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.

Function calling without waiting for Enter. Answers only when needed. TypeSafe AI Jev understands intent and arguments as you type, then executes ahead of time once everything is in place.

Yoshiki Miura

4,847 subscribers

43,205 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

13 Comments

lakshya1 month ago

@typesafeai @a1zhang time to revisit sPTC

Tim Johnson1 month ago

@typesafeai @2sidesofacoin imagine the UX possibilities!

Meir Dick1 month ago

@typesafeai Love this use case.

Frank Martinez1 month ago

@typesafeai Superb

Jacob Jacquet1 month ago

@typesafeai This is my personal favorite jev usecase so far

Yohei1 month ago

@typesafeai noice

Yoshiki Miura1 month ago

@typesafeai 🫡

RaZaan1 month ago

@typesafeai This is wild 🔥

pleasant1 month ago

@typesafeai next level

AI Mastery Guide1 month ago

@typesafeai no enter needed, that's slick

Nick Bruce1 month ago

@typesafeai @miiura how are you stopping it from firing before the user changes their mind? or is it so cheap it just fires constantly 😂

blackcat1 month ago

@typesafeai Why I would pay to get an autocomplete?

Martin Ronfort1 month ago

@typesafeai The way it handles intent and structured output is what sets it apart from standard chatbots. We actually went deeper on this here:

Related Videos

Introducing Jev Skill Suggestion for Claude Code Now you can keep your skills completely out of the context window until they’re actually needed Set your skills as user invocable only, and the Mod sends the available skill list to Jev For every request, Jev classifies which skill best matches the task, then injects only that skill into Claude’s context Works with both the TypeSafe AI API and Vercel AI Gateway Install it with one command: npx claude-code-templates@latest --mod productivity/jev-skill-suggestion Full implementation details on the Mod page at

Introducing Jev Skill Suggestion for Claude Code Now you can keep your skills completely out of the context window until they’re actually needed Set your skills as user invocable only, and the Mod sends the available skill list to Jev For every request, Jev classifies which skill best matches the task, then injects only that skill into Claude’s context Works with both the TypeSafe AI API and Vercel AI Gateway Install it with one command: npx claude-code-templates@latest --mod productivity/jev-skill-suggestion Full implementation details on the Mod page at

Daniel San

81,680 views • 1 month ago

What is a decision model? Jev by TypeSafe AI answers yes/no and multiple-choice questions, with a confidence score. Much of software development are a sequence of decisions, and Jev is 10x cheaper and faster than an LLM. Let’s understand this through practical examples:

What is a decision model? Jev by TypeSafe AI answers yes/no and multiple-choice questions, with a confidence score. Much of software development are a sequence of decisions, and Jev is 10x cheaper and faster than an LLM. Let’s understand this through practical examples:

OpenRouter

169,768 views • 1 month ago

leetcode ❌ TypeSafe AI Jev and video games ✅

leetcode ❌ TypeSafe AI Jev and video games ✅

Serge

20,871 views • 1 month ago

Introducing typesafe/jev-router: a cache-aware model router powered by Jev and TypeSafe AI The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. Here's how it works 👇🏻

Introducing typesafe/jev-router: a cache-aware model router powered by Jev and TypeSafe AI The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. Here's how it works 👇🏻

OpenRouter

1,333,540 views • 1 month ago

Starting today, more teams can try Dropbox Dash, an AI teammate that understands you and your work. Search for content, get answers about your projects, and organize everything with Stacks—all in one place.

Starting today, more teams can try Dropbox Dash, an AI teammate that understands you and your work. Search for content, get answers about your projects, and organize everything with Stacks—all in one place.

Dropbox

105,037 views • 1 year ago

Yeah Jev by TypeSafe AI is very cool. It classified 500 emails in seconds. And it costed 3.5 cents.

Yeah Jev by TypeSafe AI is very cool. It classified 500 emails in seconds. And it costed 3.5 cents.

Riley Brown

298,723 views • 1 month ago

Jev by TypeSafe AI might change how we control robots. We compared Jev, GPT-6 Astra and GPT-4.1 mini in MuJoCo. One apple. One plate. Each model chooses intent → X/Y/Z direction + gripper open/hold/close. 🧵

Jev by TypeSafe AI might change how we control robots. We compared Jev, GPT-6 Astra and GPT-4.1 mini in MuJoCo. One apple. One plate. Each model chooses intent → X/Y/Z direction + gripper open/hold/close. 🧵

OpenRoboto

49,117 views • 1 month ago

TypeSafe AI has added image support and bounding boxes to Jev. Agent Zero supports both from day one through the TypeSafe AI - Jev plugin, available in the Plugin Hub. Click the puzzle piece icon in the sidebar. Update the plugin if you already use it.

TypeSafe AI has added image support and bounding boxes to Jev. Agent Zero supports both from day one through the TypeSafe AI - Jev plugin, available in the Plugin Hub. Click the puzzle piece icon in the sidebar. Update the plugin if you already use it.

Agent Zero

202,965 views • 22 days ago

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

nader dabit

434,354 views • 1 month ago

Blanche: "Many people in this room have done it as well. They're just as guilty as a lot of people on X. When you have reporters, when you have media just being overly critical and calling the president horrible names for no reason and without evidence, it shouldn't surprise us that this type of rhetoric takes place."

Blanche: "Many people in this room have done it as well. They're just as guilty as a lot of people on X. When you have reporters, when you have media just being overly critical and calling the president horrible names for no reason and without evidence, it shouldn't surprise us that this type of rhetoric takes place."

Aaron Rupar

305,910 views • 6 months ago

what if drag and drop was smart? powered by TypeSafe AI jev

what if drag and drop was smart? powered by TypeSafe AI jev

Malay

52,679 views • 1 month 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

173,296 views • 1 month ago

Jev is actually insane. Made this real time ad creative generator. It creates ads in real time. Just start typing and Jev will choose a combination of: - All your products - 8 Layouts - 150 Headlines (you can also customize this) - 100 Subheaders - 40 Background Colors - 40 Accent Colors Instant generations. Effectively $0 per ad. (s/o TypeSafe AI) Video is in real time.

Jev is actually insane. Made this real time ad creative generator. It creates ads in real time. Just start typing and Jev will choose a combination of: - All your products - 8 Layouts - 150 Headlines (you can also customize this) - 100 Subheaders - 40 Background Colors - 40 Accent Colors Instant generations. Effectively $0 per ad. (s/o TypeSafe AI) Video is in real time.

Shiv

23,787 views • 1 month ago

Next up on First Pass: a conversation with Sam Crowder from LangChain on decision models. Jev from TypeSafe AI took the world by storm. Then OpenAI and Databricks released producs (Decisions API and ai_decide function) So what are Decision Models? We dig in!

Next up on First Pass: a conversation with Sam Crowder from LangChain on decision models. Jev from TypeSafe AI took the world by storm. Then OpenAI and Databricks released producs (Decisions API and ai_decide function) So what are Decision Models? We dig in!

Jamin Ball

12,147 views • 28 days ago

The smartass clipboard chrome extension I built with TypeSafe AI Jev is now open source. It reads the text you paste, breaks it into blocks and scans the form to understand what each field is. Jev then matches the right block to each field, verifies it against the original text and pastes only confident matches.

The smartass clipboard chrome extension I built with TypeSafe AI Jev is now open source. It reads the text you paste, breaks it into blocks and scans the form to understand what each field is. Jev then matches the right block to each field, verifies it against the original text and pastes only confident matches.

Noman

30,262 views • 1 month ago

Congrats to Diogo Almeida & TypeSafe AI , I didn't know how much I needed this model until I got access. My Simplified Breakdown of Jev 👇

Congrats to Diogo Almeida & TypeSafe AI , I didn't know how much I needed this model until I got access. My Simplified Breakdown of Jev 👇

Rob Shocks - Build With AI

14,183 views • 1 month ago

BREAKING: Acting Attorney General Todd Blanche calls out the media for continuing to fuel threats against President Trump: "They're just as guilty as a lot of people on X. When you have when you have reporters, when you have media just being overly critical and calling the president horrible names for no reason and without evidence, without proof, it shouldn't surprise us that this type of rhetoric takes place."

BREAKING: Acting Attorney General Todd Blanche calls out the media for continuing to fuel threats against President Trump: "They're just as guilty as a lot of people on X. When you have when you have reporters, when you have media just being overly critical and calling the president horrible names for no reason and without evidence, without proof, it shouldn't surprise us that this type of rhetoric takes place."

Fox News

89,603 views • 6 months ago

JEV MADE ME $3,031 WITH A 7-MINUTE AI AGENT SETUP Prompt → GrokBot → Jev decision → GrokBot execution → Result Jev decides what actually needs to run. GrokBot handles the execution directly on your computer. → Less wasted calls → Lower cost → Faster agent workflow Create a Typesafe API key, install typesafe-sdk and smoke test system_one. Build the usage lab with router, dry-run, config and logs. Add jev-usage-router before browser, research, retry or extra bot calls. Start in shadow mode and check the logs. Once you trust the routing, flip it to active. Now GrokBot follows the route. Jev decides what makes sense to run. You still control irreversible actions. I’ve already tested this setup on routine tasks. And the difference is crazy. → Jev decides → GrokBot executes → You stay in control Copy the setup and explore the repo below. → Full Jev deep dive ↓

JEV MADE ME $3,031 WITH A 7-MINUTE AI AGENT SETUP Prompt → GrokBot → Jev decision → GrokBot execution → Result Jev decides what actually needs to run. GrokBot handles the execution directly on your computer. → Less wasted calls → Lower cost → Faster agent workflow Create a Typesafe API key, install typesafe-sdk and smoke test system_one. Build the usage lab with router, dry-run, config and logs. Add jev-usage-router before browser, research, retry or extra bot calls. Start in shadow mode and check the logs. Once you trust the routing, flip it to active. Now GrokBot follows the route. Jev decides what makes sense to run. You still control irreversible actions. I’ve already tested this setup on routine tasks. And the difference is crazy. → Jev decides → GrokBot executes → You stay in control Copy the setup and explore the repo below. → Full Jev deep dive ↓

winkle.

12,135 views • 1 month ago

What if you could compose music with Jev? Music composition is full of structured choices: tempo, instruments, chords, rhythm, etc. So I wanted to see if Jev could compose an entire song, one decision at a time. Meet Jevthoven. cc: TypeSafe AI

What if you could compose music with Jev? Music composition is full of structured choices: tempo, instruments, chords, rhythm, etc. So I wanted to see if Jev could compose an entire song, one decision at a time. Meet Jevthoven. cc: TypeSafe AI

cocktail peanut

25,664 views • 1 month ago

Latency has been the main UX concern we've heard for Flutter teams building GenUI/A2UI experiences. The new Jev model from TypeSafe AI solves this and unlocks a ton of new potential. All the UI generated in this video was picked by Jev - it felt like everything was running locally!

Latency has been the main UX concern we've heard for Flutter teams building GenUI/A2UI experiences. The new Jev model from TypeSafe AI solves this and unlocks a ton of new potential. All the UI generated in this video was picked by Jev - it felt like everything was running locally!

Abdallah Shaban

11,177 views • 1 month ago