正在加载视频...

视频加载失败

返回首页

FOUR TYPES OF AGENT LOOPS. LOOP ENGINEERING IS PICKING THE RIGHT ONE, NOT THE FANCIEST ONE every loop answers two questions: what starts a run, what ends it hand-run, you answer both yourself, every time 1) turn-based > you prompt, it acts, you review, you prompt again > use...

0x_fokki's profile picture

Fokki

14,550 subscribers

10,312 次观看 • 28 天前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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
0:40

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

20,917 次观看 • 2 个月前

There are two types of engineers in 2026 The first opens his laptop in the morning, writes a prompt, waits, reads the diff, fixes it, repeats The second opens his phone, checks what shipped while he was asleep Different answer to one question: who is the loop? The first engineer is the loop, he starts the agent, reviews the output, decides what's next, the moment he steps away it stops The second engineer built the system that is the loop instead of him, PR review, flaky tests, CI triage, all running without him, he just reads the report What stops most people isn't complexity It's that they never noticed they are the bottleneck Full guide to building the system that runs without you below
1:04

There are two types of engineers in 2026 The first opens his laptop in the morning, writes a prompt, waits, reads the diff, fixes it, repeats The second opens his phone, checks what shipped while he was asleep Different answer to one question: who is the loop? The first engineer is the loop, he starts the agent, reviews the output, decides what's next, the moment he steps away it stops The second engineer built the system that is the loop instead of him, PR review, flaky tests, CI triage, all running without him, he just reads the report What stops most people isn't complexity It's that they never noticed they are the bottleneck Full guide to building the system that runs without you below

plutos

14,653 次观看 • 2 个月前

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch
39:43

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

GREG ISENBERG

82,960 次观看 • 1 个月前

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves it - which checks run every pass - which artifact gets saved - which failure sends it back into the loop Then let the agent run The loop can keep going because proof sits outside the agent's own explanation Tests, screenshots, benchmark curves, browser runs, changed files That's how you get autonomy without babysitting a transcript for 6 hours Read the full breakdown on goals, verifiers, loops, artifacts, and session memory in the article below
1:06:31

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves it - which checks run every pass - which artifact gets saved - which failure sends it back into the loop Then let the agent run The loop can keep going because proof sits outside the agent's own explanation Tests, screenshots, benchmark curves, browser runs, changed files That's how you get autonomy without babysitting a transcript for 6 hours Read the full breakdown on goals, verifiers, loops, artifacts, and session memory in the article below

Alpha Batcher

43,806 次观看 • 2 个月前

your agent loop needs 8 exits. most people ship only one. (explained with triggers) 1) goal met → an evaluator scores the output against a rubric, and the run stops on a pass. → fires when the work is measurably done, not when the model says it is done. 2) turn cap → a hard ceiling on iterations, counted and enforced by the harness, not the prompt. → fires on the task it was never going to finish, before you pay to find that out. 3) budget cap → a limit on tokens or dollars, whichever one runs out first. → fires mid-run, which is exactly why it is the exit that saves you the 3am bill. 4) wall clock → a deadline on elapsed time, independent of how much progress was made. → fires when the run collides with a deploy window or the start of business hours. 5) no progress → hash the state every turn and compare it against the last few. → fires when three turns in a row change nothing. busy is not the same as moving. 6) human interrupt → an approval gate before risky steps, plus a kill switch that lives outside the loop. → fires whenever you decide, and it is the one exit the model cannot argue with. 7) error threshold → a counter of consecutive failures that resets on any success. → fires at n in a row, so it halts instead of retrying into the same wall all night. 8) external event → a webhook or a poll on whatever the task was actually about. → fires when the PR merged or the ticket closed and the work stopped mattering. a loop with one exit hangs. a loop with eight is a system. write the exits before you write the prompt.
0:40

your agent loop needs 8 exits. most people ship only one. (explained with triggers) 1) goal met → an evaluator scores the output against a rubric, and the run stops on a pass. → fires when the work is measurably done, not when the model says it is done. 2) turn cap → a hard ceiling on iterations, counted and enforced by the harness, not the prompt. → fires on the task it was never going to finish, before you pay to find that out. 3) budget cap → a limit on tokens or dollars, whichever one runs out first. → fires mid-run, which is exactly why it is the exit that saves you the 3am bill. 4) wall clock → a deadline on elapsed time, independent of how much progress was made. → fires when the run collides with a deploy window or the start of business hours. 5) no progress → hash the state every turn and compare it against the last few. → fires when three turns in a row change nothing. busy is not the same as moving. 6) human interrupt → an approval gate before risky steps, plus a kill switch that lives outside the loop. → fires whenever you decide, and it is the one exit the model cannot argue with. 7) error threshold → a counter of consecutive failures that resets on any success. → fires at n in a row, so it halts instead of retrying into the same wall all night. 8) external event → a webhook or a poll on whatever the task was actually about. → fires when the PR merged or the ticket closed and the work stopped mattering. a loop with one exit hangs. a loop with eight is a system. write the exits before you write the prompt.

Hanako

181,823 次观看 • 1 个月前

Right now, most developers are still doing the job AI should be doing. Assign a task. Wait. Review the result. Fix it. Repeat. You're not building with AI. You're babysitting it. The shift happening now is much bigger than better coding agents. It's loop engineering. Instead of managing every AI agent yourself, you build a system that manages them for you. One loop assigns the work. Another checks the output. A third retries failures. Everything keeps moving without waiting for your next prompt. Your job doesn't disappear. It changes. You stop acting like a project manager... ...and start designing the system that manages the entire team. That's exactly the transition I break down in the article below.
1:41

Right now, most developers are still doing the job AI should be doing. Assign a task. Wait. Review the result. Fix it. Repeat. You're not building with AI. You're babysitting it. The shift happening now is much bigger than better coding agents. It's loop engineering. Instead of managing every AI agent yourself, you build a system that manages them for you. One loop assigns the work. Another checks the output. A third retries failures. Everything keeps moving without waiting for your next prompt. Your job doesn't disappear. It changes. You stop acting like a project manager... ...and start designing the system that manages the entire team. That's exactly the transition I break down in the article below.

Pure

11,257 次观看 • 1 个月前

10 agent evals for AI engineers: (explained with usage) 1) golden set → a fixed set of cases you never edit, run on every single change. → use as the baseline that tells you whether anything moved at all. 2) llm as judge → a second model scores the output against a written rubric. → use when the answer is open-ended and there is no string to match against. 3) rubric scoring → one number per dimension: correctness, tone, safety, cost. → use when a single score hides which part actually got worse. 4) trajectory eval → grade the path the agent took, not only the answer it landed on. → use when the right answer for the wrong reason is going to bite you later. 5) tool unit tests → test each tool on its own, with fixtures, no model in the loop. → use always. most agent bugs are tool bugs wearing a costume. 6) regression suite → replay past runs against the new prompt or model and diff the results. → use before every prompt change, because prompts have no type system. 7) a/b in prod → split live traffic between two versions and compare outcomes, not vibes. → use when offline scores stopped predicting what users actually do. 8) human review → sample a slice of runs and have a person grade them honestly. → use to calibrate your judge, because a judge nobody checks quietly drifts. 9) shadow run → the candidate runs on real traffic in parallel and its output is shown to nobody. → use before a risky rollout, when one bad answer would be expensive. 10) red team → deliberately attack it: jailbreaks, injection, exfil, tool abuse. → use before anyone external can reach it, not after. offline evals tell you it works. online evals tell you it still works. both sides matter, but not all ten do. run the two that would have caught your last outage. save this. then read the full breakdown on loop engineering below.
0:40

10 agent evals for AI engineers: (explained with usage) 1) golden set → a fixed set of cases you never edit, run on every single change. → use as the baseline that tells you whether anything moved at all. 2) llm as judge → a second model scores the output against a written rubric. → use when the answer is open-ended and there is no string to match against. 3) rubric scoring → one number per dimension: correctness, tone, safety, cost. → use when a single score hides which part actually got worse. 4) trajectory eval → grade the path the agent took, not only the answer it landed on. → use when the right answer for the wrong reason is going to bite you later. 5) tool unit tests → test each tool on its own, with fixtures, no model in the loop. → use always. most agent bugs are tool bugs wearing a costume. 6) regression suite → replay past runs against the new prompt or model and diff the results. → use before every prompt change, because prompts have no type system. 7) a/b in prod → split live traffic between two versions and compare outcomes, not vibes. → use when offline scores stopped predicting what users actually do. 8) human review → sample a slice of runs and have a person grade them honestly. → use to calibrate your judge, because a judge nobody checks quietly drifts. 9) shadow run → the candidate runs on real traffic in parallel and its output is shown to nobody. → use before a risky rollout, when one bad answer would be expensive. 10) red team → deliberately attack it: jailbreaks, injection, exfil, tool abuse. → use before anyone external can reach it, not after. offline evals tell you it works. online evals tell you it still works. both sides matter, but not all ten do. run the two that would have caught your last outage. save this. then read the full breakdown on loop engineering below.

Hanako

150,676 次观看 • 1 个月前

6 agent patterns for AI engineers: (explained with usage) 1) prompt chaining → split the task into fixed steps, each one checking the last. → use when the task decomposes cleanly and accuracy matters more than latency. 2) routing → classify the input first, then send it to the model or tool built for it. → use when inputs fall into distinct classes that need different handling. 3) parallelization → run several calls at once and merge them, either by splitting the work or voting on the same question. → use when subtasks are independent, or when one answer deserves several opinions. 4) orchestrator-workers → a lead model decides what the subtasks are at runtime, then delegates them. → use when you cannot list the steps in advance. 5) evaluator-optimizer → one model writes, another grades, the loop repeats until it passes. → use when you have clear criteria and iteration measurably helps. 6) autonomous agent → no fixed path. it plans, acts, reads feedback from the environment, and decides when it is done. → use when the steps are unknowable and you can afford the cost and the blast radius. the first five are workflows: you wrote the path. only the last one writes its own. most production systems people call agents are pattern 1, 2, or 5 with good error handling. this taxonomy is from Anthropic's own writeup on building effective agents. full breakdown in the article below.
0:37

6 agent patterns for AI engineers: (explained with usage) 1) prompt chaining → split the task into fixed steps, each one checking the last. → use when the task decomposes cleanly and accuracy matters more than latency. 2) routing → classify the input first, then send it to the model or tool built for it. → use when inputs fall into distinct classes that need different handling. 3) parallelization → run several calls at once and merge them, either by splitting the work or voting on the same question. → use when subtasks are independent, or when one answer deserves several opinions. 4) orchestrator-workers → a lead model decides what the subtasks are at runtime, then delegates them. → use when you cannot list the steps in advance. 5) evaluator-optimizer → one model writes, another grades, the loop repeats until it passes. → use when you have clear criteria and iteration measurably helps. 6) autonomous agent → no fixed path. it plans, acts, reads feedback from the environment, and decides when it is done. → use when the steps are unknowable and you can afford the cost and the blast radius. the first five are workflows: you wrote the path. only the last one writes its own. most production systems people call agents are pattern 1, 2, or 5 with good error handling. this taxonomy is from Anthropic's own writeup on building effective agents. full breakdown in the article below.

Hanako

144,618 次观看 • 1 个月前

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today
0:50

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

Sprytix

153,690 次观看 • 1 个月前

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:
0:53

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:

cvxv666

53,163 次观看 • 2 个月前

The guy who kicked off the entire "loop engineering" wave Peter Steinberger: "You shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agents." One post. 6.5M views in a week. In this talk he walks the real stack: the agent loop, a verifier that fails its own work and retries, and a loop that rewrites the agent while he sleeps. Worth more than any $500 vibe-coding course. Watch it, then read the full breakdown of the 4 loops below.
17:30

The guy who kicked off the entire "loop engineering" wave Peter Steinberger: "You shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agents." One post. 6.5M views in a week. In this talk he walks the real stack: the agent loop, a verifier that fails its own work and retries, and a loop that rewrites the agent while he sleeps. Worth more than any $500 vibe-coding course. Watch it, then read the full breakdown of the 4 loops below.

dunik

219,932 次观看 • 2 个月前

EVERYONE HAS BEEN TALKING ABOUT AI AGENTS. BUT THE REAL UNLOCK ISN'T BETTER PROMPTS: IT'S BETTER LOOPS. Everyone is chasing the perfect prompt. The top AI engineers are chasing something else: loops. Instead of chatting back and forth with AI, they give it one goal and let it continuously improve its own work until the objective is met. Here's the framework: • Define the goal once • AI discovers the work required • Specialized agents tackle tasks in parallel • A verification agent checks the results • If the goal isn't met: loop again. If it is: deliver. The key ingredient is memory. Each cycle remembers what was completed, what failed, and what still needs work, so every iteration gets smarter instead of starting from scratch. There are two approaches: • Open loops: Maximum autonomy, but higher token costs as AI explores freely. • Closed loops: Clear boundaries, defined success metrics, lower costs, and far more practical for everyday workflows. Don't ask AI to complete a task. Build a system where AI can plan, execute, verify, remember, and repeat until the task is actually finished. Prompt engineering got us here. Loop engineering is what takes AI from assistant to autonomous teammate.
19:17

EVERYONE HAS BEEN TALKING ABOUT AI AGENTS. BUT THE REAL UNLOCK ISN'T BETTER PROMPTS: IT'S BETTER LOOPS. Everyone is chasing the perfect prompt. The top AI engineers are chasing something else: loops. Instead of chatting back and forth with AI, they give it one goal and let it continuously improve its own work until the objective is met. Here's the framework: • Define the goal once • AI discovers the work required • Specialized agents tackle tasks in parallel • A verification agent checks the results • If the goal isn't met: loop again. If it is: deliver. The key ingredient is memory. Each cycle remembers what was completed, what failed, and what still needs work, so every iteration gets smarter instead of starting from scratch. There are two approaches: • Open loops: Maximum autonomy, but higher token costs as AI explores freely. • Closed loops: Clear boundaries, defined success metrics, lower costs, and far more practical for everyday workflows. Don't ask AI to complete a task. Build a system where AI can plan, execute, verify, remember, and repeat until the task is actually finished. Prompt engineering got us here. Loop engineering is what takes AI from assistant to autonomous teammate.

Dami-Defi

13,354 次观看 • 1 个月前

Every skill file I write ends with a self-improvement loop. It sits at the bottom of the skill.md and runs before the skill finishes: - Did any step fail or need a workaround? - Did I correct or reject anything meaningful? - Did you discover something a future run might need? Most runs it comes back with one or two suggested edits. I say not needed, or I say run it, and it rewrites its own file. It never edits without asking first, so every change still goes through you. Put the loop at the bottom of the skills you already have and let them self-improve while you use them.
3:28

Every skill file I write ends with a self-improvement loop. It sits at the bottom of the skill.md and runs before the skill finishes: - Did any step fail or need a workaround? - Did I correct or reject anything meaningful? - Did you discover something a future run might need? Most runs it comes back with one or two suggested edits. I say not needed, or I say run it, and it rewrites its own file. It never edits without asking first, so every change still goes through you. Put the loop at the bottom of the skills you already have and let them self-improve while you use them.

The Startup Ideas Podcast (SIP) 🧃

11,799 次观看 • 8 天前

ANTHROPIC LEAKED 6 RULES THAT RUN 8 LOOPS AT ONCE - AND ONE ENGINEER DOES THE WORK OF A TEAM one engineer with this system replaces an entire team - and costs the company 8 times less You → Opus 5 plan → Fable 5 ×8 execute → Fable 5 review → you: 5 min Opus 5 takes your intent and breaks it into subtasks - a bad plan multiplied across every loop gives the same number of disasters - the plan is the only thing you read carefully one repo - isolated worktrees for each loop - nobody stands on anyone's file - parallel PRs ship while you do nothing the agent runs the tests and fixes until green PR - a red build never reaches your eyes one CLAUDE.md for the whole fleet - without it you get different opinions from every loop and one merge hell the average engineer closes 3-4 tasks a day - this system closes a full sprint overnight with zero working hours Fable 5 pre-reviews every PR before it reaches you - you spend 5 minutes - your throughput is now measured in diffs read per hour bookmark and paste into Claude Code - your first fleet can start tonight
1:15

ANTHROPIC LEAKED 6 RULES THAT RUN 8 LOOPS AT ONCE - AND ONE ENGINEER DOES THE WORK OF A TEAM one engineer with this system replaces an entire team - and costs the company 8 times less You → Opus 5 plan → Fable 5 ×8 execute → Fable 5 review → you: 5 min Opus 5 takes your intent and breaks it into subtasks - a bad plan multiplied across every loop gives the same number of disasters - the plan is the only thing you read carefully one repo - isolated worktrees for each loop - nobody stands on anyone's file - parallel PRs ship while you do nothing the agent runs the tests and fixes until green PR - a red build never reaches your eyes one CLAUDE.md for the whole fleet - without it you get different opinions from every loop and one merge hell the average engineer closes 3-4 tasks a day - this system closes a full sprint overnight with zero working hours Fable 5 pre-reviews every PR before it reaches you - you spend 5 minutes - your throughput is now measured in diffs read per hour bookmark and paste into Claude Code - your first fleet can start tonight

Sprytix

37,904 次观看 • 1 个月前

You Can Learn AI Agent Harness & Loop Engineering In 19 Min, with LLM Ops, Eval, Tracing and RAG. They went viral not because they're complicated but because they're simple building blocks, and once you see them you can prompt your way to building real systems. 🎬YouTube: Here's the whole thing in one picture. An LLM is a powerful brain that knows everything about humanity and nothing about you or the software you're running. The harness is the set of tools you put on that horse so it runs where you want. Memory gives it context: who you are, what happened before, how to act. The loop lets it call tools again and again, with guardrails so it knows when to stop. Eval and LLM Ops trace every run, score it, and feed the fixes back in so the system keeps improving itself. Master these four and you can read almost any AI agent repo or paper and actually know what's going on. You Can Build Anything. You Can Learn Anything. 💪 Chapters: Intro: the 4 AI agent buzzwords What an AI agent run actually is The memory system: procedural, semantic, episodic What "harness" really means (the horse) Storing and updating memory (databases, skills, summarizer agent) Retrieval: RAG, SQL vs semantic search Tool calling and why agents loop Loop engineering and end-loop guardrails A Claude Code hooks example Eval and LLM Ops: why you need them Tracing every run (Langfuse, LangSmith) Evaluation: LLM as a judge Diagnosing what broke The gate: ship the fix or fix the bug Zoom out: the full system
19:59

You Can Learn AI Agent Harness & Loop Engineering In 19 Min, with LLM Ops, Eval, Tracing and RAG. They went viral not because they're complicated but because they're simple building blocks, and once you see them you can prompt your way to building real systems. 🎬YouTube: Here's the whole thing in one picture. An LLM is a powerful brain that knows everything about humanity and nothing about you or the software you're running. The harness is the set of tools you put on that horse so it runs where you want. Memory gives it context: who you are, what happened before, how to act. The loop lets it call tools again and again, with guardrails so it knows when to stop. Eval and LLM Ops trace every run, score it, and feed the fixes back in so the system keeps improving itself. Master these four and you can read almost any AI agent repo or paper and actually know what's going on. You Can Build Anything. You Can Learn Anything. 💪 Chapters: Intro: the 4 AI agent buzzwords What an AI agent run actually is The memory system: procedural, semantic, episodic What "harness" really means (the horse) Storing and updating memory (databases, skills, summarizer agent) Retrieval: RAG, SQL vs semantic search Tool calling and why agents loop Loop engineering and end-loop guardrails A Claude Code hooks example Eval and LLM Ops: why you need them Tracing every run (Langfuse, LangSmith) Evaluation: LLM as a judge Diagnosing what broke The gate: ship the fix or fix the bug Zoom out: the full system

Shen Sean Chen

15,952 次观看 • 2 个月前

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓
0:41

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

72,028 次观看 • 8 天前

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.
31:18

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 次观看 • 1 个月前

ChatGPT can write you a thousand trading strategies from one sentence. 999 will quietly bleed your account dry. Every single one of them looks like a winner. One method pulls the real one out. Quant desks have run it for years. It's called loop engineering. It's not a smarter prompt. It's a loop: generate a strategy, test it, score why it failed, feed that back, and run it again until one survives data it has never seen. Man Group runs $150 billion. They built an AI that writes and tests hundreds of strategies a week. And second agent whose only job is to hunt the ones that secretly overfit and kill them before a cent goes live. > describe an idea -> backtest 5 years in 12 seconds > read why it died -> feed that back in > run it again until one survives data it never saw AI can write a thousand strategies. Loop engineering is the only thing that tells you which one was ever real. 89% of retail lost money in 2025. Almost none of it from bad ideas. All of it from trading the first guess and never running it through backtest loop. Horizon just put the whole thing in a chat box, free while the beta's open: You're not losing to smarter traders. You're losing to the ones who opened the tab. Anyone can generate a strategy now. Almost no one runs the loop that proves it. That gap is the whole edge. You'll mean to check it later. Later is a "waitlist closed" page.
0:43

ChatGPT can write you a thousand trading strategies from one sentence. 999 will quietly bleed your account dry. Every single one of them looks like a winner. One method pulls the real one out. Quant desks have run it for years. It's called loop engineering. It's not a smarter prompt. It's a loop: generate a strategy, test it, score why it failed, feed that back, and run it again until one survives data it has never seen. Man Group runs $150 billion. They built an AI that writes and tests hundreds of strategies a week. And second agent whose only job is to hunt the ones that secretly overfit and kill them before a cent goes live. > describe an idea -> backtest 5 years in 12 seconds > read why it died -> feed that back in > run it again until one survives data it never saw AI can write a thousand strategies. Loop engineering is the only thing that tells you which one was ever real. 89% of retail lost money in 2025. Almost none of it from bad ideas. All of it from trading the first guess and never running it through backtest loop. Horizon just put the whole thing in a chat box, free while the beta's open: You're not losing to smarter traders. You're losing to the ones who opened the tab. Anyone can generate a strategy now. Almost no one runs the loop that proves it. That gap is the whole edge. You'll mean to check it later. Later is a "waitlist closed" page.

cvxv666

174,699 次观看 • 2 个月前

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 次观看 • 2 个月前

Introducing the Legora Agent: the execution engine at the core of the Legora aOS™. Most legal AI responds to prompts. The Agent executes objectives. You give it a goal and it builds a plan, presents it for approval, then carries the work out end-to-end — selecting the right tools as it goes, whether that's research, drafting, or review. It keeps working while you review, instead of waiting for the next prompt — while you're with clients, with family, or even while you sleep. It isn’t a tool you use. It's a super-associate you supervise. The Legora Agent is live today. Read the announcement here:
1:27

Introducing the Legora Agent: the execution engine at the core of the Legora aOS™. Most legal AI responds to prompts. The Agent executes objectives. You give it a goal and it builds a plan, presents it for approval, then carries the work out end-to-end — selecting the right tools as it goes, whether that's research, drafting, or review. It keeps working while you review, instead of waiting for the next prompt — while you're with clients, with family, or even while you sleep. It isn’t a tool you use. It's a super-associate you supervise. The Legora Agent is live today. Read the announcement here:

Legora

39,514 次观看 • 2 个月前