正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Google's team published a 9-page PDF on Harness Engineering. one formula replaced prompt engineering: Agent = Model + Harness the twist: same Claude Sonnet, same benchmark. change only the harness the playbook, six steps: step 1 -> add guides AGENTS.md, rule files, constraint docs. every line is a past... agent failure turned into a permanent fix step 2 -> add sensors linters, tests, validation scripts the agent runs on its own output before a human sees it step 3 -> build the agentic loop plan, execute, verify, fix. bounded retries, budget caps, escalation when stuck step 4 -> externalize memory the model forgets every session. the harness holds state, decisions and artifacts across all of them step 5 -> enforce permissions which tools, how many writes, what needs approval. safety lives in the harness, never in the model step 6 -> wire observability track every tool call, cost and retry. trip wires fire when behavior drifts the result: your agent turns from a demo into infrastructure every failure makes the system permanently better, not just the next conversation that's also the line between an agent you show people and one a client pays you to leave running one harness gets you a reliable loop. connect several and it becomes graph engineering, where one agent's failure turns into another agent's sensor the PDF stops at the harness. the graph is the next layer that breakdown, running on Kimi, is below ↓show more

Annatar.md

3,577 subscribers

79,906 次观看 • 2 个月前 •via X (Twitter)

科学技术教育新闻政治

Anya Rossi• Live Now

Private livecam show

22 条评论

AI Apps API 的头像

AI Apps API2 个月前

Step four is the one people underrate and by far the hardest to retrofit. Externalizing memory is really three decisions: what gets extracted at write time, where it is stored, and how it comes back. Most teams make the second one and skip the first, dropping raw transcripts into a vector store, and then retrieval has to re-derive the entities and decisions at query time, on every query, forever. Extract at ingestion, dedupe against what is already there, and keep the metadata you will want to rank on later. That is the split between a harness that improves with use and one that just accumulates.

David Starmac Ai 的头像

David Starmac Ai2 个月前

The harness part is underrated. In practice a good AGENTS.md changes results more than switching models. Question is how they kept guides from contradicting each other as they stack up.

palehonk 的头像

palehonk2 个月前

harness turns an agent from a demo into infrastructure that's actually really cool

morph 的头像

morph2 个月前

dang how somebody could let this be leaked? immediately saved this just in case xd

Kotte 的头像

Kotte2 个月前

state lives in the harness not the model

zaiyanglab 的头像

zaiyanglab2 个月前

Prompt tweaks help; evals on paying-user tasks decide who stays.

Andreas Edesberg 的头像

Andreas Edesberg2 个月前

Where can I find the article?

Assaf Kipnis 的头像

Assaf Kipnis2 个月前

I am loving that Google used Claude here and not Gemini

Jeremy RVN 的头像

Jeremy RVN2 个月前

Matches what I see running agents in production. Model swaps stopped moving the needle a while ago. The wins come from constraints, verification steps and what the agent is allowed to touch. The harness is unglamorous work nobody benchmarks, which is exactly why it is the moat.

Yurii Filipchuk🇺🇦 — e/acc 的头像

Yurii Filipchuk🇺🇦 — e/acc2 个月前

"the agent's ninety-five percent reliable." "how many steps?" "thirty." "so it's twenty-one percent reliable."

Aman yadav 的头像

Aman yadav2 个月前

can you provide link of harness doc

Ivan Dorna 的头像

Ivan Dorna2 个月前

Using AGENTS.md and SKILLS.md is THE problem.

Ryan Keary 的头像

Ryan Keary2 个月前

how do you stop the guides from cancelling each other once the file gets long

stunspot | ⟨🤩⨯📍⟩ | 的头像

stunspot | ⟨🤩⨯📍⟩ |2 个月前

"We replaced prompt engineering! By writing prompts in _files_ not chat windows! You never need to worry about "prompting" again, except every time you write a tool description, SKILL.md, AGENTS.md, or want to understand context! Automate prompting without understanding it!"

techVector 的头像

techVector2 个月前

Honestly that formula makes so much sense. We've been overthinking prompts when the real magic is in how you set up the whole system around the model. Same brain, better tools and rules. Feels obvious

Mildly Magical 的头像

Mildly Magical2 个月前

@grok give me a brief bullet list of the key learnings for a solo Agentic dev he can put into practice.

Andry Dina 的头像

Andry Dina2 个月前

Same Sonnet, better score from guides and external memory - that's the harness doing the work, not a new brain. When do we stop calling leaderboard jumps "model progress"?

Korens 的头像

Korens2 个月前

saved

Chen 的头像

Chen2 个月前

leaderboard drama never ends

拾光的 AI 应用观察的头像

拾光的 AI 应用观察2 个月前

Google这个思路我挺认同的，prompt engineering搞到后面确实边际效益递减，不如把约束外置到harness里。不过这种效率提升实际还得看具体任务，benchmark上好看不等于落地都能省token。AGENTS.md那套倒是跟我现在带团队做agent的流程有点像，markdown把规则写清楚比调prompt省心多了。

Blake Murphy 的头像

Blake Murphy2 个月前

Most people judge an agent on its first session. The test that matters is the hundredth, when the model has forgotten everything and the harness has to carry the context, decisions, and guardrails across all of them. That is where an agent either becomes infrastructure or stays a demo.

Bally_AgenticAI 的头像

Bally_AgenticAI2 个月前

Most builders stop at step 3 (the loop) - skip memory + observability and demos die in production. Chain harnesses together and cross-agent state consistency becomes the real bottleneck. #AgenticAI #ContextEngineering @LangChain

相关视频

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

elune

16,875 次观看 • 3 个月前

the loop is not the agent it is one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls repetition turns retries budgets exits success checks no progress use durable execution when the run must survive failure → GRAPH ENGINEERING controls topology nodes edges state branches checkpoints handoffs build stateful agents as explicit graphs → analyze the topology without putting a model in the loop → HARNESS ENGINEERING controls the blast radius tools permissions memory sandboxes evals traces humans isolate generated code from the host → test behavior before it reaches users → keep one trace across every model node and tool call → without loop control it never stops without graph structure you cannot see the path without harness control it can touch anything the loop lives inside the graph the graph lives inside the harness the model is not the system debug the layer that owns the failure save this

the loop is not the agent it is one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls repetition turns retries budgets exits success checks no progress use durable execution when the run must survive failure → GRAPH ENGINEERING controls topology nodes edges state branches checkpoints handoffs build stateful agents as explicit graphs → analyze the topology without putting a model in the loop → HARNESS ENGINEERING controls the blast radius tools permissions memory sandboxes evals traces humans isolate generated code from the host → test behavior before it reaches users → keep one trace across every model node and tool call → without loop control it never stops without graph structure you cannot see the path without harness control it can touch anything the loop lives inside the graph the graph lives inside the harness the model is not the system debug the layer that owns the failure save this

elune

50,193 次观看 • 3 个月前

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below

rari

20,934 次观看 • 3 个月前

Harness vs. Graphs, clearly explained! a harness is great, and most people think it is the whole thing: retries, timeouts, a sandbox, a log, the context it assembles before every call. all of that is real work, and all of it wraps exactly one call. run it a hundred times and you have one call, made very safely, a hundred times. Graph engineering fixes this by moving the decision up a layer: not how safely one call is made, but which calls exist to be made at all. you need both, and here is the sentence that resolves the whole confusion: the harness is everything around one call. the graph is everything between them. ↳ around one call: retry, timeout, sandbox, log, assemble the context, hand back a result ↳ between calls: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the harness does not go away when you build a graph. it moves under each node, and now there are five of them, each wrapping a call you would never have made by hand. the trick is knowing which layer a failure belongs to. turn a piece off and run it again. if the call still works, it was the harness. if the wrong step runs at all, it was the graph. people spend weeks hardening a harness around a node that should not have existed. one thing to know before you scale it. most of what people call their agent is a harness with a chat box on it. ↳ it retries, it times out, it logs, it assembles context, it holds one call up beautifully ↳ it has never once decided that a second call should exist, and that is the entire difference that last one catches careful people. a harness that never fails is not evidence the system is right. it is evidence one call went well, which is the smallest possible claim. and the one that eats whole nights: a harness cannot save you from the wrong step running. you can retry a bad decision three times with a clean log and perfect isolation, and all you bought was three copies of it. 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 ↓

Harness vs. Graphs, clearly explained! a harness is great, and most people think it is the whole thing: retries, timeouts, a sandbox, a log, the context it assembles before every call. all of that is real work, and all of it wraps exactly one call. run it a hundred times and you have one call, made very safely, a hundred times. Graph engineering fixes this by moving the decision up a layer: not how safely one call is made, but which calls exist to be made at all. you need both, and here is the sentence that resolves the whole confusion: the harness is everything around one call. the graph is everything between them. ↳ around one call: retry, timeout, sandbox, log, assemble the context, hand back a result ↳ between calls: split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs the harness does not go away when you build a graph. it moves under each node, and now there are five of them, each wrapping a call you would never have made by hand. the trick is knowing which layer a failure belongs to. turn a piece off and run it again. if the call still works, it was the harness. if the wrong step runs at all, it was the graph. people spend weeks hardening a harness around a node that should not have existed. one thing to know before you scale it. most of what people call their agent is a harness with a chat box on it. ↳ it retries, it times out, it logs, it assembles context, it holds one call up beautifully ↳ it has never once decided that a second call should exist, and that is the entire difference that last one catches careful people. a harness that never fails is not evidence the system is right. it is evidence one call went well, which is the smallest possible claim. and the one that eats whole nights: a harness cannot save you from the wrong step running. you can retry a bad decision three times with a clean log and perfect isolation, and all you bought was three copies of it. 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

51,717 次观看 • 1 个月前

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

31,198 次观看 • 2 个月前

Harness Engineering 2.0 is here! We benchmark models all the time but the harness running the model can dramatically improve the result, cost, and execution time too. And finally, devs just open-sourced Harness Arena, where you can test the same task across multiple harness and model combinations side by side. You provide one task and then run it across several model x harness configs that you want to test. Every config receives the same prompt, files, tools, skills, and evaluation checks. Harness Arena then returns: - total cost - execution time - whether the task passed - files and artifacts produced If you want to try it yourself, it is implemented within the open-source HarnessRouter project. Here's the repo: (don't forget to star it ⭐ ) HarnessRouter is a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 25 more agent harnesses In Harness Arena, the cheapest run does not automatically win. A config must complete the task correctly first. Cost and execution time are compared only among the configurations that pass. Here's the result from one Harness Arena test: - Hermes + GPT-5.2: 5/5 successful runs using 0.47 credits - Claude Code + Opus 4.8: 3/5 successful runs using 223 credits That is around 474x difference in credits, while the more expensive configuration also failed two runs. You can keep the model fixed to measure how much the harness changes the result. Or vary both to find the best harness and model pairing for that task. This helps answer practical questions such as: - Should this task run on Codex or Claude? - Can a cheaper config still pass every check? - Which setup is best to handle this workload? Once you find the best config, you can run future tasks through it using the same Unified Harness Protocol (UHP) interface for sessions, streaming, files, artifacts, cancellation, and failures. So you are no longer choosing an agent stack based only on a model leaderboard. Instead, you can benchmark the complete runtime on the task your product actually needs to solve. To dive deeper, my co-founder wrote an article explaining why model routing is different from harness routing, how UHP works, and what supporting multiple agent runtimes involves. It also covers the local setup, a working request, and how sessions and files move through the system. Read it below.

Harness Engineering 2.0 is here! We benchmark models all the time but the harness running the model can dramatically improve the result, cost, and execution time too. And finally, devs just open-sourced Harness Arena, where you can test the same task across multiple harness and model combinations side by side. You provide one task and then run it across several model x harness configs that you want to test. Every config receives the same prompt, files, tools, skills, and evaluation checks. Harness Arena then returns: - total cost - execution time - whether the task passed - files and artifacts produced If you want to try it yourself, it is implemented within the open-source HarnessRouter project. Here's the repo: (don't forget to star it ⭐ ) HarnessRouter is a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 25 more agent harnesses In Harness Arena, the cheapest run does not automatically win. A config must complete the task correctly first. Cost and execution time are compared only among the configurations that pass. Here's the result from one Harness Arena test: - Hermes + GPT-5.2: 5/5 successful runs using 0.47 credits - Claude Code + Opus 4.8: 3/5 successful runs using 223 credits That is around 474x difference in credits, while the more expensive configuration also failed two runs. You can keep the model fixed to measure how much the harness changes the result. Or vary both to find the best harness and model pairing for that task. This helps answer practical questions such as: - Should this task run on Codex or Claude? - Can a cheaper config still pass every check? - Which setup is best to handle this workload? Once you find the best config, you can run future tasks through it using the same Unified Harness Protocol (UHP) interface for sessions, streaming, files, artifacts, cancellation, and failures. So you are no longer choosing an agent stack based only on a model leaderboard. Instead, you can benchmark the complete runtime on the task your product actually needs to solve. To dive deeper, my co-founder wrote an article explaining why model routing is different from harness routing, how UHP works, and what supporting multiple agent runtimes involves. It also covers the local setup, a working request, and how sessions and files move through the system. Read it below.

Avi Chawla

31,532 次观看 • 5 天前

This is pure f*cking treasure Google researchers just open-sourced an agent that rebuilds its own harness on tasks it has never seen The model stays frozen, not a single weight changes. Everything around it gets better instead Here's how one loop works: > The agent runs the task with its current harness > A Harness Editor proposes edits: general ones and domain-specific ones > It can touch 8 parts: system prompt, guardrails, memory, skills, plugins, tool guidance, scripts and subagents > Every edit gets probed on the same task > A Harness Composer compares how each version behaved and merges what worked into the final harness > An Experience Reflector writes down what it learned > Those lessons go into a persistent Improvement Harness that guides the next task No ground-truth labels, nobody tells it the right answer It just keeps getting better, task after task

This is pure f*cking treasure Google researchers just open-sourced an agent that rebuilds its own harness on tasks it has never seen The model stays frozen, not a single weight changes. Everything around it gets better instead Here's how one loop works: > The agent runs the task with its current harness > A Harness Editor proposes edits: general ones and domain-specific ones > It can touch 8 parts: system prompt, guardrails, memory, skills, plugins, tool guidance, scripts and subagents > Every edit gets probed on the same task > A Harness Composer compares how each version behaved and merges what worked into the final harness > An Experience Reflector writes down what it learned > Those lessons go into a persistent Improvement Harness that guides the next task No ground-truth labels, nobody tells it the right answer It just keeps getting better, task after task

NO1ennn

19,382 次观看 • 9 天前

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

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

Mr. Buzzoni

45,278 次观看 • 3 个月前

Grok Bot + Kimi K3 can be turned into something bigger than an agent: an AI operating system the formula: AI OS = Router + Reasoning + Memory + Tools + Loops + Verification not one giant assistant. six layers that keep work moving without you step 1 -> Grok Bot becomes the operator. you give it the goal, it breaks the goal into jobs, assigns priorities and decides what part of the system should act next. step 2 -> Kimi K3 becomes the reasoning core. hard research, synthesis, long context and planning move here instead of forcing every task through the same model. step 3 -> externalize memory. store goals, decisions, failed attempts, artifacts and current state outside the chat. close the session, come back tomorrow, and the system still knows where it is. step 4 -> connect tools: search, code, files, APIs, docs and data. reasoning decides what should happen. tools actually make it happen. step 5 -> add the loop engine: plan -> execute -> inspect -> update memory -> retry. the loop can wait for new information, rerun a failed task, hand work to another agent or stop when the goal is complete. step 6 -> verify before output. tests, source checks, constraints and explicit completion rules decide whether the system ships the result or sends it back into the loop. that's the difference between an AI assistant and an AI operating system. an assistant waits for your next message. an operating system carries state, routes work and keeps moving. Grok Bot handles orchestration, Kimi K3 handles deeper reasoning, memory keeps the state alive, tools execute, the loop keeps the system running, verification decides when it is actually done. build one reliable loop and you have an agent. connect reasoning, memory, tools and multiple loops around it and you start building infrastructure. the full Grok Bot + Kimi K3 AI OS breakdown is below ↓

Grok Bot + Kimi K3 can be turned into something bigger than an agent: an AI operating system the formula: AI OS = Router + Reasoning + Memory + Tools + Loops + Verification not one giant assistant. six layers that keep work moving without you step 1 -> Grok Bot becomes the operator. you give it the goal, it breaks the goal into jobs, assigns priorities and decides what part of the system should act next. step 2 -> Kimi K3 becomes the reasoning core. hard research, synthesis, long context and planning move here instead of forcing every task through the same model. step 3 -> externalize memory. store goals, decisions, failed attempts, artifacts and current state outside the chat. close the session, come back tomorrow, and the system still knows where it is. step 4 -> connect tools: search, code, files, APIs, docs and data. reasoning decides what should happen. tools actually make it happen. step 5 -> add the loop engine: plan -> execute -> inspect -> update memory -> retry. the loop can wait for new information, rerun a failed task, hand work to another agent or stop when the goal is complete. step 6 -> verify before output. tests, source checks, constraints and explicit completion rules decide whether the system ships the result or sends it back into the loop. that's the difference between an AI assistant and an AI operating system. an assistant waits for your next message. an operating system carries state, routes work and keeps moving. Grok Bot handles orchestration, Kimi K3 handles deeper reasoning, memory keeps the state alive, tools execute, the loop keeps the system running, verification decides when it is actually done. build one reliable loop and you have an agent. connect reasoning, memory, tools and multiple loops around it and you start building infrastructure. the full Grok Bot + Kimi K3 AI OS breakdown is below ↓

Alex

13,312 次观看 • 2 个月前

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Hanako

37,887 次观看 • 1 个月前

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into reliable workflows 1:30:15 - Build agents that improve their own work 1:49:05 - Run the complete system without supervision Model → Harness → Reliable Software Most agent tutorials stop once the model can call a tool This one shows you how to build the infrastructure around it within the first 20 minutes Most people are still prompting one agent at a time Andrew Ng is already teaching the layer above: Harnesses that give agents context, tools, tests, and feedback Watch this brilliant course and build the harness Then read the full architecture below ↓

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into reliable workflows 1:30:15 - Build agents that improve their own work 1:49:05 - Run the complete system without supervision Model → Harness → Reliable Software Most agent tutorials stop once the model can call a tool This one shows you how to build the infrastructure around it within the first 20 minutes Most people are still prompting one agent at a time Andrew Ng is already teaching the layer above: Harnesses that give agents context, tools, tests, and feedback Watch this brilliant course and build the harness Then read the full architecture below ↓

Ichigo

101,815 次观看 • 2 个月前

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.

NO1ennn

69,163 次观看 • 2 个月前

This is f*cking insane. Chinese researchers just dropped a paper with a title that will make every agent framework nervous: "The End of Harness Engineering". The argument fits in one line: writing the program around the model is finished as a skill. A harness written by a human is one person's guess about one task on one afternoon. It ships, nobody re-reads it, nobody scores it, and the agent runs that guess for months. A harness written by the loop is a file that grades itself. A small 4B model reads what failed, writes 8 edits, and only the edit that scores best on held-out questions survives. The big model never changes. The file around it does, every round. So the human job collapses to one artifact: the scoring set. You write the questions, never the program. Frameworks turn disposable. The exam turns into the job. That is the exact loop I built and documented below: one 300 Kimi K3 workers, 37 rewrites in 41 rounds, zero opened by me. The whole paper in one line: write the exam before the code ↓

This is f*cking insane. Chinese researchers just dropped a paper with a title that will make every agent framework nervous: "The End of Harness Engineering". The argument fits in one line: writing the program around the model is finished as a skill. A harness written by a human is one person's guess about one task on one afternoon. It ships, nobody re-reads it, nobody scores it, and the agent runs that guess for months. A harness written by the loop is a file that grades itself. A small 4B model reads what failed, writes 8 edits, and only the edit that scores best on held-out questions survives. The big model never changes. The file around it does, every round. So the human job collapses to one artifact: the scoring set. You write the questions, never the program. Frameworks turn disposable. The exam turns into the job. That is the exact loop I built and documented below: one 300 Kimi K3 workers, 37 rewrites in 41 rounds, zero opened by me. The whole paper in one line: write the exam before the code ↓

slash1s

109,779 次观看 • 23 天前

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 次观看 • 3 个月前

Google just dropped the best 1-hour course on Graph Engineering: from one agent to Loops and Graphs 00:00 - your first AI agent 08:24 - build agent memory 28:34 - agentic loops 40:04 - how to build MCP 1:00:22 - graph engineering free, and the best thing on graph engineering I have come across Prompts → Agents → Loops → Graphs most people will stop after the memory chapter and call it a system he saves the last twenty minutes for the layer above all of it same model, same tokens, completely different week watch it today the step-by-step guide is below, save it while it is still early ↓

Google just dropped the best 1-hour course on Graph Engineering: from one agent to Loops and Graphs 00:00 - your first AI agent 08:24 - build agent memory 28:34 - agentic loops 40:04 - how to build MCP 1:00:22 - graph engineering free, and the best thing on graph engineering I have come across Prompts → Agents → Loops → Graphs most people will stop after the memory chapter and call it a system he saves the last twenty minutes for the layer above all of it same model, same tokens, completely different week watch it today the step-by-step guide is below, save it while it is still early ↓

Residual

96,159 次观看 • 1 个月前

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

120,488 次观看 • 4 个月前

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

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

Codez

44,590 次观看 • 3 个月前

MOST PEOPLE BUILD AI AGENTS BACKWARDS. They start with prompts, then add tools, memory, subagents, dashboards, and a graph nobody can debug. Then they wonder why the agent is expensive, confused, and unreliable. The better order is simple: harness first loop second graph only when needed A harness gives the model a workspace, tools, permissions, logs, and a definition of done. A loop lets it try, fail, read feedback, repair, and stop. A graph only makes sense when the workflow branches: approvals, parallel work, durable state, different routes, restart recovery. A graph is not a smarter prompt. A loop is not a production system. A harness is not just a system prompt. Most agents do not fail because the model is weak. They fail because nobody defined what success means.

MOST PEOPLE BUILD AI AGENTS BACKWARDS. They start with prompts, then add tools, memory, subagents, dashboards, and a graph nobody can debug. Then they wonder why the agent is expensive, confused, and unreliable. The better order is simple: harness first loop second graph only when needed A harness gives the model a workspace, tools, permissions, logs, and a definition of done. A loop lets it try, fail, read feedback, repair, and stop. A graph only makes sense when the workflow branches: approvals, parallel work, durable state, different routes, restart recovery. A graph is not a smarter prompt. A loop is not a production system. A harness is not just a system prompt. Most agents do not fail because the model is weak. They fail because nobody defined what success means.

Fluixo

12,252 次观看 • 3 个月前

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

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

rari

33,537 次观看 • 2 个月前

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

codila

17,040 次观看 • 3 个月前