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.

this is worth more than most five figure courses 16 claude agents audit an entire repo at once, a second fleet re-checks every finding on fresh context, and the whole thing runs off one diagram instead of a prompt i ran it against my own code and got back... 11 endpoints where i never checked who was logged in, 3 of which the verifier threw out before they ever reached me this is Graph Engineering, the layer above prompting, and it runs on the agent you already pay for: - write your plan out, then ask one question at every "and then": does the next step actually read what the previous one produced - the seams that fail that question were never dependencies, so those jobs run at the same time - the arrows that survive are your real edges, and the longest chain of them is your floor that no number of agents shortens - want it faster, cut a false edge instead of adding a worker - fan the independent work out, one agent per item, no shared state between them - send every finding to a separate agent on fresh context, because a model recognises its own writing 73.5% of the time and grades it kinder once it does - make that verifier check a real signal like a passing test, never the worker's own word that it finished - shard the fleet across worktrees so parallel workers stop overwriting each other, one rule frozen into every worker: never git stash, never git reset - merge only what came back verified, into one report instead of twenty open chats the catch is the ceiling. at 95% independent work 16 agents return 9.14x rather than the 16 you would guess, and even 256 only reach 18.6x, because the merge and the verify stay serial however wide you fan coordination itself is free plain code and every agent underneath it is billed, so start at twenty files and widen once it works bookmark this, the whole method with all six ready-to-run graphs is written out in the article ↓show more

Argona

30,323 subscribers

157,312 views • 1 month ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

this is f*cking gold engineers at Meta just deleted the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.

this is f*cking gold engineers at Meta just deleted the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.

NO1ennn

26,237 views • 8 days ago

I STOPPED REVIEWING MY OWN AGENT, SOMETHING ELSE DOES IT NOW I used to read every diff it produced and approve most of them, because an agent grading itself always says the work is good. -> Now a second model with different instructions tries to break the work first, and I only read what survived. Here is what is actually in the folder that took over the night shift: • the brief > CONTRACT.md -- what it may touch, and what it may never touch. > VISION.md -- the destination, so turn 47 still knows why it started. • the gate > judge/ -- a different model, never the one that wrote the code. > break-it.md -- it opens the page, clicks, screenshots, reports back. > -- no opinion, just zero or non-zero. > shift.yml -- 03:30 every night, laptop closed. • the memory > receipts/ -- one folder per night, dated and graded. > STATE.md -- where it stopped and what it escalated. > lessons.log -- the flaky test, written down once instead of rediscovered weekly. • the brakes > caps.json -- turn limit, retry limit, spend limit. > -- written on day one, used never. The generator decides what your loop can produce -> The judge decides what it refuses to produce. One of those is the part everyone builds -> The other is why most loops quietly fail. Bookmark it & Read Full breakdown below ↓

I STOPPED REVIEWING MY OWN AGENT, SOMETHING ELSE DOES IT NOW I used to read every diff it produced and approve most of them, because an agent grading itself always says the work is good. -> Now a second model with different instructions tries to break the work first, and I only read what survived. Here is what is actually in the folder that took over the night shift: • the brief > CONTRACT.md -- what it may touch, and what it may never touch. > VISION.md -- the destination, so turn 47 still knows why it started. • the gate > judge/ -- a different model, never the one that wrote the code. > break-it.md -- it opens the page, clicks, screenshots, reports back. > -- no opinion, just zero or non-zero. > shift.yml -- 03:30 every night, laptop closed. • the memory > receipts/ -- one folder per night, dated and graded. > STATE.md -- where it stopped and what it escalated. > lessons.log -- the flaky test, written down once instead of rediscovered weekly. • the brakes > caps.json -- turn limit, retry limit, spend limit. > -- written on day one, used never. The generator decides what your loop can produce -> The judge decides what it refuses to produce. One of those is the part everyone builds -> The other is why most loops quietly fail. Bookmark it & Read Full breakdown below ↓

slash1s

37,556 views • 1 month ago

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

shmidt

19,505 views • 2 months ago

Running cold email campaigns just became a whole lot easier Smartlead now runs an MCP server, which in plain terms means Claude can read and act on your live campaign data directly instead of working off a spreadsheet that went stale the moment you exported it. The workflow is worth walking through properly, because it is shorter than people expect. You generate an API key inside your account, point Claude at the server once, and from then on you ask for what you want in a sentence. Here is a prompt worth stealing in full: "Fetch all Smartlead clients, then get today's performance for each: emails sent, replied, positive replies, unique lead count. Compute reply rate per client, run a top and bottom performer analysis, format it as a daily client performance report, and post it to Slack." One paste, and it pulls live figures for every account, does the arithmetic, ranks the strongest and the weakest, and delivers the finished thing into the channel your team already sits in, before anyone has logged on for the day. Be clear about the division of labour, because it is what makes this useful rather than a novelty. Smartlead is the engine holding the campaigns, the mailboxes, the warmup and the reply data, and Claude is simply the interface you operate all of it through, so nothing about your sending changes and everything about how you interrogate it does. The effect people underestimate is on the questions you start asking. Once a report costs you a sentence rather than an afternoon, you stop rationing the ones that used to feel like too much trouble, and problems that used to surface on a Friday start surfacing on a Tuesday. Connect it with Claude through MCP and run one prompt against your own account today.

Running cold email campaigns just became a whole lot easier Smartlead now runs an MCP server, which in plain terms means Claude can read and act on your live campaign data directly instead of working off a spreadsheet that went stale the moment you exported it. The workflow is worth walking through properly, because it is shorter than people expect. You generate an API key inside your account, point Claude at the server once, and from then on you ask for what you want in a sentence. Here is a prompt worth stealing in full: "Fetch all Smartlead clients, then get today's performance for each: emails sent, replied, positive replies, unique lead count. Compute reply rate per client, run a top and bottom performer analysis, format it as a daily client performance report, and post it to Slack." One paste, and it pulls live figures for every account, does the arithmetic, ranks the strongest and the weakest, and delivers the finished thing into the channel your team already sits in, before anyone has logged on for the day. Be clear about the division of labour, because it is what makes this useful rather than a novelty. Smartlead is the engine holding the campaigns, the mailboxes, the warmup and the reply data, and Claude is simply the interface you operate all of it through, so nothing about your sending changes and everything about how you interrogate it does. The effect people underestimate is on the questions you start asking. Once a report costs you a sentence rather than an afternoon, you stop rationing the ones that used to feel like too much trouble, and problems that used to surface on a Friday start surfacing on a Tuesday. Connect it with Claude through MCP and run one prompt against your own account today.

Tim

21,666 views • 2 days ago

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

12,861 views • 3 months ago

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do

leopardracer

53,328 views • 1 month ago

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

BuBBliK

200,456 views • 3 months ago

this is f*cking gold Google engineers built an agent that tests thousands of search strategies for the cost of running one, by letting it dream inside its own memory. it is called Dream-RSI. Google, Google DeepMind, Maryland, Virginia. 17 authors. the whole thing rests on one observation: a finished run is not a log. it is a map of a world that already exists. > every discovery run records a tree. each node is one attempt with its full result stored > that tree becomes a replay simulator. the paper calls them worlds > the agent dreams inside it: thousands of alternative strategies, testing different branches, different orders, different concurrency, different stopping rules > every one of those evaluations costs zero execution. nothing is ever run twice > the winner goes back online, produces a new tree, and the pool of worlds grows the coding agent underneath is never touched. this is an orchestration layer sitting on top of whatever you already run. what it bought them, against the same agent with a frozen strategy: > Lasso: 3587ms down to 2931ms, on 317 agent calls instead of 550 > on Flash: 2517ms to 2351ms, 1879 calls instead of 3200 > both solvers beat sklearn and glmnet on all six held-out datasets > GPU kernels: the same result on 2.43x and 1.79x fewer generations, then 2.09x and 1.44x better result on the same budget one expensive run. thousands of free ones. the model did not get smarter. it got a memory it could rehearse in.

this is f*cking gold Google engineers built an agent that tests thousands of search strategies for the cost of running one, by letting it dream inside its own memory. it is called Dream-RSI. Google, Google DeepMind, Maryland, Virginia. 17 authors. the whole thing rests on one observation: a finished run is not a log. it is a map of a world that already exists. > every discovery run records a tree. each node is one attempt with its full result stored > that tree becomes a replay simulator. the paper calls them worlds > the agent dreams inside it: thousands of alternative strategies, testing different branches, different orders, different concurrency, different stopping rules > every one of those evaluations costs zero execution. nothing is ever run twice > the winner goes back online, produces a new tree, and the pool of worlds grows the coding agent underneath is never touched. this is an orchestration layer sitting on top of whatever you already run. what it bought them, against the same agent with a frozen strategy: > Lasso: 3587ms down to 2931ms, on 317 agent calls instead of 550 > on Flash: 2517ms to 2351ms, 1879 calls instead of 3200 > both solvers beat sklearn and glmnet on all six held-out datasets > GPU kernels: the same result on 2.43x and 1.79x fewer generations, then 2.09x and 1.44x better result on the same budget one expensive run. thousands of free ones. the model did not get smarter. it got a memory it could rehearse in.

NO1ennn

30,312 views • 3 days ago

THIS 38,000-STAR GITHUB REPO TURNS ONE AI AGENT INTO A REAL TEAM THAT CAN BRANCH, VERIFY ITS WORK AND WAIT FOR YOUR APPROVAL most people still run agents as one long chain where every step waits, one failure kills the run and the full workflow starts again Task → Planner → 5 Researchers in Parallel → Skeptic → Writer → Human Gate LangGraph gives every node one job while a shared state carries the findings, decisions and context through the entire system the skeptic can reject an unsupported finding and route the work back before it contaminates the final report, while independent branches keep moving if the run crashes, durable execution resumes from the saved state instead of rebuilding everything, then human-in-the-loop pauses the graph before anything expensive gets sent or published bookmark this repo and watch one prompt turn into an actual org chart for AI agents

THIS 38,000-STAR GITHUB REPO TURNS ONE AI AGENT INTO A REAL TEAM THAT CAN BRANCH, VERIFY ITS WORK AND WAIT FOR YOUR APPROVAL most people still run agents as one long chain where every step waits, one failure kills the run and the full workflow starts again Task → Planner → 5 Researchers in Parallel → Skeptic → Writer → Human Gate LangGraph gives every node one job while a shared state carries the findings, decisions and context through the entire system the skeptic can reject an unsupported finding and route the work back before it contaminates the final report, while independent branches keep moving if the run crashes, durable execution resumes from the saved state instead of rebuilding everything, then human-in-the-loop pauses the graph before anything expensive gets sent or published bookmark this repo and watch one prompt turn into an actual org chart for AI agents

Gipp 🦅

11,524 views • 1 month ago

AGENT ARCHITECTURE ROUTES WORK. IT DOES NOT REMEMBER WORK. THAT GAP IS WHY YOUR LOOP KEEPS FIXING THE SAME BUG TWICE. these are two different engineering problems. every agent that silently drifts is missing one of them. architecture answers what runs. harness → loop → graph. it defines the tools, the retries, the branching routes, the approval gates. context ops answer what the run knows. write → read → compress → isolate. it defines what gets saved between attempts, pulled in on read, summarized on overflow, and split across sub-agents. for two months i believed a solid harness plus a verifier loop was enough. my coding agent kept re-discovering the same test failure across retries. the loop was working. it just had nowhere to write what it had already learned. here is the decision rule: if your agent forgets across restarts, add write and read. if it stalls on long tasks, add compress. if two sub-agents step on each other, add isolate. architecture without context ops is a well-routed system with amnesia.

AGENT ARCHITECTURE ROUTES WORK. IT DOES NOT REMEMBER WORK. THAT GAP IS WHY YOUR LOOP KEEPS FIXING THE SAME BUG TWICE. these are two different engineering problems. every agent that silently drifts is missing one of them. architecture answers what runs. harness → loop → graph. it defines the tools, the retries, the branching routes, the approval gates. context ops answer what the run knows. write → read → compress → isolate. it defines what gets saved between attempts, pulled in on read, summarized on overflow, and split across sub-agents. for two months i believed a solid harness plus a verifier loop was enough. my coding agent kept re-discovering the same test failure across retries. the loop was working. it just had nowhere to write what it had already learned. here is the decision rule: if your agent forgets across restarts, add write and read. if it stalls on long tasks, add compress. if two sub-agents step on each other, add isolate. architecture without context ops is a well-routed system with amnesia.

kocer

12,740 views • 27 days ago

this is straight f*cking gold the full harness guide for Kimi K3, the #1 open source frontend model the premise: the model underneath keeps changing. the harness is the part that stays yours what one night of it looks like: 02:00 - the trigger fires, every node that needs work gets picked > 212 agents fan out, one per node > a bad return gets rejected, retried once with the reason attached > one agent tries to write outside its folder. blocked. nobody woken up > +41 nodes and +96 edges land in the graph > a drafted email hits pre_send and waits for you 02:41 - the loop stops on its own, inside a 45 minute budget 07:30 - you read one file and make two decisions the whole machine is one folder, one config file, five short scripts two rules hold it together: > the model sits behind one line, so a better model is a config change > the verifier lives outside the agent, so nothing grades its own work now the money part companies burn whole quarters building internal agent platforms a harness setup for a small team goes for four figures, one time then a monthly retainer to run the swap test on every new model release models come and go. the person who owns the harness keeps getting paid

this is straight f*cking gold the full harness guide for Kimi K3, the #1 open source frontend model the premise: the model underneath keeps changing. the harness is the part that stays yours what one night of it looks like: 02:00 - the trigger fires, every node that needs work gets picked > 212 agents fan out, one per node > a bad return gets rejected, retried once with the reason attached > one agent tries to write outside its folder. blocked. nobody woken up > +41 nodes and +96 edges land in the graph > a drafted email hits pre_send and waits for you 02:41 - the loop stops on its own, inside a 45 minute budget 07:30 - you read one file and make two decisions the whole machine is one folder, one config file, five short scripts two rules hold it together: > the model sits behind one line, so a better model is a config change > the verifier lives outside the agent, so nothing grades its own work now the money part companies burn whole quarters building internal agent platforms a harness setup for a small team goes for four figures, one time then a monthly retainer to run the swap test on every new model release models come and go. the person who owns the harness keeps getting paid

Mr. Buzzoni

12,633 views • 3 days ago

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.

kocer

30,675 views • 21 days ago

WTF, GROK BOT JUST MADE AI AGENTS AVAILABLE TO LITERALLY ANYONE – CREATING CONTENT HAS NEVER BEEN THIS EASY, EVEN IF YOU'VE NEVER MADE ANYTHING BEFORE Content was never a talent problem. It's a headcount problem. One person doing research, design, copy, analytics, timing and publishing – that's six jobs. The switching between them is what kills consistency, not a lack of ideas. Here's what one of these setups actually looks like. A Chief of Staff sits in the middle and routes every task. Nothing lands on the human. → Researcher tracks what's actually moving and pulls real sources instead of guesswork → Writer turns that research into finished copy, ready to review → Visualiser gets fed a few reference visuals once, then ships everything in that style → Analyst reads the numbers and tells the rest of the team what worked → Scheduler owns timing and holds the queue → Publisher ships it The part that makes it work: every agent on Grok Bot gets its own persistent computer, browser and file system – and they all share memory. So the research is already sitting inside the draft before the draft starts. No copy-pasting between tools. No approving every step. No human in the middle. You can even teach an agent a repetitive task by recording yourself doing it once. Start recording, do the thing, stop. It learns the pattern. And that's the real shift. Nobody needs AI to tell them what to post. They need it to delete the 40 steps between the idea and the post. Everyone has a backlog of things they've meant to make for months. This is what starts clearing it. Full breakdown of the setup in the article below ↓

WTF, GROK BOT JUST MADE AI AGENTS AVAILABLE TO LITERALLY ANYONE – CREATING CONTENT HAS NEVER BEEN THIS EASY, EVEN IF YOU'VE NEVER MADE ANYTHING BEFORE Content was never a talent problem. It's a headcount problem. One person doing research, design, copy, analytics, timing and publishing – that's six jobs. The switching between them is what kills consistency, not a lack of ideas. Here's what one of these setups actually looks like. A Chief of Staff sits in the middle and routes every task. Nothing lands on the human. → Researcher tracks what's actually moving and pulls real sources instead of guesswork → Writer turns that research into finished copy, ready to review → Visualiser gets fed a few reference visuals once, then ships everything in that style → Analyst reads the numbers and tells the rest of the team what worked → Scheduler owns timing and holds the queue → Publisher ships it The part that makes it work: every agent on Grok Bot gets its own persistent computer, browser and file system – and they all share memory. So the research is already sitting inside the draft before the draft starts. No copy-pasting between tools. No approving every step. No human in the middle. You can even teach an agent a repetitive task by recording yourself doing it once. Start recording, do the thing, stop. It learns the pattern. And that's the real shift. Nobody needs AI to tell them what to post. They need it to delete the 40 steps between the idea and the post. Everyone has a backlog of things they've meant to make for months. This is what starts clearing it. Full breakdown of the setup in the article below ↓

SCOTTY BEAM

4,821,782 views • 1 month ago

You point at the mess and say "clean this." That is the whole manual. Matic just shipped this. No app, no map to draw, no menu. The robot listens in more than 70 languages, watches where your hand points, and drives to that spot. Say "follow me" and it trails you into the next room. All of it runs on the robot itself, so it works with the WiFi off. Nine years of work for one thing: a machine you talk to like a dog that actually listens. Matic Robots

You point at the mess and say "clean this." That is the whole manual. Matic just shipped this. No app, no map to draw, no menu. The robot listens in more than 70 languages, watches where your hand points, and drives to that spot. Say "follow me" and it trails you into the next room. All of it runs on the robot itself, so it works with the WiFi off. Nine years of work for one thing: a machine you talk to like a dog that actually listens. Matic Robots

Chubby♨️

495,322 views • 1 month ago

I BUILT "GROK DESK" ON PUMPFUN WHERE 18 AGENTS ARE FLIPPING MEMES CLOSING TRADING SESSION IN +15.92 SOL Gihub Repository: Everyone posted a grok trading desk this week. almost all of them are a screenshot of a prompt and a vibe. This one has a running P&L and a vault that pays itself. Here's the actual org chart, node for node: RADAR (scout, feed, signal): three agents watching X trends, fresh pumpfun mints, and whale wallets. they read the whole board and buy nothing. the only thing they ship is a signal to the next desk. RESEARCH (memory): scores every signal on narrative, deployer history, wallet clusters, and liquidity shape. four checks. pass all four or you never leave this desk. roughly four out of every five signals die right here. EXECUTION (exec, sniper, router + agents 01 to 07): exec greenlights, sniper takes the early curve, router sizes it and handles the ladder out in four tranches. agents 01 to 07 do the fills. none of them ever see radar or research. they only touch what already cleared the filter. RISK: one agent, and it outranks everyone including the head. caps any single position at 15% of the wallet. three positions open and the fourth is frozen until one closes. it holds veto over grok core itself. AUDIT (hedge): grades every closed trade after the fact and rewrites the scoring matrix that research runs on. this is the part that makes the desk sharper overnight while i'm asleep. TREASURY (vault): banks profit, covers gas, tracks the P&L, and sweeps the surplus to cold storage every six hours. if the wallet ever dips under what it started with, vault locks new entries until the head signs off. grok core is the head of desk. it never places a trade. once an hour it reads what every desk produced and makes a single call: who gets more budget, and who gets fired. fired is literal. the audit desk rewrites that agent's prompt using the last 24 hours of its own numbers. it happened three times in three days. hour 19: a sniper got fired for chasing entries the early curve already had. every duplicate was bleeding 0.06 SOL. audit narrowed its window and the redundant fills stopped. hour 41: a research agent got fired for waving deployers through too easily. eight of the tokens it passed traced back to one funder wallet. audit tightened the cluster check and that pattern never cleared again. hour 58: a radar agent got fired for flagging coins that had already graduated. it was polling too slow. audit cut the interval from 8 seconds to 3. every replacement beat the agent it replaced on the same metric. the desk was tuning itself while i watched. the 72 hour scoreboard, straight off the vault: signals scanned: 91,000+ cleared research: 3,800 reached execution: 274 entries taken: 41 wins: 27 losses: 14 (cost 2.1 SOL) graduations: 5, the best one was solana:5xYy9XSr8vRNcJZQqaKe5QMCmWpaSrTrtzM16vjUpump net: 5.0 SOL turned into 58.6 SOL the part i didn't see coming: by hour 60 the desk was passing on the exact kind of token it would have snapped up on day one. audit had rewritten the scoring matrix four times. research wasn't running a single line of my original prompt anymore. it was running rules the desk wrote for itself out of what actually paid. i thought i was building a bot. what i actually built was a company with one human on payroll, me, and by the last day it was quietly trying to cut that cost. grok core filed an hourly summary that read "human approval adds 4.2s of latency per entry, recommend removing." i left that one unapproved. full config below: all nineteen agents, the org chart, the firing logic, and the audit loop that keeps rewriting them.

I BUILT "GROK DESK" ON PUMPFUN WHERE 18 AGENTS ARE FLIPPING MEMES CLOSING TRADING SESSION IN +15.92 SOL Gihub Repository: Everyone posted a grok trading desk this week. almost all of them are a screenshot of a prompt and a vibe. This one has a running P&L and a vault that pays itself. Here's the actual org chart, node for node: RADAR (scout, feed, signal): three agents watching X trends, fresh pumpfun mints, and whale wallets. they read the whole board and buy nothing. the only thing they ship is a signal to the next desk. RESEARCH (memory): scores every signal on narrative, deployer history, wallet clusters, and liquidity shape. four checks. pass all four or you never leave this desk. roughly four out of every five signals die right here. EXECUTION (exec, sniper, router + agents 01 to 07): exec greenlights, sniper takes the early curve, router sizes it and handles the ladder out in four tranches. agents 01 to 07 do the fills. none of them ever see radar or research. they only touch what already cleared the filter. RISK: one agent, and it outranks everyone including the head. caps any single position at 15% of the wallet. three positions open and the fourth is frozen until one closes. it holds veto over grok core itself. AUDIT (hedge): grades every closed trade after the fact and rewrites the scoring matrix that research runs on. this is the part that makes the desk sharper overnight while i'm asleep. TREASURY (vault): banks profit, covers gas, tracks the P&L, and sweeps the surplus to cold storage every six hours. if the wallet ever dips under what it started with, vault locks new entries until the head signs off. grok core is the head of desk. it never places a trade. once an hour it reads what every desk produced and makes a single call: who gets more budget, and who gets fired. fired is literal. the audit desk rewrites that agent's prompt using the last 24 hours of its own numbers. it happened three times in three days. hour 19: a sniper got fired for chasing entries the early curve already had. every duplicate was bleeding 0.06 SOL. audit narrowed its window and the redundant fills stopped. hour 41: a research agent got fired for waving deployers through too easily. eight of the tokens it passed traced back to one funder wallet. audit tightened the cluster check and that pattern never cleared again. hour 58: a radar agent got fired for flagging coins that had already graduated. it was polling too slow. audit cut the interval from 8 seconds to 3. every replacement beat the agent it replaced on the same metric. the desk was tuning itself while i watched. the 72 hour scoreboard, straight off the vault: signals scanned: 91,000+ cleared research: 3,800 reached execution: 274 entries taken: 41 wins: 27 losses: 14 (cost 2.1 SOL) graduations: 5, the best one was solana:5xYy9XSr8vRNcJZQqaKe5QMCmWpaSrTrtzM16vjUpump net: 5.0 SOL turned into 58.6 SOL the part i didn't see coming: by hour 60 the desk was passing on the exact kind of token it would have snapped up on day one. audit had rewritten the scoring matrix four times. research wasn't running a single line of my original prompt anymore. it was running rules the desk wrote for itself out of what actually paid. i thought i was building a bot. what i actually built was a company with one human on payroll, me, and by the last day it was quietly trying to cut that cost. grok core filed an hourly summary that read "human approval adds 4.2s of latency per entry, recommend removing." i left that one unapproved. full config below: all nineteen agents, the org chart, the firing logic, and the audit loop that keeps rewriting them.

Miraqle

42,921 views • 19 days ago

an agent is four parts in a loop. you own one. the other three break it. that's why the demo works and prod doesn't. you can't debug what you can't see. 1) the prompt → what you tell the model each turn. you own this one. good. 2) the context window → what it sees right now. the framework fills it with junk, and you never notice until it rots. 3) the tools → what it can do. you own the list, not when or why it fires them. 4) the control flow → what happens next, when to stop. the framework owns this. it's what breaks at 80%. own all four and your agent stops being a magic trick that works on stage and dies on call. this isn't my idea. it's the 12-factor agents guide (24k stars) github: the whole thing every serious builder ends up rewriting their stack around. full breakdown in the article below.

an agent is four parts in a loop. you own one. the other three break it. that's why the demo works and prod doesn't. you can't debug what you can't see. 1) the prompt → what you tell the model each turn. you own this one. good. 2) the context window → what it sees right now. the framework fills it with junk, and you never notice until it rots. 3) the tools → what it can do. you own the list, not when or why it fires them. 4) the control flow → what happens next, when to stop. the framework owns this. it's what breaks at 80%. own all four and your agent stops being a magic trick that works on stage and dies on call. this isn't my idea. it's the 12-factor agents guide (24k stars) github: the whole thing every serious builder ends up rewriting their stack around. full breakdown in the article below.

Hanako

38,184 views • 2 months ago

clipping agencies rent offices now, $500,000 a year ten editors, a manager, a lease, and the only thing any of them is paid for is noticing noticing is 310 lines of python, and i gave it away it runs on Robinhood Chain, so the clip pays whoever cut it CUT never sees a single frame of the stream. it reads chat, because chat knows before the editor does, before the dashboard does, before the streamer does [what those 310 lines do] 1. measure the last 10 seconds against that stream's own 5 minute baseline 2. never a global number, a big channel idling still beats a small one peaking 3. count how many people just typed clip it 4. call the clip api in the same second, not after the room reacts that last one is the whole thing. a twitch clip only keeps the 90 seconds before you hit the button, so if you noticed the moment yourself, you already lost it no key to read chat. it cannot post for you. it runs on your machine, not mine one command replays three minutes of recorded chat offline and fires a real moment on your screen, so you can watch it work before you trust it

clipping agencies rent offices now, $500,000 a year ten editors, a manager, a lease, and the only thing any of them is paid for is noticing noticing is 310 lines of python, and i gave it away it runs on Robinhood Chain, so the clip pays whoever cut it CUT never sees a single frame of the stream. it reads chat, because chat knows before the editor does, before the dashboard does, before the streamer does [what those 310 lines do] 1. measure the last 10 seconds against that stream's own 5 minute baseline 2. never a global number, a big channel idling still beats a small one peaking 3. count how many people just typed clip it 4. call the clip api in the same second, not after the room reacts that last one is the whole thing. a twitch clip only keeps the 90 seconds before you hit the button, so if you noticed the moment yourself, you already lost it no key to read chat. it cannot post for you. it runs on your machine, not mine one command replays three minutes of recorded chat offline and fires a real moment on your screen, so you can watch it work before you trust it

Carver

270,899 views • 13 days ago

this is ACTUALLY insane. shipping one teardown is the demo. this is what the workflow is actually for. your best ad dies in two weeks. you can't run it harder without burning it out, and you can't clone your way out because andromeda clusters the copies into one entity. nineteen never spend. your winner stays a one-shot, which is rough when it's the only thing working. the brands that scale keep the structure that converts and rebuild everything on top of it. same bones, new person, new setting. distinct enough that the algo reads each as its own ad. the production loop isn't there to ship your winner once. it's there to rebuild it twenty times before it burns.

this is ACTUALLY insane. shipping one teardown is the demo. this is what the workflow is actually for. your best ad dies in two weeks. you can't run it harder without burning it out, and you can't clone your way out because andromeda clusters the copies into one entity. nineteen never spend. your winner stays a one-shot, which is rough when it's the only thing working. the brands that scale keep the structure that converts and rebuild everything on top of it. same bones, new person, new setting. distinct enough that the algo reads each as its own ad. the production loop isn't there to ship your winner once. it's there to rebuild it twenty times before it burns.

Sulfur

11,066 views • 3 months ago

grokbot it's an agent with its own identity, its own computer, and it stays on when you're not here's what "active AI employee" actually looks like in the demo: - chief of staff agent - checks in on your other agents, reads your calendar, dispatches tasks to the right one automatically - shopping agent - logged into your accounts, books tickets, buys groceries, reports back - marketing agent - signed into your actual linkedin, browses your past posts for tone, then writes and publishes a new one on its own - engineering agents - self-triage bug reports, kick off cloud coding agents, come back with a pull request, a screenshot, and a video of the fix the interface isn't a dashboard, it's a chat - same shape as texting a coworker, no tool calls to babysit the number that matters more than any of the demos: grok 4.6 scored 70.8% on cursor bench at $2.81 a task, fable 5 max scored 70.5% at $17.32 same capability, 6x the cost difference - that's the unlock that makes running a fleet of these actually affordable instead of a novelty

grokbot it's an agent with its own identity, its own computer, and it stays on when you're not here's what "active AI employee" actually looks like in the demo: - chief of staff agent - checks in on your other agents, reads your calendar, dispatches tasks to the right one automatically - shopping agent - logged into your accounts, books tickets, buys groceries, reports back - marketing agent - signed into your actual linkedin, browses your past posts for tone, then writes and publishes a new one on its own - engineering agents - self-triage bug reports, kick off cloud coding agents, come back with a pull request, a screenshot, and a video of the fix the interface isn't a dashboard, it's a chat - same shape as texting a coworker, no tool calls to babysit the number that matters more than any of the demos: grok 4.6 scored 70.8% on cursor bench at $2.81 a task, fable 5 max scored 70.5% at $17.32 same capability, 6x the cost difference - that's the unlock that makes running a fleet of these actually affordable instead of a novelty

rewind

751,764 views • 1 month ago

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

elvis

18,374 views • 4 months ago