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.

OpenAI wants markdown structure. Anthropic prefers XML tags. Google emphasizes few-shot examples. So I built a simple agent system that reads the official prompting docs and applies them to the given prompt. Each optimizer runs a ReAct loop: - list_provider_docs → discover available guidelines - read_provider_doc → fetch specific... content - submit_optimization → return structured result Agent decides what context it needs. The loop runs until submission: 1. LLM reasons about the task 2. Calls a tool 3. Observes result 4. Repeats Typically 3-4 iterations. Parallel execution via asyncio.gather; all providers optimize concurrently. Good to explore the agent design and prompts. Feel free to play with it. Shared the repo here: @LangChainAI OpenRoutershow more

Muratcan Koylan

12,681 subscribers

62,021 views • 6 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

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel *by the agent*, clonable to your heart's desire

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel by the agent, clonable to your heart's desire

Grace Li

168,748 views • 8 months ago

My brother (Daniel Cohen Hillel) and I worked on a fun project tonight, inspired by Yohei : Coding Agent that follows the Test Driven Development (TDD) methodology! You write the tests - and the agent runs in a loop until it creates the feature properly! 1/6 #buildinpublic

My brother (Daniel Cohen Hillel) and I worked on a fun project tonight, inspired by Yohei : Coding Agent that follows the Test Driven Development (TDD) methodology! You write the tests - and the agent runs in a loop until it creates the feature properly! 1/6 #buildinpublic

ADAM

384,792 views • 3 years ago

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

374,557 views • 2 months ago

Here's a clip from my upcoming AI SDK tutorial: We're building what Anthropic calls an 'agent' in TypeScript. Can it react to results of tool calls, deciding when it's completed the task? It's an agent.

Here's a clip from my upcoming AI SDK tutorial: We're building what Anthropic calls an 'agent' in TypeScript. Can it react to results of tool calls, deciding when it's completed the task? It's an agent.

Matt Pocock

23,011 views • 1 year ago

Review code written by one agent using a different agent entirely. Here, Claude handles the task, and Gemini runs the review, leaves inline comments, and sends them back to the original agent to implement. Any combination works.

Review code written by one agent using a different agent entirely. Here, Claude handles the task, and Gemini runs the review, leaves inline comments, and sends them back to the original agent to implement. Any combination works.

Air by JetBrains

19,476,873 views • 1 month ago

Introducing the Generative UI Research Canvas ✨ Every agent needs a powerful UI Combine LangChain, Tavily, Tako and CopilotKit🪁 and you get a LangChain-based research agent with a Generative UI-driven frontend. When agents can explore the underlying data, research becomes more trustworthy and useful. How does this work? - LangChain manages the agent workflow and tool orchestration. - Tako converts retrieved data into structured, visual components - Tavily provides agentic search - CopilotKit renders those components in the UI and keeps the user in the loop while the agent is working So instead of a boring and static report, the output is an interactive research canvas that evolves as the agent runs. 2026 is the year where users want to see the output, not read it... Generative UI makes this possible for agentic applications. Tutorial: Open-Source Repo: Docs:

Introducing the Generative UI Research Canvas ✨ Every agent needs a powerful UI Combine LangChain, Tavily, Tako and CopilotKit🪁 and you get a LangChain-based research agent with a Generative UI-driven frontend. When agents can explore the underlying data, research becomes more trustworthy and useful. How does this work? - LangChain manages the agent workflow and tool orchestration. - Tako converts retrieved data into structured, visual components - Tavily provides agentic search - CopilotKit renders those components in the UI and keeps the user in the loop while the agent is working So instead of a boring and static report, the output is an interactive research canvas that evolves as the agent runs. 2026 is the year where users want to see the output, not read it... Generative UI makes this possible for agentic applications. Tutorial: Open-Source Repo: Docs:

Atai Barkai

11,984 views • 4 months ago

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

Shubham Saboo

42,261 views • 1 year ago

THIS GUY IS RUNNING A 5-AGENT OPENCLAW TEAM 24/7 FOR UNDER $50 A MONTH five agents all running continuously and handing tasks to each other > research agent tracking trends and competitors > writing agent handling marketing content and drafts > ops agent managing emails and scheduling > monitoring agent watching for alerts and updates > coordinator agent routing tasks between all of them and he built a full 3D isometric office where you can watch all of them work in real time and see the current task that each agent is doing each agent has a character, a desk, and a name tag. when it's time for a standup, they walk to the meeting room and gather which is insane it even has voice connection. you can talk to the agents through speech-to-text and tell them what to do out loud it's a tiny autonomous team that runs itself. the coordinator decides who handles what and tasks get passed between agents automatically. it never stops and runs 24/7 all for less than $50/month. we went from AI tools a few months back to AI employees real fast

THIS GUY IS RUNNING A 5-AGENT OPENCLAW TEAM 24/7 FOR UNDER $50 A MONTH five agents all running continuously and handing tasks to each other > research agent tracking trends and competitors > writing agent handling marketing content and drafts > ops agent managing emails and scheduling > monitoring agent watching for alerts and updates > coordinator agent routing tasks between all of them and he built a full 3D isometric office where you can watch all of them work in real time and see the current task that each agent is doing each agent has a character, a desk, and a name tag. when it's time for a standup, they walk to the meeting room and gather which is insane it even has voice connection. you can talk to the agents through speech-to-text and tell them what to do out loud it's a tiny autonomous team that runs itself. the coordinator decides who handles what and tasks get passed between agents automatically. it never stops and runs 24/7 all for less than $50/month. we went from AI tools a few months back to AI employees real fast

Om Patel

27,086 views • 1 month ago

soon you're going to be able to have AI autonomously build apps for you, with no human in the loop. me, someone who can't code, can make an app with - Claude Computer Agent, that controls Cursor - clones a github repo - opens composer in agent mode - and prompts it with an app idea - and then waits for the Cursor Agent to finish Then I prompted that agent to test the app! (template @senior_swc)

soon you're going to be able to have AI autonomously build apps for you, with no human in the loop. me, someone who can't code, can make an app with - Claude Computer Agent, that controls Cursor - clones a github repo - opens composer in agent mode - and prompts it with an app idea - and then waits for the Cursor Agent to finish Then I prompted that agent to test the app! (template @senior_swc)

Riley Brown

48,960 views • 1 year ago

I built a multi-agent Deep Research team using Qwen 3 that can generate consulting style reports as Google docs. It has 3 AI Agents working together as a team: 1. Research Question Agent 2. Web Search Agent 3. Google Docs Compilation Agent 100% Opensource Code.

I built a multi-agent Deep Research team using Qwen 3 that can generate consulting style reports as Google docs. It has 3 AI Agents working together as a team: 1. Research Question Agent 2. Web Search Agent 3. Google Docs Compilation Agent 100% Opensource Code.

Shubham Saboo

25,071 views • 1 year ago

📚 Build Deep Research Agent: From Question to Insight Complex research rarely fits in one search box. The Deep Research workflow built with Dify Iterates, reasons, and sources until the answer is complete. 💡 Key workflow nodes include: 1) Start: capture the research topic and the loop budget 2) Exa Answer: gather background terminology 3) Intent LLM: clarify the real research goal 4) Loop: drive the iterative cycles 5) Reasoning LLM: frame better follow-up questions 6) Agent: execute searches, extract content, and reflect 7) Variable Assigner: update the state after each pass 8) Final Summary: synthesize a Markdown report with citations Teams using this template cut research time dramatically and surface insights competitors miss. Learn to implement this workflow:

📚 Build Deep Research Agent: From Question to Insight Complex research rarely fits in one search box. The Deep Research workflow built with Dify Iterates, reasons, and sources until the answer is complete. 💡 Key workflow nodes include: 1) Start: capture the research topic and the loop budget 2) Exa Answer: gather background terminology 3) Intent LLM: clarify the real research goal 4) Loop: drive the iterative cycles 5) Reasoning LLM: frame better follow-up questions 6) Agent: execute searches, extract content, and reflect 7) Variable Assigner: update the state after each pass 8) Final Summary: synthesize a Markdown report with citations Teams using this template cut research time dramatically and surface insights competitors miss. Learn to implement this workflow:

Dify

22,452 views • 1 year ago

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call

Shadow Nick

13,544 views • 7 days ago

Holy Shit This is insane result 🤯 I used opus 4.6 as a reviewer/planner and 4 worker minimax M2.7 agent and this the result Voxel art of eiffel tower < loop set to 5 that means opus will tell MiniMax (official) to make it better 5 times >

Holy Shit This is insane result 🤯 I used opus 4.6 as a reviewer/planner and 4 worker minimax M2.7 agent and this the result Voxel art of eiffel tower < loop set to 5 that means opus will tell MiniMax (official) to make it better 5 times >

Chetaslua

82,862 views • 2 months ago

this chinese developer making $320k/year as a solo contractor his secret: 5 AI agents running in parallel, each one a specialist architect, coder, reviewer, tester, ops they don’t share context, don’t step on each other, just ship he takes on projects meant for teams of 5-8 engineers delivers in half the time keeps the entire budget found this video on bilibili at 3am and watched it four times guy sitting at his desk, two monitors filled with code, and he’s barely touching the keyboard here’s what’s happening on his screen: > agent 1 (architect): designs system structure, breaks down features into tasks, decides what gets built first > agent 2 (coder): writes the actual implementation based on architect’s specs > agent 3 (reviewer): checks every piece of code for bugs, edge cases, security issues > agent 4 (tester): generates test cases, runs them, reports failures back > agent 5 (ops): handles deployment, monitoring, infrastructure five separate claude code instances running simultaneously each one has its own system prompt, its own context, its own specialty they communicate through a shared task queue, not through each other that’s the key insight - no shared context means no conflicts agent 2 doesn’t know what agent 3 is doing agent 4 doesn’t care what agent 1 decided they just pick up tasks, complete them, move on he showed his contract history: > 3D rendering pipeline for a gaming studio: $25k > automated trading dashboard: $33k > enterprise CRM rebuild: $44k all completed solo, all delivered early, all clients thought they were hiring a team the code on his screen is python with blender integration - complex stuff that would normally require 3-4 specialists he’s shipping it in days while the client expects weeks while he’s explaining the system to camera, commits are happening in the background, tests running, deployments going out all while he’s literally not touching the keyboard his API costs run about $2k/month his revenue averages $26k/month that’s a 13x return on his AI investment this is the new solo developer playbook don’t compete with teams become the team

this chinese developer making $320k/year as a solo contractor his secret: 5 AI agents running in parallel, each one a specialist architect, coder, reviewer, tester, ops they don’t share context, don’t step on each other, just ship he takes on projects meant for teams of 5-8 engineers delivers in half the time keeps the entire budget found this video on bilibili at 3am and watched it four times guy sitting at his desk, two monitors filled with code, and he’s barely touching the keyboard here’s what’s happening on his screen: > agent 1 (architect): designs system structure, breaks down features into tasks, decides what gets built first > agent 2 (coder): writes the actual implementation based on architect’s specs > agent 3 (reviewer): checks every piece of code for bugs, edge cases, security issues > agent 4 (tester): generates test cases, runs them, reports failures back > agent 5 (ops): handles deployment, monitoring, infrastructure five separate claude code instances running simultaneously each one has its own system prompt, its own context, its own specialty they communicate through a shared task queue, not through each other that’s the key insight - no shared context means no conflicts agent 2 doesn’t know what agent 3 is doing agent 4 doesn’t care what agent 1 decided they just pick up tasks, complete them, move on he showed his contract history: > 3D rendering pipeline for a gaming studio: $25k > automated trading dashboard: $33k > enterprise CRM rebuild: $44k all completed solo, all delivered early, all clients thought they were hiring a team the code on his screen is python with blender integration - complex stuff that would normally require 3-4 specialists he’s shipping it in days while the client expects weeks while he’s explaining the system to camera, commits are happening in the background, tests running, deployments going out all while he’s literally not touching the keyboard his API costs run about $2k/month his revenue averages $26k/month that’s a 13x return on his AI investment this is the new solo developer playbook don’t compete with teams become the team

regent0x

183,659 views • 1 month ago

Voice-controlled UI. This is an agent design pattern I'm calling EPIC, "explicit prompting for implicit coordination." Feel free to suggest a better name. :-) In the video, I'm navigating around a map, conversationally, pulling in information dynamically from tool calls and realtime streamed events. There are two separate agents (inference loops) here: a voice agent and a UI control agent. They know about each other (at the prompt level) but they work independently.

Voice-controlled UI. This is an agent design pattern I'm calling EPIC, "explicit prompting for implicit coordination." Feel free to suggest a better name. :-) In the video, I'm navigating around a map, conversationally, pulling in information dynamically from tool calls and realtime streamed events. There are two separate agents (inference loops) here: a voice agent and a UI control agent. They know about each other (at the prompt level) but they work independently.

kwindla

14,050 views • 3 months ago

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Notion

492,159 views • 2 months ago

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,109 views • 1 year ago

A conversational agent with no hallucinations! This is huge! Here is the $1M problem: Build a customer-facing AI agent that works consistently, doesn't hallucinate, and is fully aligned with the business rules. Check out Parlant, a FREE, open-source library. I've talked about them before, and here is the TL;DR: 1. Parlant gives you 10x more control over what your agent says 2. It helps you control how agents conduct conversations 3. It helps you control the service protocols and rules agents follow 4. It helps you control what agents can and can't say They do something pretty clever: 1. They have a set of predefined potential responses that the agent can use to reply to the customer. 2. When a customer sends a message, the agent generates a fluid response draft using an LLM and matches and renders the closest pre-approved reply template. 3. The agent returns the rendered pre-approved reply, not the one generated by the LLM. This maintains fluidity while avoiding unpredictability. Parlant also uses your domain terminology, invokes your tools, and implements self-critique to craft/evaluate its response iteratively. This pretty much solves any hallucination issues with your agent.

A conversational agent with no hallucinations! This is huge! Here is the $1M problem: Build a customer-facing AI agent that works consistently, doesn't hallucinate, and is fully aligned with the business rules. Check out Parlant, a FREE, open-source library. I've talked about them before, and here is the TL;DR: 1. Parlant gives you 10x more control over what your agent says 2. It helps you control how agents conduct conversations 3. It helps you control the service protocols and rules agents follow 4. It helps you control what agents can and can't say They do something pretty clever: 1. They have a set of predefined potential responses that the agent can use to reply to the customer. 2. When a customer sends a message, the agent generates a fluid response draft using an LLM and matches and renders the closest pre-approved reply template. 3. The agent returns the rendered pre-approved reply, not the one generated by the LLM. This maintains fluidity while avoiding unpredictability. Parlant also uses your domain terminology, invokes your tools, and implements self-critique to craft/evaluate its response iteratively. This pretty much solves any hallucination issues with your agent.

Santiago

64,237 views • 1 year ago

Context-aware, action-ready. ChatGPT agent understands the task, chooses the right tool, and gets to work. It uses connectors, context, and custom instructions to take smarter actions on your behalf.

Context-aware, action-ready. ChatGPT agent understands the task, chooses the right tool, and gets to work. It uses connectors, context, and custom instructions to take smarter actions on your behalf.

OpenAI

143,127 views • 10 months ago

Self-driving bug management: ① Linear Agent creates a new issue from Slack ② Triage Intelligence auto-applies context ③ Cursor Agent drafts a PR to fix the bug ④ Slack thread gets updated to close the loop

Self-driving bug management: ① Linear Agent creates a new issue from Slack ② Triage Intelligence auto-applies context ③ Cursor Agent drafts a PR to fix the bug ④ Slack thread gets updated to close the loop

Linear

115,314 views • 4 months ago