tell a good story, an ad, or a visual masterpiece. I took Luma for a spin with images from Google's Whisk to achieve a cinematic feeling. It worked:

I don't want you to look at my content... And watch it because I made it with AI. AI is a tool, a means to an end, to tell a good story, an ad, or a visual masterpiece. I took Luma for a spin with images from Google's Whisk to achieve a cinematic feeling. It worked:

Alex Patrascu

18,474 views • 1 year ago