a developer showed me the cleanest multi-agent architecture i've... seen. one mission. nobody steps on anyone else. the mission: ship a safe feature. the graph decides what happens next. router reads the mission and asks one question: where should this go? three workers split in parallel. each in their own private work area. researcher finds the evidence. architect designs it. builder creates it. none of them share context. the three workers run independently. everything lands in shared state. facts, decisions, artifacts. one place where the whole picture exists without anyone copying transcripts. then the crew's work converges. integrator combines what was built. reviewer tests quality and safety. human checkpoint approves anything high-impact. then ship. verified output. private context. shared state. that separation is the whole trick. a prompter asks a question. an architect draws a graph. full breakdown with code in the article below.show more

rvaniaaa
27,465 Aufrufe • vor 3 Monaten
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 doshow more

leopardracer
54,830 Aufrufe • vor 3 Monaten
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.show more

kocer
31,198 Aufrufe • vor 2 Monaten
THIS IS A PURE F*CKING GOLDMINE Anthropic just shared... one of the best tricks for Claude Code: one model plans, a swarm executes, and nobody waits for anybody Opus 5.5 reads the task once, cuts it into 12 parallel lanes and then stops spending tokens entirely Haiku 4.5 takes everything mechanical, Sonnet 5.5 takes the few pieces that actually need judgment most setups die because the expensive model watches the work happen, and 12 agent transcripts in its context is how $12 disappears on a single task here the planner never reads raw output, every agent reports one line and the whole session stays under 9k of context a hard spend cap sits on the run, so one stuck agent cannot quietly eat the budget nothing gets reported until it passes its own check, and anything that fails re-runs in its own lane instead of landing back on the planner the planner comes back once at the end, reads 12 verified results and signs off, 2 minutes and 28 cents for the whole thing save it, this is the difference between burning your budget and finishing the jobshow more

Sprytix
13,966 Aufrufe • vor 26 Tagen
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 agentsshow more

Gipp 🦅
11,709 Aufrufe • vor 3 Monaten
AN ENGINEER SOLVED A PROBLEM NOBODY IN THE COMPANY... COULD FULLY MAP ON THEIR OWN The problem wasn't a missing tool, it was that every process touched three other processes nobody had written down. He wired dozens of agents into one shared graph instead of documenting each department's workflow by hand. Each agent owned one process, reading its own logs while writing every dependency it found straight into the shared structure. Within days, the graph surfaced a connection between two departments that had been quietly blocking each other for over a year. The company adopted the graph as its live map of operations, and it hasn't stopped finding new connections since. See what the graph found in the first 48 hours below👇show more

wast3
16,489 Aufrufe • vor 3 Monaten
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.show more

Hanako
38,387 Aufrufe • vor 4 Monaten
AN ANTHROPIC SYSTEM TURNS ONE PROMPT INTO A COMPLETE... GRAPH MODEL BUILT ENTIRELY ON ITS OWN One prompt is enough to spin up the full architecture, no schema written by hand, no roles assigned in advance. Parallel workers process every branch of the graph at once, each one handling its own slice independently. As each worker finishes, its output compacts straight into a single unified project instead of scattered fragments. Nothing needs stitching together manually, the compaction step folds every worker's result into one file automatically. The whole build runs end to end without a single manual step between the prompt and the finished project. See the full build and compact pipeline below👇show more

wast3
18,460 Aufrufe • vor 3 Monaten
sorry, they just did WHAT someone gave a machine... one disease name, the leading cause of blindness in the developed world with 1.5 million americans already in its path, and it came back pointing at a drug that has sat in pharmacies for years under a different label: 551 papers read in 30 minutes against the 294 hours a human would have needed, and the loop that did it is public on GitHub most agent setups answer one question at a time, so the ceiling on the work is the quality of the question you happened to think of this one was handed a single question and wrote the second one itself. turns out that follow-up is where the real find was: a target called ABCA1, upregulated threefold, in an experiment no human ordered i read the whole paper looking for the trick, and the trick is structural. that is the second question, and it is the gap between an assistant and a factory: - hand the loop a field rather than a task: it was given a disease, and choosing the mechanism was part of its job - make it rank before it spends: 151 papers in, ten candidate mechanisms out, scored against each other before anything touched a bench - split reading from judging, so the agent that forms the theory is a different agent from the one grading it - close every cycle on physical reality: the verdict was an experiment, and another model's opinion was never allowed to stand in for one - feed each result back as the next question rather than a log line, which is the step almost nobody builds - search what already passed inspection first: the winner was an approved compound with a safety file already on record - write down what the round learned before opening the next one, so round two starts where round one stopped my read, and i think it is the uncomfortable one: reading was the entire bottleneck in that field, and everybody spent the decade optimising the writing. people ran every physical experiment here, the analysis agent needs a domain expert writing its prompts, and the authors decline to call this the leap it resembles. the thinking got replaced, and the hands did not so the question i cannot answer for my own setup: which step of your loop still stops dead until you sit down and type something bookmark this one. the four parts that turn one model into a line that runs like this, the queue, the rooms, the write permissions and the gate, are built file by file in the piece below ↓show more

Argona
32,752 Aufrufe • vor 3 Monaten
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
157,688 Aufrufe • vor 3 Monaten
It is becoming f*cking dangerous A 23-year-old dev from... China just ran 300 Claude Code agents in parallel and hooked them to a verification layer so none of them could bullshit him He opens the live dashboard: - 300 agents writing and checking at the same time - Every output verified against the source in ~100 ms - Three passes over 100 company profiles → zero errors left - Everything dumped straight into an Obsidian vault The trick is the split: one model does the work, a cheaper one decides if the claim is actually true. The loop doesn’t stop until everything checks out An analyst team would bill weeks for this. He got it in one run Same kind of Second Brain + swarm setup that keeps circulating. Bookmark the full breakdownshow more

Lyren_o
7,003,307 Aufrufe • vor 29 Tagen
It is becoming f*cking dangerous A 27-year-old dev from... China just ran 300 Grok agents in parallel and hooked them to a Jev verification layer so none of them could bullshit him He opens the live dashboard: - 300 agents writing and checking at the same time - Every output verified against the source in ~100 ms - Three passes over 100 company profiles → zero errors left - Everything dumped straight into an Obsidian vault The trick is the split: one model does the work, a cheaper one decides if the claim is actually true. The loop doesn’t stop until everything checks out An analyst team would bill weeks for this. He got it in one run Jev + Grok Bots swarm setup that keeps circulating. Bookmark the full breakdown below:show more

rody
13,279 Aufrufe • vor 28 Tagen
You've probably scrolled past a dozen posts about Jev... this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.show more

John Turner
21,029 Aufrufe • vor 1 Monat
loop engineering worked for 6 months. then one pipeline... forced a graph a loop is one agent on discover → plan → execute → verify, until a stop condition hits enough for most agent work: failing tests, draft + self-review, inbox triage, one research writeup the break is nameable: if the thing that produced the output also grades it, you don't have quality control, you have a rubber stamp his numbers before the split: 40 drafts 31 passed self-review 18 actually publish-ready on manual read gap = 13 drafts with a passing grade from a biased judge he split one loop into 3 nodes - researcher · sources + notes only - writer · notes + task only · never grades itself - reviewer · separate model call · check the bar · write nothing same 40-draft workload. manual approval 18/40 → 33/40. reviewer rejected 14 with quotable reasons. 2 escalated to human instead of burning tokens forever approval 45% → 82.5%. inference cost +60% worth it when a bad draft costs more than three model calls. not worth it for "fix the failing test" playbook: - 1 law · producer never grades - 1 router · ship / retry / escalate - 1 state object · one owner per field · guarded writes - split the verifier first · cheapest highest-leverage move loop engineering → graph engineering. not five nodes for vibes, one split verifier when the loop starts grading its own homework full contracts, router, and decision function in the articleshow more

seeco
14,534 Aufrufe • vor 3 Monaten
YOUR OBSIDIAN VAULT READS ALL 2,000 NOTES TO ANSWER... ONE QUESTION. THAT'S NOT A SECOND BRAIN. That's a hoarder with markdown files. Hundreds of thousands of tokens burned per answer, and it still grabs the wrong note half the time. A real second brain runs on a graph: a router, an index, nodes, edges. Fable 5 reads 2-3 files instead of the whole vault. Answer back in under a second. The graph view everyone screenshots in Obsidian is a poster. The index is the actual engine. Full 11-step build below, from raw vault to working graph 👇show more

unicode
53,046 Aufrufe • vor 3 Monaten
After Andrej Karpathy released autoresearch, where an agent runs... experiments in a loop on its own, I packed his method into one prompt that turns Opus 5.5 into a graph and can carry almost any task to the finish. → writes a check that can actually fail, first → splits the task into parts → runs the independent parts in parallel → loops each one until it passes the check → sends back only the part that failed → turns every mistake into a rule for next time → calls you only for the step that can’t be undone Throw it at Opus 5.5 with the task you’ve been putting off for a week, and you’ll see the difference in one run. The full prompt is in the comments. How to tune it for your own work is in the article below. Save it before it gets lost ↓show more

Hoodie
331,551 Aufrufe • vor 12 Tagen
Rocket Missions If Rocket could do one thing for... you every day... Or every week... What would it be? Open the UpRock App. Assign Rocket a mission. Then let it work while you focus on everything else. Come back and share your Rocket Mission in the comments. 👇 You might inspire someone else's next mission.show more

UpRock
10,749 Aufrufe • vor 4 Monaten
Marriage with an ADHD husband is just one long... game of “where did he go this time?” She steps outside and finds him mid-mission… completely different mission than the one he started. That final “yep” from her is the sound of pure acceptance. Anyone else living this exact loop on the daily?show more

End3of6Days9 (Helen) 🇺🇸
40,701 Aufrufe • vor 3 Monaten
Pi rocks. the fact it can be steered programmatically... to such an extent is sick. below we have a structure: - coordinator speaks with me - it's the only one seeing the project broadly: vision, build board, feature lanes - it can spawn workers in separate sessions - workers are dispatched with a feature card and just enough context to deliver, nothing that would distract them - when workers are finished, reviewer kicks in in a separate session. it either accepts the work or sends it back with findings, to a fresh worker, never the one that wrote it. coordinator gets woken either way most of the logic related to communication happens deterministically, so there's a very little chance something relevant is skipped. Pi you guys building one of the most important piece of software of the upcoming months, at least.show more

Adam
101,316 Aufrufe • vor 3 Monaten
a contractor in Shenzhen priced a ¥12,470,900 hospital contract,... about $1.7m, in one afternoon and beat firms carrying forty people he explained how he did it: the bid consultancy he used to pay took three days and ¥46,000 for the same envelope. he did this one alone, off one screen, at 11.4% margin, uploaded before the 17:00 cutoff 214 pages of tender documents read, 68 binding clauses pulled out, 9,485 building parts loaded, 14 places found where a duct and a beam sit in the same cubic metre, deepest one 38mm, all of them fixed, 3,318 lines of quantities priced and the package encrypted and uploaded before the 17:00 cutoff this is Graph Engineering: the job gets cut into small nodes, one narrow task each, wired so that one node's output is the next node's input, and any node is allowed to stop the whole run. it turns a model that answers you into a machine that finishes the job: - give every node one job and one output. a node doing two things fails at both and you cannot tell which one broke - put the cheapest rejection first. his qualification node reads clause 7.4, foreign-owned firms barred, and ends the run four seconds in, before anything expensive touches the model - what moves between nodes is a file. the model travels as a model, the quantities as a table, the price as a number - build exactly one loop: the checker finds 14 collisions, the fixer drops the duct 550mm, the checker runs again, and nothing moves on until the count is zero - cap that loop, or a graph will grind on three impossible clashes until the deadline passes - keep one node whose only job is to say no, and give it authority over everything above it - log each node's output on its own, because when the price comes out wrong you need to know which node believed the wrong thing - run the expensive nodes last, always the catch is that a graph is an extremely confident machine: point it at an outdated rate book and it prices an entire hospital off it without a single node noticing, because no node is asked to doubt the input, only to process it so the nodes that earn their keep are the ones that reject, and almost nobody builds those first bookmark this, the full build with all nine nodes and what each one hands to the next is written out in the article ↓show more

Argona
38,189 Aufrufe • vor 3 Monaten
Introducing Parallel in Slack. Tell Parallel what to monitor... on the web, and the agent posts in the channel when there's a hit. Or tag it with a question to get a cited answer based on the context in your thread. Available today on the Slack Marketplace.show more

Parallel
20,087 Aufrufe • vor 16 Tagen