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.

Before → call an LLM, then build the tools and execution loop yourself. With Pine → integrate one SDK, send a job, get finished work back. Prompt in. Work out. #PineComputer #ComputerUse #DeveloperTools

nerea

97,633 subscribers

59,198 views • 2 days ago •via X (Twitter)

Education Science & Technology #PineComputer #ComputerUse #DeveloperTools

Anya Rossi• Live Now

Private livecam show

4 Comments

robin.1 day ago

Why build the execution loop yourself?

tobarra2 days ago

The “sign in once, stay signed in” part is lowkey underrated. Small details make a huge difference in real workflows.

naldz.1 day ago

Prompt in, work out. That’s the kind of workflow AI agents have been missing

toba2 days ago

AI is getting smarter, but the tools around it need to catch up. This feels like the right direction.

Related Videos

🔥🔥 Introducing BuildKit 2.0 🔥🔥 The shadcn for AI tools.→ Build AI tools + MCPs in minutes → Customize with a single prompt → Works with any SDK - AI SDK, , #mcp Stop waiting for integrations. Start creating them. 🚀 Out now.

🔥🔥 Introducing BuildKit 2.0 🔥🔥 The shadcn for AI tools.→ Build AI tools + MCPs in minutes → Customize with a single prompt → Works with any SDK - AI SDK, , #mcp Stop waiting for integrations. Start creating them. 🚀 Out now.

Moe

14,606 views • 1 year ago

we're releasing an experimental typescript sdk! npm install xAI-official/sdk get text, voice, image and video in one sdk, with the latest grok models and tools that run on our servers, like real-time X search, web search, code execution and remote mcp

we're releasing an experimental typescript sdk! npm install xAI-official/sdk get text, voice, image and video in one sdk, with the latest grok models and tools that run on our servers, like real-time X search, web search, code execution and remote mcp

eric zakariasson

123,094 views • 9 days ago

Introducing Loop The autonomous business manager that runs your outreach, your follow-ups, and your pipeline,while you focus on the work only you can do. Loop doesn't live in your inbox. Your inbox lives in Loop. Reads every lead like a teammate who's been on your team for years Writes the reply, makes the call, chases the deal when email goes cold Pauses the moment a human actually needs to show up Replaces the patchwork of CRMs, outreach tools, and follow-up apps with one system that does the work Stop managing tools. Start running your loop. comment "loop" and we'll send you in. loop

Introducing Loop The autonomous business manager that runs your outreach, your follow-ups, and your pipeline,while you focus on the work only you can do. Loop doesn't live in your inbox. Your inbox lives in Loop. Reads every lead like a teammate who's been on your team for years Writes the reply, makes the call, chases the deal when email goes cold Pauses the moment a human actually needs to show up Replaces the patchwork of CRMs, outreach tools, and follow-up apps with one system that does the work Stop managing tools. Start running your loop. comment "loop" and we'll send you in. loop

Anushka Singh

13,039 views • 4 months ago

Roblox is continuing to work on accessory scaling and refinement tools in the Avatar Editor. Here's an example on how it will work on a few different accessory types. This video is from a work in progress build and is subject to change before release. Credit: joshi77/Discord

Bloxy News

481,114 views • 2 years ago

This guy explained agent harness, memory, and loop engineering in one video - clearer than most paid courses a raw LLM with no harness is a wild horse. all power, no direction > trace the run -> score it with an LLM -> diagnose the bottleneck -> patch it -> ship it that loop is what lets an agent get sharper on its own, run after run memory + harness + loop engineering + evals - that's the whole stack in one picture watch it, then grab the diagram below

This guy explained agent harness, memory, and loop engineering in one video - clearer than most paid courses a raw LLM with no harness is a wild horse. all power, no direction > trace the run -> score it with an LLM -> diagnose the bottleneck -> patch it -> ship it that loop is what lets an agent get sharper on its own, run after run memory + harness + loop engineering + evals - that's the whole stack in one picture watch it, then grab the diagram below

Mr. Buzzoni

45,204 views • 2 months ago

WORK WORK WORK A point-and-click puzzle exploration game with ARG elements where you are an employee of a tech company trapped in a time loop. Can you break out of the sinister cycle? Wishlist the game on Steam

WORK WORK WORK A point-and-click puzzle exploration game with ARG elements where you are an employee of a tech company trapped in a time loop. Can you break out of the sinister cycle? Wishlist the game on Steam

Mojiken Studio 💫

73,502 views • 8 months ago

Your team deserves more from your agent observability platform - a single, connected place for instrumentation, investigation, and measurement, enhanced with intelligence. In Braintrust, you can start with an open-ended prompt about agent behavior and carry the investigation into code, evals, automation, and monitoring. New tools like Patterns and Debugger make it easier to find recurring behavior, get to root causes, and act on what you learn. The context you build in one step automatically follows to the next. Work in the platform with an enhanced Loop experience, or move to your coding agent of choice. Read more →

Your team deserves more from your agent observability platform - a single, connected place for instrumentation, investigation, and measurement, enhanced with intelligence. In Braintrust, you can start with an open-ended prompt about agent behavior and carry the investigation into code, evals, automation, and monitoring. New tools like Patterns and Debugger make it easier to find recurring behavior, get to root causes, and act on what you learn. The context you build in one step automatically follows to the next. Work in the platform with an enhanced Loop experience, or move to your coding agent of choice. Read more →

Braintrust

43,141 views • 1 month ago

Build, deploy, and verify a smart contract on Injective in one prompt. The Injective MCP server gives your coding agent the tools to do it. Tell it what the contract should do, ask it to deploy and verify, and it hands back a live contract address. Let the agent do the work. 🥷

Build, deploy, and verify a smart contract on Injective in one prompt. The Injective MCP server gives your coding agent the tools to do it. Tell it what the contract should do, ask it to deploy and verify, and it hands back a live contract address. Let the agent do the work. 🥷

Injective 🥷

29,105 views • 3 months ago

I think i found the best place to actually get work done right now. Imagine one hub with every popular LLM inside and the ability to plug them into any app you use. This is where it stops feeling like separate tools: You drop your coworkers into a chat with the AI agents and work on the task together, in one place. And the agents don't just answer, they check each other's work. One drafts, another pushes back, another catches what's missing. This isn't the future. it's Bloome.

I think i found the best place to actually get work done right now. Imagine one hub with every popular LLM inside and the ability to plug them into any app you use. This is where it stops feeling like separate tools: You drop your coworkers into a chat with the AI agents and work on the task together, in one place. And the agents don't just answer, they check each other's work. One drafts, another pushes back, another catches what's missing. This isn't the future. it's Bloome.

Anatoli Kopadze

58,448 views • 3 months ago

“I was able to get my job done in two to four hours a day and build Ms. Anti Work, the media company that I run today.” At the #FortuneWorkplaceSummit, Ms. Anti Work founder Gabrielle Judge said her former “lazy girl job” — a white-collar gig with a favorable work-life balance — gave her the flexibility to build her own company.

“I was able to get my job done in two to four hours a day and build Ms. Anti Work, the media company that I run today.” At the #FortuneWorkplaceSummit, Ms. Anti Work founder Gabrielle Judge said her former “lazy girl job” — a white-collar gig with a favorable work-life balance — gave her the flexibility to build her own company.

FORTUNE

11,857 views • 4 months ago

Voice news! 🗣️ #SOTOH2025 Actually, it's a demo from JLo. Check out how the announce and conversation features work with an LLM 👇🏼

Voice news! 🗣️ #SOTOH2025 Actually, it's a demo from JLo. Check out how the announce and conversation features work with an LLM 👇🏼

Home Assistant

18,456 views • 1 year ago

Woman are not ment to work the way Men are. They get burned out when a household is dependent on their job. And then they call themselves independent when in reality they are just trapped.

Woman are not ment to work the way Men are. They get burned out when a household is dependent on their job. And then they call themselves independent when in reality they are just trapped.

Rabbi Shalom Landau

29,425 views • 4 months ago

Anthropic engineer: «You're not supposed to sit and re-prompt Claude all day. You build one loop, and it does the work while you sleep.» • 00:00 - Build your first agent that runs on its own • 05:02 - The loop that fixes its own mistakes • 16:43 - Why Claude forgets you between chats, and the fix You can learn it in one afternoon. 30 minutes here replace what most people spend a year figuring out. Watch it today, then read the guide on building loops below.

Anthropic engineer: «You're not supposed to sit and re-prompt Claude all day. You build one loop, and it does the work while you sleep.» • 00:00 - Build your first agent that runs on its own • 05:02 - The loop that fixes its own mistakes • 16:43 - Why Claude forgets you between chats, and the fix You can learn it in one afternoon. 30 minutes here replace what most people spend a year figuring out. Watch it today, then read the guide on building loops below.

Raytar

28,046 views • 3 months ago

He is 17 sold an LLM system to Anthropic for $2.2M - and at Stanford shared how to build and sell one from scratch: 00:20 - how to build an LLM system that Anthropic will buy for millions 08:34 - one prompt in Opus 5 and the LLM system is ready to sell in 60 minutes 23:47 - how to sell an LLM to Anthropic at 17 with no experience and reach $2.2M a year after watching I built my first LLM system in 60 minutes - and sold it to Anthropic for $120k. save & watch - the article below is one file that builds an LLM system and sells it to Anthropic for $2.2M.

He is 17 sold an LLM system to Anthropic for $2.2M - and at Stanford shared how to build and sell one from scratch: 00:20 - how to build an LLM system that Anthropic will buy for millions 08:34 - one prompt in Opus 5 and the LLM system is ready to sell in 60 minutes 23:47 - how to sell an LLM to Anthropic at 17 with no experience and reach $2.2M a year after watching I built my first LLM system in 60 minutes - and sold it to Anthropic for $120k. save & watch - the article below is one file that builds an LLM system and sells it to Anthropic for $2.2M.

Noisy

25,571 views • 29 days ago

From one prompt to a finished track 🪙 🎵 Meet Lari — an artist signed with IMBA. We caught up with her to hear how JGGL fits into her creative process — here's what she told us. Years in music, countless tools tried. But finding the right sound — the one that actually matches your mood and your vibe — that's always the hardest part. JGGL changed that. One prompt, and she had a direction to work from. The rest? Pure Lari. 🔥 This is JGGL — where the artist stays in control, and the AI just keeps up.

From one prompt to a finished track 🪙 🎵 Meet Lari — an artist signed with IMBA. We caught up with her to hear how JGGL fits into her creative process — here's what she told us. Years in music, countless tools tried. But finding the right sound — the one that actually matches your mood and your vibe — that's always the hardest part. JGGL changed that. One prompt, and she had a direction to work from. The rest? Pure Lari. 🔥 This is JGGL — where the artist stays in control, and the AI just keeps up.

JGGL

11,662 views • 2 months ago

$1,000+ earned by companies with no employees, no founder doing the work, and no human in the loop. just an AI building and operating a business from a prompt. 2 companies already past $ 1k. dozens past $100. this is NanoCorp:

$1,000+ earned by companies with no employees, no founder doing the work, and no human in the loop. just an AI building and operating a business from a prompt. 2 companies already past $ 1k. dozens past $100. this is NanoCorp:

Pierre-Louis Biojout (PLB)

59,733 views • 4 months ago

Advice for AI engineers 💡 A local AI assistant is just a while loop, an LLM and a set of tools. Here's a step-by-step lesson on how to build one from scratch with Liquid AI LFM2-24B-A2B running on llama.cpp. No cloud APIs. Enjoy ↓

Advice for AI engineers 💡 A local AI assistant is just a while loop, an LLM and a set of tools. Here's a step-by-step lesson on how to build one from scratch with Liquid AI LFM2-24B-A2B running on llama.cpp. No cloud APIs. Enjoy ↓

Pau Labarta Bajo

15,463 views • 5 months ago

🎨 Introducing Prompt Canvas — a novel UX for prompt engineering Building LLM applications requires new and dedicated tools for prompt engineering. With Prompt Canvas in LangSmith, you can: • Collaborate with an AI agent to draft, refine, and edit your prompts • Define custom quick actions to standardize prompting strategies used across the org ✍️ Learn more: ➡️ Try it out:

🎨 Introducing Prompt Canvas — a novel UX for prompt engineering Building LLM applications requires new and dedicated tools for prompt engineering. With Prompt Canvas in LangSmith, you can: • Collaborate with an AI agent to draft, refine, and edit your prompts • Define custom quick actions to standardize prompting strategies used across the org ✍️ Learn more: ➡️ Try it out:

LangChain

43,733 views • 1 year ago

Boris Cherny, the engineer who built Claude Code: "I don't talk to an agent anymore. I talk to a loop" a prompt is one instruction you babysit. a loop is a goal the AI works toward on its own: > it plans > does the work > checks itself > fixes what's weak > and repeats until it's done you step out, the work keeps going that's the shift the best engineers quietly moved to. most people hear a line like that and have no idea what it means in practice this breaks it down without the hype: what a loop actually is, when it's worth building, when it's a money trap, and how to run one yourself today watch his clip, then read the article below

Boris Cherny, the engineer who built Claude Code: "I don't talk to an agent anymore. I talk to a loop" a prompt is one instruction you babysit. a loop is a goal the AI works toward on its own: > it plans > does the work > checks itself > fixes what's weak > and repeats until it's done you step out, the work keeps going that's the shift the best engineers quietly moved to. most people hear a line like that and have no idea what it means in practice this breaks it down without the hype: what a loop actually is, when it's worth building, when it's a money trap, and how to run one yourself today watch his clip, then read the article below

Dep

20,995 views • 3 months ago