Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Claude Code team: "we oversimplify agentic engineering - like it's just prompts, just loops No. We need to know what we're doing " "I think Fable smarter than we think and we're hobbling Claude" what he means: step 1 → stop rewriting the prompt, give it a tool, the...

0xCodila's profile picture

codila

29,323 subscribers

11,759 Aufrufe • vor 3 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

12 Kommentare

Profilbild von 安叫兽|Bird🕊️ 🔶 BNB
安叫兽|Bird🕊️ 🔶 BNBvor 3 Monaten

别老搓 prompt，先把手脚接上

Profilbild von ALEXYZ
ALEXYZvor 3 Monaten

Tools beat prompts every time. Stop hobbling the model.

Profilbild von codila
codilavor 3 Monaten

exactly, that’s what this video explains

Profilbild von Shoopy
Shoopyvor 3 Monaten

"we're hobbling Claude" is the right frame bro – the model has it, the harness just won't let it out

Profilbild von Shubh Thorat
Shubh Thoratvor 3 Monaten

the loop framing is what's holding back most agent products honestly. it's not a loop, it's a state machine with really bad error handling

Profilbild von Fiction
Fictionvor 3 Monaten

underrated interview honestly, alpha info as always codila

Profilbild von Maxim Titarenko
Maxim Titarenkovor 3 Monaten

True, oversimplification can hinder progress. In my fleet, leveraging tools strategically allows agents to handle complex tasks without constant prompt rewrites. How do you integrate tool-use with models effectively?

Profilbild von Maximiliano Rodríguez
Maximiliano Rodríguezvor 3 Monaten

El "dale una tool en vez de reescribir el prompt" es medio camino. La otra mitad es la capa de conocimiento: qué sabe el agente antes de arrancar. En un vertical B2B el 60-70% del laburo no fue el loop, fue codificar el dominio en algo que el modelo pueda usar.

Profilbild von Manish
Manishvor 3 Monaten

The skill is slowly moving from “writing the perfect prompt” to “designing the perfect environment for the model to work in.”

Profilbild von Addiction
Addictionvor 3 Monaten

building agent loops requires way more nuance than prompting

Profilbild von ContextFirstAI
ContextFirstAIvor 3 Monaten

In client deployments, the difference is almost never the model. It's the quality of the context, access to the right tools, and a well-defined workflow. What change has had the biggest impact for your team?

Profilbild von Granite
Granitevor 3 Monaten

honestly haven't seen this video before how could i have slept on it?...

Ähnliche Videos

Claude Code creator: "I don't prompt Claude anymore. I have loops that figure out what to do. My job is to create loops." in 30 minutes Boris breaks down his daily Claude Code setup, step by step the person who built the tool doesn't use it the way most people think no prompts, no chat box, just loops running on their own I broke down 17 Claude features most people have never found full guide in the post below
29:49

Claude Code creator: "I don't prompt Claude anymore. I have loops that figure out what to do. My job is to create loops." in 30 minutes Boris breaks down his daily Claude Code setup, step by step the person who built the tool doesn't use it the way most people think no prompts, no chat box, just loops running on their own I broke down 17 Claude features most people have never found full guide in the post below

Anatoli Kopadze

413,313 Aufrufe • vor 5 Monaten

i don't think people realize what one person can now build with Claude... a Google Cloud engineer just went on stage and built a full app from scratch in 26 minutes, live. he showed everything step by step, no team, no setup, just Claude and a goal. worth more than any $500 vibe-coding course, and most people will scroll right past it. watch it, then read the guide below on the Claude features 99% of users never find.
26:05

i don't think people realize what one person can now build with Claude... a Google Cloud engineer just went on stage and built a full app from scratch in 26 minutes, live. he showed everything step by step, no team, no setup, just Claude and a goal. worth more than any $500 vibe-coding course, and most people will scroll right past it. watch it, then read the guide below on the Claude features 99% of users never find.

Anatoli Kopadze

35,402 Aufrufe • vor 14 Tagen

Anthropic just released a 4-hour course to getting a $500k AI engineering job: 00:15 - The right way to prompt Claude 33:21 - What makes Claude act dumber on your code 01:33:39 - How Anthropic use Claude every day 02:50:56 - The fix that makes Claude way smarter This 4-hour Anthropic free course replaces about 10 paid engineering courses. Watch it today, then read the step-by-step guide on building loops below.
3:46:20

Anthropic just released a 4-hour course to getting a $500k AI engineering job: 00:15 - The right way to prompt Claude 33:21 - What makes Claude act dumber on your code 01:33:39 - How Anthropic use Claude every day 02:50:56 - The fix that makes Claude way smarter This 4-hour Anthropic free course replaces about 10 paid engineering courses. Watch it today, then read the step-by-step guide on building loops below.

Raytar

494,676 Aufrufe • vor 4 Monaten

A Google Cloud engineer just showed how to build a full app with Claude from scratch he spent 26 minutes live on stage doing what most teams take weeks to do worth more than any $500 vibe-coding course here's what he covers: > zero to deployed app in a single session > handling five engineering roles alone with Claude > the exact workflow Google uses internally > no team, no setup, just Claude and a goal the people who figure out what Claude can actually do are building things everyone else thinks requires a team that's exactly why I wrote a step by step guide on how to build your first AI agent the guide is in the article below
26:23

A Google Cloud engineer just showed how to build a full app with Claude from scratch he spent 26 minutes live on stage doing what most teams take weeks to do worth more than any $500 vibe-coding course here's what he covers: > zero to deployed app in a single session > handling five engineering roles alone with Claude > the exact workflow Google uses internally > no team, no setup, just Claude and a goal the people who figure out what Claude can actually do are building things everyone else thinks requires a team that's exactly why I wrote a step by step guide on how to build your first AI agent the guide is in the article below

Anatoli Kopadze

465,359 Aufrufe • vor 5 Monaten

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build loops" In just 42 minutes, she shows how the Claude team builds loops that can prompt themselves If this were a $400 course, people would probably call it one of the best agent courses of the year It's completely free Watch it, then use the step-by-step guide below to build your first loop
29:48

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build loops" In just 42 minutes, she shows how the Claude team builds loops that can prompt themselves If this were a $400 course, people would probably call it one of the best agent courses of the year It's completely free Watch it, then use the step-by-step guide below to build your first loop

Lunar

73,963 Aufrufe • vor 2 Monaten

Boris Cherny: "I don't write code anymore, I just prompt with Claude" he spent 57 minutes explaining exactly where this is all going here's what stood out: > Claude Code grew faster than anyone at Anthropic expected > AI agents are moving beyond coding into every industry > running 1,000 agents in parallel is already happening > SaaS may not survive the agent era if the Head of Claude Code prompts instead of codes, what does that tell you about the next 2 years? that's exactly why I put together an article on Claude features most people don't know exist it will change how you work with Claude completely you can find it below
51:00

Boris Cherny: "I don't write code anymore, I just prompt with Claude" he spent 57 minutes explaining exactly where this is all going here's what stood out: > Claude Code grew faster than anyone at Anthropic expected > AI agents are moving beyond coding into every industry > running 1,000 agents in parallel is already happening > SaaS may not survive the agent era if the Head of Claude Code prompts instead of codes, what does that tell you about the next 2 years? that's exactly why I put together an article on Claude features most people don't know exist it will change how you work with Claude completely you can find it below

Anatoli Kopadze

20,003 Aufrufe • vor 5 Monaten

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.
46:31

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.

Codez

44,590 Aufrufe • vor 3 Monaten

Anthropic just dropped a 100% free course on Loop Engineering with Fable 5. This is the clearest breakdown of Claude Code and agentic loops you'll find anywhere. People are paying for tutorials that teach less than this one hour does. Watch it today, then read the step by step guide on building loops below.
1:01:16

Anthropic just dropped a 100% free course on Loop Engineering with Fable 5. This is the clearest breakdown of Claude Code and agentic loops you'll find anywhere. People are paying for tutorials that teach less than this one hour does. Watch it today, then read the step by step guide on building loops below.

Anatoli Kopadze

1,111,304 Aufrufe • vor 3 Monaten

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.
0:37

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 Aufrufe • vor 4 Monaten

Claude finally killed the need for OpenClaw They launched "Claude Channels" which allows you to control Claude Code from your Telegram / Discord I show you how to set it up in ~6 minutes in mainly 3 steps Step 1: Create bot with BotFather Step 2: Install the Claude plugin Step 3: Pair with a code Now I can code, research, manage files from my phone using Claude Code If you don't watch this tutorial now I highly suggest you bookmark for later!
6:22

Claude finally killed the need for OpenClaw They launched "Claude Channels" which allows you to control Claude Code from your Telegram / Discord I show you how to set it up in ~6 minutes in mainly 3 steps Step 1: Create bot with BotFather Step 2: Install the Claude plugin Step 3: Pair with a code Now I can code, research, manage files from my phone using Claude Code If you don't watch this tutorial now I highly suggest you bookmark for later!

Chris ☕️

70,433 Aufrufe • vor 7 Monaten

You asked for it, and it's finally here! 🚀 I just dropped a step-by-step tutorial on how to edit your AI videos using the FREE version of Claude! And yes, you don't need a paid Claude subscription👀 I broke everything down so even a beginner can follow along. Go watch, try it out, and let me know what you think! Don't forget to subscribe to my Youtube channel here:
19:43

You asked for it, and it's finally here! 🚀 I just dropped a step-by-step tutorial on how to edit your AI videos using the FREE version of Claude! And yes, you don't need a paid Claude subscription👀 I broke everything down so even a beginner can follow along. Go watch, try it out, and let me know what you think! Don't forget to subscribe to my Youtube channel here:

Digital Dame

24,240 Aufrufe • vor 12 Tagen

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.
55:30

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.

MIKE

32,313 Aufrufe • vor 3 Monaten

Сreator of Claude Code: BORIS CHERNY, WHO BUILT CLAUDE CODE, SAID IT PLAINLY." I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops. "He is not typing anymore. He runs loops that write the code for him. That is the shift most people miss. Not a better prompt. A loop that keeps running while you are gone.People sell $500 courses on this. The person who built the tool said it for free. The exact setup is in the article below.Bookmark this. Follow CyrilXBT
18:08

Сreator of Claude Code: BORIS CHERNY, WHO BUILT CLAUDE CODE, SAID IT PLAINLY." I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops. "He is not typing anymore. He runs loops that write the code for him. That is the shift most people miss. Not a better prompt. A loop that keeps running while you are gone.People sell $500 courses on this. The person who built the tool said it for free. The exact setup is in the article below.Bookmark this. Follow CyrilXBT

CyrilXBT

38,827 Aufrufe • vor 4 Monaten

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.
0:22

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,445 Aufrufe • vor 8 Monaten

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓
26:23

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓

codila

294,001 Aufrufe • vor 3 Monaten

I genuinely don't understand why everyone isn't using this yet. Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral: Stop using AI to write code. Use it to build a second brain. You point Claude Code at a folder. Drop in any source: an article, a transcript, a PDF. Claude reads it, links it, files it into a living wiki of everything you know. It compounds like interest. The more you feed it, the smarter it gets. Here's the whole thing: 1) Install Obsidian 2) Create a vault 3) Open it in Claude Code 4) Paste Karpathy's wiki idea and tell Claude to build it 5) Claude makes three folders: - raw (for sources) - wiki (for its pages) - CLAUDE. md (that runs it) 6) Drop any source into raw and say: "ingest this" 7) Ask questions across everything, forever Five minutes to set up and you never start from a blank chat again. Full step by step guide below.
1:48

I genuinely don't understand why everyone isn't using this yet. Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral: Stop using AI to write code. Use it to build a second brain. You point Claude Code at a folder. Drop in any source: an article, a transcript, a PDF. Claude reads it, links it, files it into a living wiki of everything you know. It compounds like interest. The more you feed it, the smarter it gets. Here's the whole thing: 1) Install Obsidian 2) Create a vault 3) Open it in Claude Code 4) Paste Karpathy's wiki idea and tell Claude to build it 5) Claude makes three folders: - raw (for sources) - wiki (for its pages) - CLAUDE. md (that runs it) 6) Drop any source into raw and say: "ingest this" 7) Ask questions across everything, forever Five minutes to set up and you never start from a blank chat again. Full step by step guide below.

CyrilXBT

332,891 Aufrufe • vor 4 Monaten

i built a small playable game in Unreal Engine with Claude Opus 5.5... no blueprints by hand, Claude worked inside the running editor the trick is the live connection, but there's a smart way to set it up: - step 1: Unreal Engine 5.8 + a Third Person project, under source control - step 2: enable Unreal MCP and AllToolsets, start the server - step 3: install Epic's free plugin for Claude Code and start Claude in the project folder - step 4: build a greybox level first: a path, a walled village, a tower you can see from the start - step 5: add the rules: 3 orbs, a locked gate, "You made it", R to restart - step 6: add one enemy, then health, then your attack, one feature per prompt - step 7: only then make it look good: your character, real assets, lighting and every prompt follows the same 4 rules... - say what "done" means - say what must not change - ask for a list of everything it touched - no silent workarounds: if it can't do it, it stops and says so the full course is in the article 👇🏻
0:27

i built a small playable game in Unreal Engine with Claude Opus 5.5... no blueprints by hand, Claude worked inside the running editor the trick is the live connection, but there's a smart way to set it up: - step 1: Unreal Engine 5.8 + a Third Person project, under source control - step 2: enable Unreal MCP and AllToolsets, start the server - step 3: install Epic's free plugin for Claude Code and start Claude in the project folder - step 4: build a greybox level first: a path, a walled village, a tower you can see from the start - step 5: add the rules: 3 orbs, a locked gate, "You made it", R to restart - step 6: add one enemy, then health, then your attack, one feature per prompt - step 7: only then make it look good: your character, real assets, lighting and every prompt follows the same 4 rules... - say what "done" means - say what must not change - ask for a list of everything it touched - no silent workarounds: if it can't do it, it stops and says so the full course is in the article 👇🏻

rewind

63,067 Aufrufe • vor 1 Monat

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build harnesses" In just 42 minutes, she shows how the Claude team builds harnesses that prompt themselves Agents → Harness → Loops → Graphs → Self-Improving Systems If this were a $500 course, people would call it one of the best agent courses of the year But it's completely free And it's better than most paid agent engineering courses Watch it today Then use the step-by-step harness engineering guide below
30:04

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build harnesses" In just 42 minutes, she shows how the Claude team builds harnesses that prompt themselves Agents → Harness → Loops → Graphs → Self-Improving Systems If this were a $500 course, people would call it one of the best agent courses of the year But it's completely free And it's better than most paid agent engineering courses Watch it today Then use the step-by-step harness engineering guide below

rari

33,537 Aufrufe • vor 2 Monaten

I think this is the future of prompting. Instead of figuring out the perfect instruction and hoping you didn't miss anything - just let the AI interview you. It asks what it needs to know, you brain dump, done. Built a /interview-me command for Claude Code to do exactly this. Here's me using it to write this post. The idea came from Claude Code's plan mode - it uses a tool called AskUserQuestion to clarify things before it starts working. That's when it clicked: Claude isn't just the best at answering questions, it's also the best at asking them. This command takes that idea further.
5:33

I think this is the future of prompting. Instead of figuring out the perfect instruction and hoping you didn't miss anything - just let the AI interview you. It asks what it needs to know, you brain dump, done. Built a /interview-me command for Claude Code to do exactly this. Here's me using it to write this post. The idea came from Claude Code's plan mode - it uses a tool called AskUserQuestion to clarify things before it starts working. That's when it clicked: Claude isn't just the best at answering questions, it's also the best at asking them. This command takes that idea further.

Nityesh

18,605 Aufrufe • vor 9 Monaten

Stop what you're doing. Claude Opus 4.6 just released and it's incredible Both OpenClaw and Claude Code are 10x better with it It's now my daily driver for both In this video I cover EVERYTHING you need to know about Opus, and how to get the most out of it:
17:28

Stop what you're doing. Claude Opus 4.6 just released and it's incredible Both OpenClaw and Claude Code are 10x better with it It's now my daily driver for both In this video I cover EVERYTHING you need to know about Opus, and how to get the most out of it:

Alex Finn

72,614 Aufrufe • vor 9 Monaten