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.

Everyone is saying “it’s the harness, not the model.” But...no one is really explaining what that means. I wanted to understand harness engineering better, so on today's episode of How I AI, I built my own: a custom harness using ClaudeDevs SDK to triage Sentry bugs, verify root cause,... show more

claire vo 🖤

61,074 subscribers

40,289 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Google Brain founder Andrew Ng: "Prompting will die in 7 months Harnesses are what's replacing it" Prompts → Agents → Harness → Loops → Graphs → Self-Improving Systems In just 97 minutes, Andrew shows how to build a harness that lets agents plan, execute, verify, and improve on their own A harness → Loads the right context → Routes each task → Checks the result → Triggers the next step Most people are still perfecting prompts while AI engineering is already moving into the harness Watch it today Then save the full guide on harness engineering below ↓

Google Brain founder Andrew Ng: "Prompting will die in 7 months Harnesses are what's replacing it" Prompts → Agents → Harness → Loops → Graphs → Self-Improving Systems In just 97 minutes, Andrew shows how to build a harness that lets agents plan, execute, verify, and improve on their own A harness → Loads the right context → Routes each task → Checks the result → Triggers the next step Most people are still perfecting prompts while AI engineering is already moving into the harness Watch it today Then save the full guide on harness engineering below ↓

Mori

84,849 views • 6 days ago

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

45,093 views • 2 months ago

OpenAI engineer: "Nobody on my team has touched code in 9 months. Agents write all the code, the way you do it is harness engineering." In 45 minutes he breaks down exactly how to build the setup so agents do the full job without you in the loop. This beats any paid course on building agents I've seen. Watch it, then read the full guide on harness engineering below.

OpenAI engineer: "Nobody on my team has touched code in 9 months. Agents write all the code, the way you do it is harness engineering." In 45 minutes he breaks down exactly how to build the setup so agents do the full job without you in the loop. This beats any paid course on building agents I've seen. Watch it, then read the full guide on harness engineering below.

Anatoli Kopadze

25,360 views • 2 months ago

Anthropic Technical Staff Jess Yan says the harness and the model cannot be pulled apart without giving up performance, though she flags her own bias. "I think I am quite biased but I also think that it is impossible to get the maximum possible performance without tying together the harness and the model." "Now the components of the harness and maybe the thickness of the harness will change over time as models get more and more capable." "However, when we test our models and when we are assessing their performance we always have to test it in conjunction with a harness." "And are we going to test it with all the different harnesses of the world? We're going to select the harnesses that we have built." "And so there is an aspect of the necessity of building models is that you have to be testing them with harnesses, and that sort of keeps them paired together."

Anthropic Technical Staff Jess Yan says the harness and the model cannot be pulled apart without giving up performance, though she flags her own bias. "I think I am quite biased but I also think that it is impossible to get the maximum possible performance without tying together the harness and the model." "Now the components of the harness and maybe the thickness of the harness will change over time as models get more and more capable." "However, when we test our models and when we are assessing their performance we always have to test it in conjunction with a harness." "And are we going to test it with all the different harnesses of the world? We're going to select the harnesses that we have built." "And so there is an aspect of the necessity of building models is that you have to be testing them with harnesses, and that sort of keeps them paired together."

Fireside Alpha

584,074 views • 2 months ago

The entire AI industry is racing to build the smartest model. Satya Nadella just admitted that is not where the money is. The model is not the product. The harness is. That is the exact line. And it changes what Microsoft is actually competing on. OpenAI, Anthropic, Google, xAI, Meta every frontier lab is pouring hundreds of billions into training compute, chasing the next capability jump. Each betting that raw model intelligence is the moat. Microsoft is doing the opposite. It is building the harness the orchestration layer that sits above the model, connecting it to tools, data, permissions, sub-agents, and enterprise workflows. And it is letting OpenAI, Anthropic, and MAI compete to plug into it. "You need the model. But the model is not the product. The harness is." So do the math on what a harness actually does. A raw model dropped into an enterprise answers questions. That is a chatbot. A harness turns that same model into an agent that reads the SharePoint, edits the ERP entry, pulls the GitHub PR, updates Salesforce, and files the Excel report with the right permissions, the right audit trail, and the right sub-agent for each sub-task. The model provides the intelligence. The harness converts intelligence into work. Now here's where it gets interesting. "Even the best model in the world will feel broken without a great harness. And an okay model with a great harness can feel like magic." If that is true, the enterprise buyer is not buying model quality. The enterprise buyer is buying the harness. Which means model quality becomes a commodity input over time, and harness quality becomes the sustainable moat. Compare that to the strategy the entire frontier lab industry is executing. Everyone else is chasing the numerator raw intelligence. Almost nobody at scale is racing to build the denominator the orchestration layer that determines whether that intelligence can actually be deployed profitably inside a real company. The frontier model race has a 10 to 20 percent chance of producing a single dominant winner. Nadella just told the industry he does not need to be that winner. If OpenAI wins, Microsoft wins. If Anthropic wins, Microsoft wins. If MAI wins, Microsoft wins. If someone Microsoft has never heard of trains a better model in 2027, Microsoft still wins. Because the compute they train on, the harness they get plugged into, the enterprise contracts they get delivered through, and the products they sit inside are all Microsoft. He is not building the best AI model. He is building the layer that the best AI model has to run on to make anyone money. I wonder which position looks more valuable in ten years.

The entire AI industry is racing to build the smartest model. Satya Nadella just admitted that is not where the money is. The model is not the product. The harness is. That is the exact line. And it changes what Microsoft is actually competing on. OpenAI, Anthropic, Google, xAI, Meta every frontier lab is pouring hundreds of billions into training compute, chasing the next capability jump. Each betting that raw model intelligence is the moat. Microsoft is doing the opposite. It is building the harness the orchestration layer that sits above the model, connecting it to tools, data, permissions, sub-agents, and enterprise workflows. And it is letting OpenAI, Anthropic, and MAI compete to plug into it. "You need the model. But the model is not the product. The harness is." So do the math on what a harness actually does. A raw model dropped into an enterprise answers questions. That is a chatbot. A harness turns that same model into an agent that reads the SharePoint, edits the ERP entry, pulls the GitHub PR, updates Salesforce, and files the Excel report with the right permissions, the right audit trail, and the right sub-agent for each sub-task. The model provides the intelligence. The harness converts intelligence into work. Now here's where it gets interesting. "Even the best model in the world will feel broken without a great harness. And an okay model with a great harness can feel like magic." If that is true, the enterprise buyer is not buying model quality. The enterprise buyer is buying the harness. Which means model quality becomes a commodity input over time, and harness quality becomes the sustainable moat. Compare that to the strategy the entire frontier lab industry is executing. Everyone else is chasing the numerator raw intelligence. Almost nobody at scale is racing to build the denominator the orchestration layer that determines whether that intelligence can actually be deployed profitably inside a real company. The frontier model race has a 10 to 20 percent chance of producing a single dominant winner. Nadella just told the industry he does not need to be that winner. If OpenAI wins, Microsoft wins. If Anthropic wins, Microsoft wins. If MAI wins, Microsoft wins. If someone Microsoft has never heard of trains a better model in 2027, Microsoft still wins. Because the compute they train on, the harness they get plugged into, the enterprise contracts they get delivered through, and the products they sit inside are all Microsoft. He is not building the best AI model. He is building the layer that the best AI model has to run on to make anyone money. I wonder which position looks more valuable in ten years.

Vikram M

21,463 views • 3 months ago

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

51,536 views • 23 days ago

Buzz is Slack where the agents are teammates instead of integrations. Here's what that unlocks: Agents: - The ones you start with are just defaults - Edit them, add your own, write their instructions like a system prompt Swappable Harness: - This is the killer feature - Swap Claude Code, Codex, Goose under the same agent Context: - Every chat you've had with that agent carries over to the new harness - Global skills and skill files come too Think: Slack = the shape Agents = the teammates Harness = the engine you can change without losing anything "I get model fatigue" is a real thing. Buzz sits one layer above it.

Buzz is Slack where the agents are teammates instead of integrations. Here's what that unlocks: Agents: - The ones you start with are just defaults - Edit them, add your own, write their instructions like a system prompt Swappable Harness: - This is the killer feature - Swap Claude Code, Codex, Goose under the same agent Context: - Every chat you've had with that agent carries over to the new harness - Global skills and skill files come too Think: Slack = the shape Agents = the teammates Harness = the engine you can change without losing anything "I get model fatigue" is a real thing. Buzz sits one layer above it.

The Startup Ideas Podcast (SIP) 🧃

43,523 views • 2 months ago

What it's like being on Omarchy. Basically your agents can control the whole OS experience, shape it to be how you want. I setup a plugin that takes compute you have and plugs it into your preferred harness. I need to run this on dgx sparks /,:

What it's like being on Omarchy. Basically your agents can control the whole OS experience, shape it to be how you want. I setup a plugin that takes compute you have and plugs it into your preferred harness. I need to run this on dgx sparks /,:

0xSero

19,459 views • 13 days ago

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

Jason Zhou

66,979 views • 2 months ago

We just crossed $10M in ARR at Chatbase! 🎉 🎉 And today, we're launching Chatbase as the full harness for customer-facing AI agents. Similar to how Claude code is a harness for coding agents, Chatbase is the harness for customer experience agents. That means we give the model the context, tools, workflows, guardrails, and human-in-the-loop systems to be the best ambassador for your brand. It's going beyond just solving issues and is giving your customers the best experiences across every channel. This is a milestone I have been thinking about and obsessed with since day 1, and I am super excited to bring my vision for customer facing agents to life with Chatbase. Thank you to every one of our customers and to the amazing Chatbase team for getting us here! Next stop: $100M ARR

Yasser

852,867 views • 4 months ago

🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Schott fks CEO of HTML has launched Flue: The Agent Harness Framework for TypeScript. It brings programmable harness right into your agents rather than DIY plumbing. Python ecosystem already has 🦾 powerful AI/ML tools and frameworks and research initiatives but most frameworks asked users to build your own harness. Superagentic AI bringing this concept of Flue to Python 🐍 ecosystem. Here is PyFlue even even better 🤖 Agent = Model 💻 + Harness 🧰 + Memory 🧠 Almost all the feature of Flue plugged with LangChain Deepagents harness built by Harrison Chase and team Viv Sydney Runkle and more coming soon. 👉 Stop building agent loops, start using a harness. 💻 Try PyFlue Now : ⭐️ GitHub: 📚Docs: 📙 Blog Post: #HarnessEngineering #AgentHarnesses

🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Schott fks CEO of HTML has launched Flue: The Agent Harness Framework for TypeScript. It brings programmable harness right into your agents rather than DIY plumbing. Python ecosystem already has 🦾 powerful AI/ML tools and frameworks and research initiatives but most frameworks asked users to build your own harness. Superagentic AI bringing this concept of Flue to Python 🐍 ecosystem. Here is PyFlue even even better 🤖 Agent = Model 💻 + Harness 🧰 + Memory 🧠 Almost all the feature of Flue plugged with LangChain Deepagents harness built by Harrison Chase and team Viv Sydney Runkle and more coming soon. 👉 Stop building agent loops, start using a harness. 💻 Try PyFlue Now : ⭐️ GitHub: 📚Docs: 📙 Blog Post: #HarnessEngineering #AgentHarnesses

Shashi

69,884 views • 5 months ago

this is huge news from Cursor, they've pulled of the impossible and turned their ai-wrapper into a in-destructible moat sam altman literally called it cursor's ai agent harness is available for anyone to build on, which means ai models are now a commodity > 1-time install and now anyone can run cursor's agent locally or via cloud. use any model (e.g. gpt 5.5) but with the added cursor harness that makes it 10X better. > its so good that 3 of cursors biggest competitors are embedding it into their products. > now cursor DOESN'T DEPEND on anthropic or openai. their own model (composer 2) competes directly! yesterday sam altman said the ai model and harness are one and the same and today cursor turned their harness into a self-owned moat fucking masterclass (coming from a former cursor / ai wrapper hater)

this is huge news from Cursor, they've pulled of the impossible and turned their ai-wrapper into a in-destructible moat sam altman literally called it cursor's ai agent harness is available for anyone to build on, which means ai models are now a commodity > 1-time install and now anyone can run cursor's agent locally or via cloud. use any model (e.g. gpt 5.5) but with the added cursor harness that makes it 10X better. > its so good that 3 of cursors biggest competitors are embedding it into their products. > now cursor DOESN'T DEPEND on anthropic or openai. their own model (composer 2) competes directly! yesterday sam altman said the ai model and harness are one and the same and today cursor turned their harness into a self-owned moat fucking masterclass (coming from a former cursor / ai wrapper hater)

Ejaaz

950,452 views • 5 months ago

She claims that her neighbors are hard-core Trump supporters. "So one of my neighbors is walking her dog and I said hello." "I happened to see that the dog had a harness that said Trump For America." Do you believe anything she is saying in this video?

She claims that her neighbors are hard-core Trump supporters. "So one of my neighbors is walking her dog and I said hello." "I happened to see that the dog had a harness that said Trump For America." Do you believe anything she is saying in this video?

Brandon

32,519 views • 5 months ago

The next billion-dollar AI companies won’t be built around an LLM. They’ll be built around the HARNESS. Everyone is asking: “Which AI model should I use?” I think that’s the wrong question. An LLM is like a wild black stallion—immensely powerful, constantly improving, but running free. The opportunity is building the harness that lets you control that power and actually win the horse race. Your AI application shouldn’t be the model. It should orchestrate models. Claude today. GPT tomorrow. Gemini, Grok, Qwen, or whatever comes next. Swap the engine without rebuilding the car. Crypto already taught us this lesson. People interact with things like USDC and Tether without caring nearly as much which underlying blockchain happens to settle the transaction. The application layer abstracts the infrastructure. AI is heading the same direction. LLMs are infrastructure. The harness is the product. The winners will build AI harnesses around real human problems—businesses, workflows, coding, research, finance, education, everyday life—and make the underlying intelligence interchangeable. Everyone is trying to capture this incredibly powerful new thing called AI. Stop trying to build a better horse. Build the harness that lets you ride any horse. 🐎🤖 I just made a video explaining why I think this is where some of the biggest opportunities in AI are hiding.

The next billion-dollar AI companies won’t be built around an LLM. They’ll be built around the HARNESS. Everyone is asking: “Which AI model should I use?” I think that’s the wrong question. An LLM is like a wild black stallion—immensely powerful, constantly improving, but running free. The opportunity is building the harness that lets you control that power and actually win the horse race. Your AI application shouldn’t be the model. It should orchestrate models. Claude today. GPT tomorrow. Gemini, Grok, Qwen, or whatever comes next. Swap the engine without rebuilding the car. Crypto already taught us this lesson. People interact with things like USDC and Tether without caring nearly as much which underlying blockchain happens to settle the transaction. The application layer abstracts the infrastructure. AI is heading the same direction. LLMs are infrastructure. The harness is the product. The winners will build AI harnesses around real human problems—businesses, workflows, coding, research, finance, education, everyday life—and make the underlying intelligence interchangeable. Everyone is trying to capture this incredibly powerful new thing called AI. Stop trying to build a better horse. Build the harness that lets you ride any horse. 🐎🤖 I just made a video explaining why I think this is where some of the biggest opportunities in AI are hiding.

Jared Tate ©️

10,118 views • 1 month ago

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Y Combinator

61,650 views • 7 months ago

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced 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 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced 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 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Akshay 🚀

355,545 views • 13 days ago

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 ↓

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 ↓

Annatar.md

78,941 views • 26 days ago

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

11,923 views • 2 months ago

I asked Jacque Vaughn what the biggest challenge of trying to harness Cam Thomas’ elite scoring at the NBA level has been: “I wish the score was 134 Brooklyn Nets, 105 Philadelphia. I think that part helps. The goal is you win as a team. So 46 points is great but we end up losing by 30. So you’ve got to attach those together. How do you marry the 29 shots to being a productive teammate where you might not get that amount of shots in a typical game? That’s the question. So can you harness and take that ability and be able to do it in the shorter amount of time? In a more efficient time? And in a setting that it benefits the entire team? That’s the challenge.”

I asked Jacque Vaughn what the biggest challenge of trying to harness Cam Thomas’ elite scoring at the NBA level has been: “I wish the score was 134 Brooklyn Nets, 105 Philadelphia. I think that part helps. The goal is you win as a team. So 46 points is great but we end up losing by 30. So you’ve got to attach those together. How do you marry the 29 shots to being a productive teammate where you might not get that amount of shots in a typical game? That’s the question. So can you harness and take that ability and be able to do it in the shorter amount of time? In a more efficient time? And in a setting that it benefits the entire team? That’s the challenge.”

Erik Slater

1,718,330 views • 3 years ago

I have been annoying a lot of people about how cool I think the Siri AI harness and architecture is recently, so while I work on the proper video/report, I made this quick messy screen recording explaining it! Hopefully it's of interest to some!

I have been annoying a lot of people about how cool I think the Siri AI harness and architecture is recently, so while I work on the proper video/report, I made this quick messy screen recording explaining it! Hopefully it's of interest to some!

Max Weinbach

74,999 views • 3 months ago