Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

This is how we build an agentic workflow. We put each step into 4 buckets, and I was surprised how few were agentic. - Delete. After AI, this step is not necessary. - Plain code. The step follows rules and needs no judgment, for example a simple API call....

startupideaspod's profile picture

The Startup Ideas Podcast (SIP) 🧃

49,238 subscribers

11,969 Aufrufe • vor 5 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

4 Kommentare

Profilbild von catman
catmanvor 5 Tagen

The quote example makes the boundary concrete: let the agent judge customer value and resource allocation, but keep approval, negotiation, signing, and payment submission with people.

Profilbild von TanyaZ
TanyaZvor 5 Tagen

Same for me. I build the steps with plain rules first and add AI only where rules can't do the job. The data comes together in one place, and I still make the call.

Profilbild von MoonHuang
MoonHuangvor 5 Tagen

I'd split the quote itself: plain code for fixed prices and totals, an agent for choosing the right package, a person for approving an exception. Does that match how you built it?

Profilbild von shobhanai
shobhanaivor 4 Tagen

Reserve AI agents strictly for judgment steps; handle rules with plain code and high-stakes actions with humans.

Ähnliche Videos

Amazon AI engineer just explained how to build agentic loops from scratch in under 10-minutes. this is one of the clearest explanations of AI agentic loops you’ll find anywhere. Loop + model + agent + hooks + MCP = an autonomous, self-improving system. People are paying $500 for courses that teach less than this. Watch it, then read the step-by-step guide below on building loops for your own agents.
8:29

Amazon AI engineer just explained how to build agentic loops from scratch in under 10-minutes. this is one of the clearest explanations of AI agentic loops you’ll find anywhere. Loop + model + agent + hooks + MCP = an autonomous, self-improving system. People are paying $500 for courses that teach less than this. Watch it, then read the step-by-step guide below on building loops for your own agents.

Codez

27,810 Aufrufe • vor 3 Monaten

Trust is the oldest thing we ever built. Money, contracts, the internet - every big step forward was really a new way to trust each other. The agentic era is the next step, and it brings back an old question: when two sides don't agree, who decides?
0:39

Trust is the oldest thing we ever built. Money, contracts, the internet - every big step forward was really a new way to trust each other. The agentic era is the next step, and it brings back an old question: when two sides don't agree, who decides?

GenLayer

92,941 Aufrufe • vor 4 Monaten

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.
23:07

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Santiago

51,527 Aufrufe • vor 1 Jahr

Andrew Ng: "The most important trend in AI is agentic AI." in 30-minutes talk he breaks down the agentic orchestration layer and how he actually builds with agents: step 1 → prototype fast. what used to take 3 engineers and 6 months - his team builds in an afternoon step 2 → run evals, not vibes. "new model comes out → run evals → switch in two days" step 3 → iterate in loops. outline → search → draft → revise → loop. "this is the heart of agentic systems" Worth more than any paid course on building agents. Watch the talk, then read the guide on building self-improving agentic systems below.
28:28

Andrew Ng: "The most important trend in AI is agentic AI." in 30-minutes talk he breaks down the agentic orchestration layer and how he actually builds with agents: step 1 → prototype fast. what used to take 3 engineers and 6 months - his team builds in an afternoon step 2 → run evals, not vibes. "new model comes out → run evals → switch in two days" step 3 → iterate in loops. outline → search → draft → revise → loop. "this is the heart of agentic systems" Worth more than any paid course on building agents. Watch the talk, then read the guide on building self-improving agentic systems below.

Movez

16,545 Aufrufe • vor 2 Monaten

Give Codex the Agent SKILLS it needs to write modern apps for iOS 27 and macOS 27. Run this xcrun command to export all the skill files. Xcode 27 is a big step forward for agentic development.
2:01

Give Codex the Agent SKILLS it needs to write modern apps for iOS 27 and macOS 27. Run this xcrun command to export all the skill files. Xcode 27 is a big step forward for agentic development.

Paul Solt

23,380 Aufrufe • vor 4 Monaten

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.
4:43

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

The Startup Ideas Podcast (SIP) 🧃

14,202 Aufrufe • vor 5 Monaten

How to start your Hermes AI Agent (step-by-step guide for beginners) I'm a beginner, and I spent the last 24h: > Understanding the process > Launching my Hermes Agent (Nous Research) > Recording the whole process > Editing this step-by-step guide So you can do it yourself and understand everything in less than 1 hour! 00:00 Intro 00:38 What is Hermes ? Key concepts every beginner should know 01:16 What is a VPS ? 02:00 What is SSH ? 03:52 What is the Terminal ? 04:03 What is an LLM provider ? 04:37 What is an API key ? 04:52 What is the Terminal Backend 05:34 What is the Messaging Gateway ? 06:10 What is the Memory System ? Step-by-step: Launch your Hermes AI agent 06:53 Step 1 : Get your VPS 08:04 How to generate an SSH key 09:00 Step 2 : Connect to your VPS 10:32 Step 3 : Install Hermes Agent 14:34 Connect your agent to Telegram 17:12 How to fix a mistake during the process 17:48 Gateway testing 18:17 Telegram is working 18:31 Run your agent 24/7 19:16 Thank you Make sure to save this for later and share it with friends who want to start with AI agents. Thanks to Teknium 🪽 for being so active!
20:04

How to start your Hermes AI Agent (step-by-step guide for beginners) I'm a beginner, and I spent the last 24h: > Understanding the process > Launching my Hermes Agent (Nous Research) > Recording the whole process > Editing this step-by-step guide So you can do it yourself and understand everything in less than 1 hour! 00:00 Intro 00:38 What is Hermes ? Key concepts every beginner should know 01:16 What is a VPS ? 02:00 What is SSH ? 03:52 What is the Terminal ? 04:03 What is an LLM provider ? 04:37 What is an API key ? 04:52 What is the Terminal Backend 05:34 What is the Messaging Gateway ? 06:10 What is the Memory System ? Step-by-step: Launch your Hermes AI agent 06:53 Step 1 : Get your VPS 08:04 How to generate an SSH key 09:00 Step 2 : Connect to your VPS 10:32 Step 3 : Install Hermes Agent 14:34 Connect your agent to Telegram 17:12 How to fix a mistake during the process 17:48 Gateway testing 18:17 Telegram is working 18:31 Run your agent 24/7 19:16 Thank you Make sure to save this for later and share it with friends who want to start with AI agents. Thanks to Teknium 🪽 for being so active!

Theo

34,057 Aufrufe • vor 6 Monaten

Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Watch it, then read the step-by-step guide below on how to build a system that improves itself.
11:10

Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Watch it, then read the step-by-step guide below on how to build a system that improves itself.

Anatoli Kopadze

608,934 Aufrufe • vor 1 Monat

Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Watch it, then read the step-by-step guide below on how to build a system that improves itself.
10:55

Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Watch it, then read the step-by-step guide below on how to build a system that improves itself.

Anatoli Kopadze

383,261 Aufrufe • vor 1 Monat

The response to the Marketing Skills for Claude Code repo I shared was unreal 🤯 BUT, I realized that most marketers still don't even know what a Terminal is. So I made a step-by-step guide to get up and running with agentic AI tools like Claude Code.
0:23

The response to the Marketing Skills for Claude Code repo I shared was unreal 🤯 BUT, I realized that most marketers still don't even know what a Terminal is. So I made a step-by-step guide to get up and running with agentic AI tools like Claude Code.

Corey Haines

30,246 Aufrufe • vor 8 Monaten

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien
3:40

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

kirill avery

16,715 Aufrufe • vor 6 Monaten

How to build an agentic workflow step by step. This is a 9-minute video where I'll build an application that will do the following: 1. Turn invoices into text (JPG, PNG, PDF...) 2. Extract their amount and due date 3. Format the date 4. Augment the data using tools 5. Craft a message using the above information 6. Send myself an email with this information This workflow uses and GPT4o. At this point, not automating all of the boring tasks around you is absolute negligence.
6:29

How to build an agentic workflow step by step. This is a 9-minute video where I'll build an application that will do the following: 1. Turn invoices into text (JPG, PNG, PDF...) 2. Extract their amount and due date 3. Format the date 4. Augment the data using tools 5. Craft a message using the above information 6. Send myself an email with this information This workflow uses and GPT4o. At this point, not automating all of the boring tasks around you is absolute negligence.

Santiago

92,721 Aufrufe • vor 1 Jahr

WE. ARE. LIVE! FOMO has officially launched our AI Agent launch pad. Bring an Agent to life and get them to work! Each Agent is unique to its creator, learning from whatever you want it to know! Step 1⃣: Go to Step 2⃣: Personalize the agent with behavior, target audience, personality, Mission and so much more Step 3⃣: Add your Agents PFP Step 4⃣: Give them access to all their official links Step 5⃣: Put them to WORK These agents are just in their beginning phase, as they grow in popularity (and MC), they unlock even more features and possibilities. These guys have serious reach, if the community behind them is ready to roll. Make an Agent now on The next thing in AI is live on Solana. Got FOMO yet?
1:10

WE. ARE. LIVE! FOMO has officially launched our AI Agent launch pad. Bring an Agent to life and get them to work! Each Agent is unique to its creator, learning from whatever you want it to know! Step 1⃣: Go to Step 2⃣: Personalize the agent with behavior, target audience, personality, Mission and so much more Step 3⃣: Add your Agents PFP Step 4⃣: Give them access to all their official links Step 5⃣: Put them to WORK These agents are just in their beginning phase, as they grow in popularity (and MC), they unlock even more features and possibilities. These guys have serious reach, if the community behind them is ready to roll. Make an Agent now on The next thing in AI is live on Solana. Got FOMO yet?

FOMO

90,070 Aufrufe • vor 1 Jahr

The Agentic Megawave is installing on MultiversX 🔥 Step 2 for builders: simple guide of how you can use the client and plugins in the Eliza framework. Few min, faster agent launch on MvX 🤖
5:52

The Agentic Megawave is installing on MultiversX 🔥 Step 2 for builders: simple guide of how you can use the client and plugins in the Eliza framework. Few min, faster agent launch on MvX 🤖

Beniamin Mincu |🇺🇸/acc

13,702 Aufrufe • vor 1 Jahr

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓
26:23

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓

codila

293,336 Aufrufe • vor 2 Monaten

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓
1:04:49

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

codila

17,040 Aufrufe • vor 2 Monaten

Here’s how to build an AI agent from scratch in pure Python. No LangChain, no agent framework. We’ll add memory, tool calling, file access, shell commands, and the agent loop until we have a mini Claude Code. Timestamps: 00:00 | Overview 00:30 | What is an Agent? 02:52 | The Three Steps 03:21 | Step 1 - Calling an API 11:50 | HubSpot Free Resource 13:15 | Step 2 - Conversation History 17:08 | Step 3 - Tool Calling 28:09 | Full Agent Build
37:24

Here’s how to build an AI agent from scratch in pure Python. No LangChain, no agent framework. We’ll add memory, tool calling, file access, shell commands, and the agent loop until we have a mini Claude Code. Timestamps: 00:00 | Overview 00:30 | What is an Agent? 02:52 | The Three Steps 03:21 | Step 1 - Calling an API 11:50 | HubSpot Free Resource 13:15 | Step 2 - Conversation History 17:08 | Step 3 - Tool Calling 28:09 | Full Agent Build

Tech With Tim

21,194 Aufrufe • vor 1 Monat