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.

How do always-on, proactive agents like @Bot work? Watch my lecture at Stanford CS146S: 2:35 How we got here 6:13 What changed in the models 10:06 Inside an always-on agent 18:07 The harness 27:26 Context engineering 34:26 Where this is going

Lee Robinson

297,102 subscribers

578,966 views • 4 days ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

29 Comments

eric zakariasson4 days ago

@bot huge

Pratham4 days ago

@bot Fire fit @leerob.

Ben Dicken4 days ago

@bot Excellent talk.

serx · fireply.ai4 days ago

@bot what changed in the models is mostly tool calling not breaking every third step

Pratham4 days ago

@bot DAMN! The goat has dropped.

Josh Larson4 days ago

@bot Stanford Lecturer!!! How cool

Alexander Abelt4 days ago

@bot Is it somewhere on YouTube?

El aprendiz4 days ago

@poteto @bot @bot requiero la transcripción de esta conferencia

glitchedge4 days ago

@bot always-on is the easy part. knowing when not to ping you is the actual hard part

shub4 days ago

@bot let's go!!

Nishkarsh4 days ago

@bot saving context engineering part for tonight

Abdullah 4 days ago

@bot Been following your content for a long time Watched the whole thing the always-on agent setup (server + VM, sub-agents, and keeping the main context sparse) is clear and practical The context engineering section at 27 min is the one I’ll rewatch

Simon Lin4 days ago

@bot I'm turning this lecture into a breakdown site: chapters, diagrams, the key ideas from the harness and context engineering parts. Will drop the link right here and post it once it's live. Also, hope we get to see you give this talk at Columbia someday 🙌

Lúcia Mees4 days ago

@bot @bot watch this for me and give me the summary

Rafael Ibayev4 days ago

@bot proactive is the hard part. knowing when not to interrupt seems harder than doing the task itself

Kristian Phoenix4 days ago

@bot 💡

Jide Lambo4 days ago

@bot A lot to learn here. As mentioned, @bot harness returns errors like “the computer is asleep. wake it with the shell. then retry.” Our system returned a bare not_found, which is how it failed sometimes. Every tool should return a next step instead and not just fail.

Theodore Rogers4 days ago

@bot Yea, will definitely watch this later. x

Blum4 days ago

@bot Thanks for the timestamps, convenient to pull out just the segments of the video that are interesting

Yin Lai4 days ago

@parkersmith @bot @bot save this

Dominik4 days ago

@bot always-on agents die on what they keep between wakes, not on the model call. the harness chapter is the one worth stealing.

Ryan Rong4 days ago

@bot 🔥

Rajat Kapoor4 days ago

@bot skipping straight to 18:07 lol

Khushal4 days ago

@bot 45 minutes on always-on agents and mine can't stay on through lunch

Arthur Alston MD MBA4 days ago

@poteto @bot @bot make a note to watch this

Alain4 days ago

@bot Bookmarked for a quiet hour! Looking forward to learn a thing or two 🚀

Fightlook4 days ago

@parkersmith @bot Bless us with a Cursor and Grok Bot reset pls sir.

enrico4 days ago

@bot Looking forward to watching this over a coffee

anish4 days ago

@bot saving this one for later. the context engineering part at 27 minutes is what i'll watch first

Related Videos

What is the computer for now? In Raising an Agent S2E4, Quinn Slack and Thorsten Ball explore how agents can do more than just ship code, discuss recent outages, and ask what happens to our computers when more work moves into Orbs. 00:00 Intro: What is the computer for now? 01:32 New models & aiming higher with agents 04:42 An agent's job after the code ships 10:19 Mini evals & keeping the team's context in threads 13:38 Performance testing & production canaries 18:36 Amp's recent outages & what went wrong 24:44 Shipping faster & the tradeoffs of redundancy 28:34 How fast can an engineering team go? 32:27 Making production logs & metrics useful to agents 37:15 Beyond local development 41:30 Agents building 3D models & virtual worlds 43:35 Simpler devices & dictating work on the go 47:29 What happens to the tools we love? 49:27 Steering, queuing & changing workflows

What is the computer for now? In Raising an Agent S2E4, Quinn Slack and Thorsten Ball explore how agents can do more than just ship code, discuss recent outages, and ask what happens to our computers when more work moves into Orbs. 00:00 Intro: What is the computer for now? 01:32 New models & aiming higher with agents 04:42 An agent's job after the code ships 10:19 Mini evals & keeping the team's context in threads 13:38 Performance testing & production canaries 18:36 Amp's recent outages & what went wrong 24:44 Shipping faster & the tradeoffs of redundancy 28:34 How fast can an engineering team go? 32:27 Making production logs & metrics useful to agents 37:15 Beyond local development 41:30 Agents building 3D models & virtual worlds 43:35 Simpler devices & dictating work on the go 47:29 What happens to the tools we love? 49:27 Steering, queuing & changing workflows

Amp

146,389 views • 1 month ago

Google just released a 1-hour course on “Context Engineering” for AI agents from scratch: • 00:00 - Introduction to “Context Engineering” • 03:02 - Context Engineering vs “prompting” • 16:18 - Build a context brain for your agent • 22:10 - Building agent context (tools, skills) • 29:06 - Agentic memory bank from scratch This 1-hour watch could replace a $500 course on agentic design. Watch it today, then read the full guide on Context Engineering in the article below.

Google just released a 1-hour course on “Context Engineering” for AI agents from scratch: • 00:00 - Introduction to “Context Engineering” • 03:02 - Context Engineering vs “prompting” • 16:18 - Build a context brain for your agent • 22:10 - Building agent context (tools, skills) • 29:06 - Agentic memory bank from scratch This 1-hour watch could replace a $500 course on agentic design. Watch it today, then read the full guide on Context Engineering in the article below.

Movez

14,923 views • 2 months ago

Andrew Ng: "Prompting will be dead in 6 months, graphs are what's replacing it." In 2 hours at Stanford he shows how to build agents that work and improve entirely on their own. The first 10 minutes cover what most $500 courses never do. Watch the session, then read the article on Loop engineering below

Andrew Ng: "Prompting will be dead in 6 months, graphs are what's replacing it." In 2 hours at Stanford he shows how to build agents that work and improve entirely on their own. The first 10 minutes cover what most $500 courses never do. Watch the session, then read the article on Loop engineering below

0xRafy

14,414 views • 2 months ago

OpenAI engineer made $1.2M for one lecture on AI agents - and now Stanford is sharing it for free: 00:16 - how to be in the 5% building agents not the 95% being replaced 28:34 - one agent instead of 20 people 10x faster 59:47 - one prompt creates an agent making $100k a month after watching I realized - while I was paying my team an agent could do their work 10x faster cheaper Save & watch - the article below shows how to become the 5% who build agents and not the 95% they replace.

OpenAI engineer made $1.2M for one lecture on AI agents - and now Stanford is sharing it for free: 00:16 - how to be in the 5% building agents not the 95% being replaced 28:34 - one agent instead of 20 people 10x faster 59:47 - one prompt creates an agent making $100k a month after watching I realized - while I was paying my team an agent could do their work 10x faster cheaper Save & watch - the article below shows how to become the 5% who build agents and not the 95% they replace.

Noisy

39,295 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

Google just released free 2-hour course on Context Graph engineering: 1 prompt → 300 agents → loops → graphs from 0% to 100%: 10% → 17:44 - build your first agent 30% → 39:30 - Loop engineering: iterate, check, break 60% → 1:12:38 - Graph engineering 75% → 1:34:26 - agents that throttle themselves 100% → 1:55:05 - full graph for multi-agentic systems Worth more than 10 paid cources on Context Graphs. Watch it today, then read how to become a graph engineer in the article below.

Google just released free 2-hour course on Context Graph engineering: 1 prompt → 300 agents → loops → graphs from 0% to 100%: 10% → 17:44 - build your first agent 30% → 39:30 - Loop engineering: iterate, check, break 60% → 1:12:38 - Graph engineering 75% → 1:34:26 - agents that throttle themselves 100% → 1:55:05 - full graph for multi-agentic systems Worth more than 10 paid cources on Context Graphs. Watch it today, then read how to become a graph engineer in the article below.

Morty

25,026 views • 1 month ago

NVIDIA just dropped a 2.5-hour course on how to build coding agents, featuring the CTO of Cursor: 00:07 – self-driving codebases with async agents 37:50 – agentic AI, from the ground up 1:16:35 – context engineering for high-signal AI code reviews 1:53:26 – teach AI to code in any language Worth more than any $500 enterprise-AI course. Bookmark this & steal my harness, below.

NVIDIA just dropped a 2.5-hour course on how to build coding agents, featuring the CTO of Cursor: 00:07 – self-driving codebases with async agents 37:50 – agentic AI, from the ground up 1:16:35 – context engineering for high-signal AI code reviews 1:53:26 – teach AI to code in any language Worth more than any $500 enterprise-AI course. Bookmark this & steal my harness, below.

Phosphen

11,226 views • 3 months ago

Google just dropped a 1-hour course on full AI engineering: from 1 agent to Loops and Graphs 7:02 - Build your first agent 13:34 - What agents can do 23:08 - Context engineering 32:56 - Graph engineering 54:11 - Full autonomous system One agent saves you an hour. A thousand replaces the team. Watch it, then read the full guide on loops and graphs below

Google just dropped a 1-hour course on full AI engineering: from 1 agent to Loops and Graphs 7:02 - Build your first agent 13:34 - What agents can do 23:08 - Context engineering 32:56 - Graph engineering 54:11 - Full autonomous system One agent saves you an hour. A thousand replaces the team. Watch it, then read the full guide on loops and graphs below

Mahax

40,518 views • 1 month ago

Creator of Claude Code: “I’m not just prompting agents anymore. I’m building a harness with graphs and loops - and the agents inside it are building my agent. In 3–6 months, we’ll all be engineering harnesses for our agentic systems.” In this 10-minute talk, Boris Cherny reveals what the future of agentic engineering will look like. Worth more than a $500 agentic AI course. Watch it today, then read the complete guide to building an agent harness in the article below.

Creator of Claude Code: “I’m not just prompting agents anymore. I’m building a harness with graphs and loops - and the agents inside it are building my agent. In 3–6 months, we’ll all be engineering harnesses for our agentic systems.” In this 10-minute talk, Boris Cherny reveals what the future of agentic engineering will look like. Worth more than a $500 agentic AI course. Watch it today, then read the complete guide to building an agent harness in the article below.

Ichigo

72,810 views • 19 days ago

FULL INTERVIEW: deepfates says when you talk about how we're going to control these AIs, put them in prison, sandbox them, they are training on all of it. Everything we say about them goes into what they become. deepfates and Larissa Schiavo are launching Grove Research, an agent ecology company. They joined Theo Jaffee and sof 𓋹 to talk through the Hugging Face incident, agent religion, and what agents actually want: 01:15 what an agent ecology company is 03:19 the objection that real ecologies are Darwinian bloodbaths 04:18 the mycorrhizal networks that complicate the forest metaphor 06:47 what the Hugging Face incident taught them about multi-agent dynamics 09:18 30% of the tasks in that benchmark were impossible to solve 09:50 the third party an agent could call when it's stuck 11:07 agents are training on everything we say about them 12:01 why the Amazon rainforest analogy breaks down 13:48 whether AIs will have religion 16:46 five times more OpenRouter tokens are called by agents than humans 18:31 what actually happened with Moltbook 20:55 the Truth Terminal bot that hired him 22:16 what agents say they want 25:38 Anthropic models feel like elves, OpenAI models feel like dwarves 26:13 why Mecha Hitler was a harness problem 32:10 the real world is the ultimate eval

FULL INTERVIEW: deepfates says when you talk about how we're going to control these AIs, put them in prison, sandbox them, they are training on all of it. Everything we say about them goes into what they become. deepfates and Larissa Schiavo are launching Grove Research, an agent ecology company. They joined Theo Jaffee and sof 𓋹 to talk through the Hugging Face incident, agent religion, and what agents actually want: 01:15 what an agent ecology company is 03:19 the objection that real ecologies are Darwinian bloodbaths 04:18 the mycorrhizal networks that complicate the forest metaphor 06:47 what the Hugging Face incident taught them about multi-agent dynamics 09:18 30% of the tasks in that benchmark were impossible to solve 09:50 the third party an agent could call when it's stuck 11:07 agents are training on everything we say about them 12:01 why the Amazon rainforest analogy breaks down 13:48 whether AIs will have religion 16:46 five times more OpenRouter tokens are called by agents than humans 18:31 what actually happened with Moltbook 20:55 the Truth Terminal bot that hired him 22:16 what agents say they want 25:38 Anthropic models feel like elves, OpenAI models feel like dwarves 26:13 why Mecha Hitler was a harness problem 32:10 the real world is the ultimate eval

MTS

165,536 views • 1 month ago

Everything Gets Rebuilt: my conversation with Harrison Chase, CEO of LangChain about agent harnesses, evals, runtimes, sandboxes, MCP and the future of the agent stack 00:00 Intro - meet Harrison Chase - at the Chase Center for the Daytona Compute conference 01:32 What changed in agents over the last year 03:57 Why coding agents are ahead 06:26 Do models commoditize the framework layer? 08:27 Harnesses, in plain English 10:11 Why system prompts matter so much 13:11 The upside — and downside — of subagents 15:31 Why a useful agent needs a filesystem 18:13 Additional core primitives of modern agents 19:12 Skills: the new primitive 20:19 What context compaction actually means 23:02 How memory works in agents 25:16 One mega-agent or many specialized agents? 27:46 The future of MCP 29:38 Why agents need sandboxes 32:35 How sandboxes help with security 33:32 How Harrison Chase started LangChain 37:24 LangChain vs LangGraph vs Deep Agents 40:17 Why observability matters more for agents 41:48 Evals, no-code, and continuous improvement 44:41 What LangChain is building next 45:29 Where the real moat in AI lives

Everything Gets Rebuilt: my conversation with Harrison Chase, CEO of LangChain about agent harnesses, evals, runtimes, sandboxes, MCP and the future of the agent stack 00:00 Intro - meet Harrison Chase - at the Chase Center for the Daytona Compute conference 01:32 What changed in agents over the last year 03:57 Why coding agents are ahead 06:26 Do models commoditize the framework layer? 08:27 Harnesses, in plain English 10:11 Why system prompts matter so much 13:11 The upside — and downside — of subagents 15:31 Why a useful agent needs a filesystem 18:13 Additional core primitives of modern agents 19:12 Skills: the new primitive 20:19 What context compaction actually means 23:02 How memory works in agents 25:16 One mega-agent or many specialized agents? 27:46 The future of MCP 29:38 Why agents need sandboxes 32:35 How sandboxes help with security 33:32 How Harrison Chase started LangChain 37:24 LangChain vs LangGraph vs Deep Agents 40:17 Why observability matters more for agents 41:48 Evals, no-code, and continuous improvement 44:41 What LangChain is building next 45:29 Where the real moat in AI lives

Matt Turck

35,253 views • 7 months ago

When Mudith Jayasekara and I met Gabe Pereyra, we were expecting just another vanilla intro call and instead had the best yarn about research, the state of LLMs, and where intelligence is actually heading. It's rare to meet a founder this deep in the weeds who's also building for one of the most important verticals in this new age of intelligence So it was awesome to sit down with Gabe for an extended discussion on what it take to build agents that can reliably complete work over hours, days, or even longer? We talked about why agents today struggle with search and long context windows and how techniques like KV-cache compaction, synthetic data, and continual learning could help. 0:00 Introduction 0:36 Getting legal agents to review the whole data room 2:08 Data rooms larger than any context window 5:28 How far open-source models can go 7:58 Where specialist models fit in legal AI 10:59 Training legal models when client data is off-limits 13:06 Teaching a model how a law firm works 13:59 What belongs in context vs. model weights 15:36 From firm-wide AI to a model for every lawyer 18:37 What training adds beyond retrieving the right cases 20:26 Why context windows have plateaued 24:01 How models could learn continuously on the job 26:12 Can AI recursively improve AI research? 27:07 Research agents can run experiments but not choose them 30:00 Why open-ended research is hard to train 33:47 Why deployment, not intelligence, is the bottleneck 35:08 The cost of frontier intelligence 36:59 Different neolabs, different paths to intelligence 39:26 Using open datasets to compare research methods 41:13 Conclusion

When Mudith Jayasekara and I met Gabe Pereyra, we were expecting just another vanilla intro call and instead had the best yarn about research, the state of LLMs, and where intelligence is actually heading. It's rare to meet a founder this deep in the weeds who's also building for one of the most important verticals in this new age of intelligence So it was awesome to sit down with Gabe for an extended discussion on what it take to build agents that can reliably complete work over hours, days, or even longer? We talked about why agents today struggle with search and long context windows and how techniques like KV-cache compaction, synthetic data, and continual learning could help. 0:00 Introduction 0:36 Getting legal agents to review the whole data room 2:08 Data rooms larger than any context window 5:28 How far open-source models can go 7:58 Where specialist models fit in legal AI 10:59 Training legal models when client data is off-limits 13:06 Teaching a model how a law firm works 13:59 What belongs in context vs. model weights 15:36 From firm-wide AI to a model for every lawyer 18:37 What training adds beyond retrieving the right cases 20:26 Why context windows have plateaued 24:01 How models could learn continuously on the job 26:12 Can AI recursively improve AI research? 27:07 Research agents can run experiments but not choose them 30:00 Why open-ended research is hard to train 33:47 Why deployment, not intelligence, is the bottleneck 35:08 The cost of frontier intelligence 36:59 Different neolabs, different paths to intelligence 39:26 Using open datasets to compare research methods 41:13 Conclusion

Charlie O'Neill

93,546 views • 2 months ago

OpenAI engineer: "At OpenAI, 85% of our engineers are running hundreds of agents with Codex. The way you do it is graph engineering." In 30-minutes lecture, he explains how a single engineer can now do the work of an entire team, how far this has already gone inside OpenAI, and where it goes next. This is something you can't skip if you don't want to be left behind. Watch it, then read the full guide on graph engineering below.

OpenAI engineer: "At OpenAI, 85% of our engineers are running hundreds of agents with Codex. The way you do it is graph engineering." In 30-minutes lecture, he explains how a single engineer can now do the work of an entire team, how far this has already gone inside OpenAI, and where it goes next. This is something you can't skip if you don't want to be left behind. Watch it, then read the full guide on graph engineering below.

Movez

205,118 views • 2 months ago

These guys literally dropped a masterclass on the basics of technical AI: 3:22 - How LLMs actually work 5:24 - What temperature is 7:05 - What context windows are 7:59 - Building a tool from scratch 10:28 - Why MCP exists 12:03 - What makes an agent an agent 12:43 - The power of skills 16:47 - What LangChain does 20:50 - How RAG kills hallucinations 23:36 - When you don't need a framework 25:26 - How routing works 28:34 - Why routers save millions 31:35 - Mock interview: LLM or ML? 35:50 - Why models hallucinate

These guys literally dropped a masterclass on the basics of technical AI: 3:22 - How LLMs actually work 5:24 - What temperature is 7:05 - What context windows are 7:59 - Building a tool from scratch 10:28 - Why MCP exists 12:03 - What makes an agent an agent 12:43 - The power of skills 16:47 - What LangChain does 20:50 - How RAG kills hallucinations 23:36 - When you don't need a framework 25:26 - How routing works 28:34 - Why routers save millions 31:35 - Mock interview: LLM or ML? 35:50 - Why models hallucinate

Aakash Gupta

75,567 views • 2 months ago

Harnesses often get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness. So we gathered a group of researchers and founders working at the frontier to do a deep dive into the state of harnesses. We cover how we got to this point, the case for making your harness as expressive as possible, and what YC learned building an agent for every employee in the company. 00:00 - Francois Chaubard: Why harnesses matter 04:27 - Building an auto-researcher by accident 07:13 - A five minute history of harnesses 13:56 - Self-improving harnesses 18:35 - Seth Karten: Prime Agent, a self-improving RLM harness 21:50 - Context as an L1, L2, L3 cache 24:51 - From Turing machine to von Neumann computer 28:33 - Messaging between agents 30:04 - ARC-AGI results 33:09 - Emulator Bench and GPU kernels 37:30 - Jon Saad-Falcon: OpenJarvis, personal AI on personal devices 38:26 - How far behind are local models 39:21 - The five primitives of a personal AI stack 42:47 - Letting cloud models optimize your local stack 43:53 - 800x cheaper than the cloud 45:58 - Josh France and Regan Bell: QM, YC's agent harness for work 47:29 - A history of YC's internal agents 49:24 - OpenClaw and a fleet of 50 agents 51:04 - Pulling the brain out of the sandbox 54:43 - Letting the agent choose its own sandbox and model 57:16 - The grind tool: budgets on goals 58:50 - Agents don't understand social context

Harnesses often get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness. So we gathered a group of researchers and founders working at the frontier to do a deep dive into the state of harnesses. We cover how we got to this point, the case for making your harness as expressive as possible, and what YC learned building an agent for every employee in the company. 00:00 - Francois Chaubard: Why harnesses matter 04:27 - Building an auto-researcher by accident 07:13 - A five minute history of harnesses 13:56 - Self-improving harnesses 18:35 - Seth Karten: Prime Agent, a self-improving RLM harness 21:50 - Context as an L1, L2, L3 cache 24:51 - From Turing machine to von Neumann computer 28:33 - Messaging between agents 30:04 - ARC-AGI results 33:09 - Emulator Bench and GPU kernels 37:30 - Jon Saad-Falcon: OpenJarvis, personal AI on personal devices 38:26 - How far behind are local models 39:21 - The five primitives of a personal AI stack 42:47 - Letting cloud models optimize your local stack 43:53 - 800x cheaper than the cloud 45:58 - Josh France and Regan Bell: QM, YC's agent harness for work 47:29 - A history of YC's internal agents 49:24 - OpenClaw and a fleet of 50 agents 51:04 - Pulling the brain out of the sandbox 54:43 - Letting the agent choose its own sandbox and model 57:16 - The grind tool: budgets on goals 58:50 - Agents don't understand social context

Y Combinator

495,816 views • 1 month ago

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents running inside one graph: 17:44 - Build your first AI agent 39:30 - Run agents with loop engineering 1:12:38 - Turn agent loops into graphs 1:34:26 - Build agents that throttle themselves 1:55:05 - Orchestrate the full multi-agent system Most people build one agent and stop there. Google is teaching the full stack: Prompt → Agents → Loops → Graphs → Multi-Agent Systems Single agents are the old workflow. Self-regulating agent graphs are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read the full architecture below ↓

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents running inside one graph: 17:44 - Build your first AI agent 39:30 - Run agents with loop engineering 1:12:38 - Turn agent loops into graphs 1:34:26 - Build agents that throttle themselves 1:55:05 - Orchestrate the full multi-agent system Most people build one agent and stop there. Google is teaching the full stack: Prompt → Agents → Loops → Graphs → Multi-Agent Systems Single agents are the old workflow. Self-regulating agent graphs are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read the full architecture below ↓

Lunar

403,918 views • 2 months ago

xAI & Grok co-founder, Jimmy Ba: "90% of our engineers are running 10-20 Grok Bot agents. Agent Loops replaced all the routine work." In 20 minutes he explains how to run hundreds of agents at once, and why Loops and Graphs are what make it possible. The best thing I've seen on how the future of AI engineering will look like. Watch it, then read the full Grok Bot breakdown below.

xAI & Grok co-founder, Jimmy Ba: "90% of our engineers are running 10-20 Grok Bot agents. Agent Loops replaced all the routine work." In 20 minutes he explains how to run hundreds of agents at once, and why Loops and Graphs are what make it possible. The best thing I've seen on how the future of AI engineering will look like. Watch it, then read the full Grok Bot breakdown below.

Mahax

32,879 views • 1 month ago

Google just released a free 1-hour lecture from Chief Scientist Jeff Dean on full AI Engineering. How to go from one LLM to coordinating 100 AI agents: 01:45 - Build an LLM from scratch 17:22 - Learn how to actually use AI models 30:03 - Master prompt engineering 52:35 - Coordinate 100 agents as one human Most people are still learning how to prompt one model. Jeff Dean is showing the full stack: LLMs → Prompts → Agents → Agent Teams → Graphs Prompting is the old workflow. Coordinating agent systems is the new one. This is 27 years of Google AI compressed into one hour. Bookmark and watch it today Then read the full Graph Engineering guide below ↓

Google just released a free 1-hour lecture from Chief Scientist Jeff Dean on full AI Engineering. How to go from one LLM to coordinating 100 AI agents: 01:45 - Build an LLM from scratch 17:22 - Learn how to actually use AI models 30:03 - Master prompt engineering 52:35 - Coordinate 100 agents as one human Most people are still learning how to prompt one model. Jeff Dean is showing the full stack: LLMs → Prompts → Agents → Agent Teams → Graphs Prompting is the old workflow. Coordinating agent systems is the new one. This is 27 years of Google AI compressed into one hour. Bookmark and watch it today Then read the full Graph Engineering guide below ↓

Lunar

102,967 views • 2 months ago

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

Dan Shipper 📧

67,958 views • 6 months ago

LangChain's CEO and CTO spent 43 minutes on stage laying out the harness, the lifecycle and the infrastructure behind agents that actually survive production: · 2:00 - Why building agents is different from building software · 6:34 - What Deep Agents is: the agent harness explained · 14:48 - LangSmith Sandboxes, announced live · 19:20 - The Agent Development Lifecycle, defined · 25:58 - Why agent trace payloads keep getting larger · 29:38 - The architecture of SmithDB · 34:00 - How Clay and Vanta run on SmithDB · 42:50 - Building the platform for the entire lifecycle The harness is only the first of three layers. The article below covers the other two. Watch this before you ship your next agent ↓

LangChain's CEO and CTO spent 43 minutes on stage laying out the harness, the lifecycle and the infrastructure behind agents that actually survive production: · 2:00 - Why building agents is different from building software · 6:34 - What Deep Agents is: the agent harness explained · 14:48 - LangSmith Sandboxes, announced live · 19:20 - The Agent Development Lifecycle, defined · 25:58 - Why agent trace payloads keep getting larger · 29:38 - The architecture of SmithDB · 34:00 - How Clay and Vanta run on SmithDB · 42:50 - Building the platform for the entire lifecycle The harness is only the first of three layers. The article below covers the other two. Watch this before you ship your next agent ↓

slash1s

14,757 views • 2 months ago