Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

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... show more

Santiago

448,526 subscribers

92,721 просмотров • 1 год назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 7

Фото профиля Santiago

Santiago1 год назад

If you want to give it a try, here is the link to the platform:

Фото профиля Breadcrumb

Breadcrumb1 год назад

Looking to automate reporting? Use AI agents to turn spreadsheets to reports in minutes without any coding.

Фото профиля ysh

ysh1 год назад

LESSSGGOOOO! 🔥🔥

Фото профиля Antoni Rosinol

Antoni Rosinol1 год назад

Amazing tutorial, thank you @svpino

Фото профиля Pɾҽɱ Kυɱαɾ Aραɾαɳʝι 🤖👶🏼🐘

Pɾҽɱ Kυɱαɾ Aραɾαɳʝι 🤖👶🏼🐘1 год назад

Yes, the goal of any kind of automation, whether with rules or with probabilities, should be to eliminate the mundane. Eliminating Tedium should be the value proposition of such startups, not cost optimisation or headcount reduction.

Фото профиля Adam Lawson

Adam Lawson1 год назад

I struggle with when to make an agent vs when to just use chat (GPT, DeepSeek etc). Example, I can accomplish this by simply uploading the file to ChatGPT, well structured prompt and viola! What's the trigger for agent? Is it scale?

Фото профиля Kai

Kai1 год назад

❤️

Похожие видео

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.

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 просмотров • 1 год назад

Build a loan underwriting agent workflow in ~5 mins 💵🤖 (No code, just English) I built an agentic workflow that can process incoming PDFs of financial statements: checking statements, bank statements, brokerage accounts, and extract/normalize the financials in each source of data. I did this by specifying the schemas and classification logic in plain English; our agent compiles this into a deterministic workflow with calls to agentic parsing to extract out all the information that you need. Our agent builder is now in LlamaCloud, you can sign up and try it yourself! Blog: Sign up:

Build a loan underwriting agent workflow in ~5 mins 💵🤖 (No code, just English) I built an agentic workflow that can process incoming PDFs of financial statements: checking statements, bank statements, brokerage accounts, and extract/normalize the financials in each source of data. I did this by specifying the schemas and classification logic in plain English; our agent compiles this into a deterministic workflow with calls to agentic parsing to extract out all the information that you need. Our agent builder is now in LlamaCloud, you can sign up and try it yourself! Blog: Sign up:

Jerry Liu

30,015 просмотров • 5 месяцев назад

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.

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 просмотров • 3 месяцев назад

In the next 2-3 years, the skills you need to build an ETL process will fundamentally differ from anything we've done in the last decade. The EXTRACT and LOAD steps of an ETL pipeline have been solved forever. They are boring, and I suspect they will continue to be boring. But the TRANSFORM step is where the money is at (and where innovation will continue happening!) An ETL pipeline that can use Large Language Models effectively to transform data is a whole new ballgame. I recorded a video to talk about this. And more importantly, I talk about how you can build ETL pipelines to transform UNSTRUCTURED data (the kind of data that's really hard to handle).

In the next 2-3 years, the skills you need to build an ETL process will fundamentally differ from anything we've done in the last decade. The EXTRACT and LOAD steps of an ETL pipeline have been solved forever. They are boring, and I suspect they will continue to be boring. But the TRANSFORM step is where the money is at (and where innovation will continue happening!) An ETL pipeline that can use Large Language Models effectively to transform data is a whole new ballgame. I recorded a video to talk about this. And more importantly, I talk about how you can build ETL pipelines to transform UNSTRUCTURED data (the kind of data that's really hard to handle).

Santiago

56,412 просмотров • 1 год назад

Scrum is a cancer. There's nothing more bureaucratic, dysfunctional, and slow than a team that just wants to build software, but they are being forced to do it using Scrum. If you are stuck with this, here is a recommendation that will change your life: Go to connect your email, GitHub account, and the software you use to manage projects, and build a workflow that will brief you before every standup. Dimension is pretty incredible. You can literally write a prompt and have Dimension build an agent that will do the work in the background for you. Example: "Go to Linear and GitHub and write a summary of the tasks I completed last week. Organize them based on priority and effort. Send me an email with the results." Schedule this workflow to run 10 minutes before your Scrum meetings, and you'll get an email right before you need it. You can have AI now do all sorts of tasks for you: 1. Brief you before a meeting 2. Reply or handle cold emails 3. Take care of support messages 4. Research tasks for you And all of this can happen unprompted, in the background. Really awesome job from the team behind Dimension! Thanks to them for supporting my work by collaborating with me on this post.

Scrum is a cancer. There's nothing more bureaucratic, dysfunctional, and slow than a team that just wants to build software, but they are being forced to do it using Scrum. If you are stuck with this, here is a recommendation that will change your life: Go to connect your email, GitHub account, and the software you use to manage projects, and build a workflow that will brief you before every standup. Dimension is pretty incredible. You can literally write a prompt and have Dimension build an agent that will do the work in the background for you. Example: "Go to Linear and GitHub and write a summary of the tasks I completed last week. Organize them based on priority and effort. Send me an email with the results." Schedule this workflow to run 10 minutes before your Scrum meetings, and you'll get an email right before you need it. You can have AI now do all sorts of tasks for you: 1. Brief you before a meeting 2. Reply or handle cold emails 3. Take care of support messages 4. Research tasks for you And all of this can happen unprompted, in the background. Really awesome job from the team behind Dimension! Thanks to them for supporting my work by collaborating with me on this post.

Santiago

56,218 просмотров • 8 месяцев назад

Google quietly shipped one of the biggest AI upgrades this year. Here’s the workflow → → Build a Notebook LM with your business docs → Import it into Gemini → Turn it into a custom Gem → Generate content using real data → Export tables straight to Sheets This replaces 5 tools instantly. Save this video, you’ll automate your workflow. Want the SOP? DM me. 💬

Google quietly shipped one of the biggest AI upgrades this year. Here’s the workflow → → Build a Notebook LM with your business docs → Import it into Gemini → Turn it into a custom Gem → Generate content using real data → Export tables straight to Sheets This replaces 5 tools instantly. Save this video, you’ll automate your workflow. Want the SOP? DM me. 💬

Julian Goldie SEO

13,220 просмотров • 6 месяцев назад

I made an agent using GitHub Copilot SDK to help me become a running influencer🏃🏾‍♀️✨ Here's the Python code you can use to build an agent that uses MCP and Skills to: - draft and send email - design pitch decks - make a website Copilot CLI then runs all of this in a workflow🐍

I made an agent using GitHub Copilot SDK to help me become a running influencer🏃🏾‍♀️✨ Here's the Python code you can use to build an agent that uses MCP and Skills to: - draft and send email - design pitch decks - make a website Copilot CLI then runs all of this in a workflow🐍

Marlene Mhangami

34,502 просмотров • 6 месяцев назад

Use this ai workflow to get 1000s of followers/day (Steps and tools included) Step 1: Find 3 posts that went massive Step 2: Ask Claude to break down WHY they worked Step 3: Extract the psychological patterns Step 4: Build prompts that interview YOU for context Tools: Claude 4.1 extended thinking (not basic GPT) Cost: $20/month Time: 10 min setup → infinite personalized content The KEY: Context is KING You have to feed it YOUR voice parameters You have to give it audience psychology You're one prompt away from automating your content creation like a pro Stop using garbage prompts Start reverse-engineering what works Use this playbook

Use this ai workflow to get 1000s of followers/day (Steps and tools included) Step 1: Find 3 posts that went massive Step 2: Ask Claude to break down WHY they worked Step 3: Extract the psychological patterns Step 4: Build prompts that interview YOU for context Tools: Claude 4.1 extended thinking (not basic GPT) Cost: $20/month Time: 10 min setup → infinite personalized content The KEY: Context is KING You have to feed it YOUR voice parameters You have to give it audience psychology You're one prompt away from automating your content creation like a pro Stop using garbage prompts Start reverse-engineering what works Use this playbook

The Startup Ideas Podcast (SIP) 🧃

21,464 просмотров • 9 месяцев назад

#WATCH | Nilgiris, Tamil Nadu: Addressing students at an event in a school, Lok Sabha LoP and Congress MP Rahul Gandhi says, "...We hear every day IT revolution, AI, data, we hear all these words, and we hear that this is the information age. An age where information is freely available and accessible. The job of an institution of a school like this is to create people who are able to look at the information, turn the information into knowledge, and, even more importantly, to behave with wisdom. Because if in the information age we do not have wisdom and we are carried away with information, the world will become a very unpleasant place. We will fight with each other, we will harm each other and so schools like this have a very important place because they turn young students into wise citizens..."

#WATCH | Nilgiris, Tamil Nadu: Addressing students at an event in a school, Lok Sabha LoP and Congress MP Rahul Gandhi says, "...We hear every day IT revolution, AI, data, we hear all these words, and we hear that this is the information age. An age where information is freely available and accessible. The job of an institution of a school like this is to create people who are able to look at the information, turn the information into knowledge, and, even more importantly, to behave with wisdom. Because if in the information age we do not have wisdom and we are carried away with information, the world will become a very unpleasant place. We will fight with each other, we will harm each other and so schools like this have a very important place because they turn young students into wise citizens..."

ANI

13,669 просмотров • 6 месяцев назад

how to build an AI-first SaaS in 2026 1. start with a big market. finance, healthcare, real estate. then zoom into a sub-niche. 2. map the niche’s workflow end-to-end. literally write every step they do daily. ex: leads → scheduling → quoting → follow-ups → payments. 3. highlight where money changes hands. deposits, invoices, negotiations. those moments are where software captures value. 4. identify the repetitive mechanical tasks. anything someone does the same way every day is an automation opportunity. 5. quantify the pain. if a business owner spends 100 hours a year on something and their time is worth $300/hour, that’s a $30k problem. 6. manually perform the workflow yourself. most AI SaaS actually starts as a service. that’s why so many new YC companies begin with humans in the loop. 7. document every step. separate judgment tasks from mechanical tasks. agents handle the mechanical work. 8. turn those steps into agent workflows and connect them to real tools (email, slack, stripe, crm, APIs). 9. build media while you build the product. post daily about the workflow. use AI to research content ideas and scripts. the audience becomes your distribution. 10. launch narrow, show proof (hours saved, revenue generated), then expand into adjacent workflows until you become the default execution layer for that niche. people saying everyday that saas is dying it’s evolving into agents + software + media. full breakdown in the latest episode of The Startup Ideas Podcast (SIP) 🧃 lots of sauce in this one all for free because i can't wait to see what you build watch

how to build an AI-first SaaS in 2026 1. start with a big market. finance, healthcare, real estate. then zoom into a sub-niche. 2. map the niche’s workflow end-to-end. literally write every step they do daily. ex: leads → scheduling → quoting → follow-ups → payments. 3. highlight where money changes hands. deposits, invoices, negotiations. those moments are where software captures value. 4. identify the repetitive mechanical tasks. anything someone does the same way every day is an automation opportunity. 5. quantify the pain. if a business owner spends 100 hours a year on something and their time is worth $300/hour, that’s a $30k problem. 6. manually perform the workflow yourself. most AI SaaS actually starts as a service. that’s why so many new YC companies begin with humans in the loop. 7. document every step. separate judgment tasks from mechanical tasks. agents handle the mechanical work. 8. turn those steps into agent workflows and connect them to real tools (email, slack, stripe, crm, APIs). 9. build media while you build the product. post daily about the workflow. use AI to research content ideas and scripts. the audience becomes your distribution. 10. launch narrow, show proof (hours saved, revenue generated), then expand into adjacent workflows until you become the default execution layer for that niche. people saying everyday that saas is dying it’s evolving into agents + software + media. full breakdown in the latest episode of The Startup Ideas Podcast (SIP) 🧃 lots of sauce in this one all for free because i can't wait to see what you build watch

GREG ISENBERG

189,054 просмотров • 4 месяцев назад

I recorded a video on how you can build a complete RAG application without writing any code. I used Langflow, an open-source project that sits on top of Langchain. Langflow hides all the complexity and makes the process 10x easier. This is a step-by-step tutorial.

I recorded a video on how you can build a complete RAG application without writing any code. I used Langflow, an open-source project that sits on top of Langchain. Langflow hides all the complexity and makes the process 10x easier. This is a step-by-step tutorial.

Santiago

96,106 просмотров • 2 лет назад

my SEO agency makes an extra $1.5k every month by using this n8n automation... my workflow builds a multi-source analytics dashboard that: - pulls data from Google Search Console, Ahrefs and SEMrush - auto-generates branded client reports - delivers trends insights via Slack weekly I wrote a step-by-step guide on how you can build this for yourself reply "SEO" + follow me and I'll send it you for free

my SEO agency makes an extra $1.5k every month by using this n8n automation... my workflow builds a multi-source analytics dashboard that: - pulls data from Google Search Console, Ahrefs and SEMrush - auto-generates branded client reports - delivers trends insights via Slack weekly I wrote a step-by-step guide on how you can build this for yourself reply "SEO" + follow me and I'll send it you for free

Machina

56,838 просмотров • 1 год назад

Here are weeks of work done in minutes: A year ago, this would have been impossible. Today, we can finish an entire workflow using AI in minutes. I recorded the step-by-step process of solving the following problem: • Connecting to Paul Graham's website • Downloading his last 3 essays • Summarizing them The best part: I didn't write a single line of code. Instead, I used n8n.io. They released an integration with Langchain and gave me access to their beta version to try. They are also sponsoring this post. I'll use a conversational agent in the video to generate fake summaries. You can include these agents in any workflow. They work everywhere. If you want to try and build a workflow, check this out: The future looks insane. Do you think coding will become less prominent with AI and automation in the next decade?

Here are weeks of work done in minutes: A year ago, this would have been impossible. Today, we can finish an entire workflow using AI in minutes. I recorded the step-by-step process of solving the following problem: • Connecting to Paul Graham's website • Downloading his last 3 essays • Summarizing them The best part: I didn't write a single line of code. Instead, I used n8n.io. They released an integration with Langchain and gave me access to their beta version to try. They are also sponsoring this post. I'll use a conversational agent in the video to generate fake summaries. You can include these agents in any workflow. They work everywhere. If you want to try and build a workflow, check this out: The future looks insane. Do you think coding will become less prominent with AI and automation in the next decade?

Santiago

218,618 просмотров • 2 лет назад

Announcing my new course: Agentic AI! Building AI agents is one of the most in-demand skills in the job market. This course, available now at teaches you how. You'll learn to implement four key agentic design patterns: - Reflection, in which an agent examines its own output and figures out how to improve it - Tool use, in which an LLM-driven application decides which functions to call to carry out web search, access calendars, send email, write code, etc. - Planning, where you'll use an LLM to decide how to break down a task into sub-tasks for execution, and - Multi-agent collaboration, in which you build multiple specialized agents — much like how a company might hire multiple employees — to perform a complex task You'll also learn to take a complex application and systematically decompose it into a sequence of tasks to implement using these design patterns. But here's what I think is the most important part of this course: Having worked with many teams on AI agents, I've found that the single biggest predictor of whether someone executes well is their ability to drive a disciplined process for evals and error analysis. In this course, you'll learn how to do this, so you can efficiently home in on which components to improve in a complex agentic workflow. Instead of guessing what to work on, you'll let evals data guide you. This will put you significantly ahead of the game compared to the vast majority of teams building agents. Together, we'll build a deep research agent that searches, synthesizes, and reports, using all of these agentic design patterns and best practices. This self-paced course is taught in a vendor neutral way, using raw Python - without hiding details in a framework. You'll see how each step works, and learn the core concepts that you can then implement using any popular agentic AI framework, or using no framework. The only prerequisite is familiarity with Python, though knowing a bit about LLMs helps. Come join me, and let's build some agentic AI systems! Sign up to get started:

Announcing my new course: Agentic AI! Building AI agents is one of the most in-demand skills in the job market. This course, available now at teaches you how. You'll learn to implement four key agentic design patterns: - Reflection, in which an agent examines its own output and figures out how to improve it - Tool use, in which an LLM-driven application decides which functions to call to carry out web search, access calendars, send email, write code, etc. - Planning, where you'll use an LLM to decide how to break down a task into sub-tasks for execution, and - Multi-agent collaboration, in which you build multiple specialized agents — much like how a company might hire multiple employees — to perform a complex task You'll also learn to take a complex application and systematically decompose it into a sequence of tasks to implement using these design patterns. But here's what I think is the most important part of this course: Having worked with many teams on AI agents, I've found that the single biggest predictor of whether someone executes well is their ability to drive a disciplined process for evals and error analysis. In this course, you'll learn how to do this, so you can efficiently home in on which components to improve in a complex agentic workflow. Instead of guessing what to work on, you'll let evals data guide you. This will put you significantly ahead of the game compared to the vast majority of teams building agents. Together, we'll build a deep research agent that searches, synthesizes, and reports, using all of these agentic design patterns and best practices. This self-paced course is taught in a vendor neutral way, using raw Python - without hiding details in a framework. You'll see how each step works, and learn the core concepts that you can then implement using any popular agentic AI framework, or using no framework. The only prerequisite is familiarity with Python, though knowing a bit about LLMs helps. Come join me, and let's build some agentic AI systems! Sign up to get started:

Andrew Ng

886,821 просмотров • 9 месяцев назад

BIG ANNOUNCEMENT We have completed phase 1 of an entirely new set of experiments this time using Vero Cells and all new laboratories. With over 150 TEMs selected by myself and a 2hr video of the open scope process this is the most comprehensive study to date

BIG ANNOUNCEMENT We have completed phase 1 of an entirely new set of experiments this time using Vero Cells and all new laboratories. With over 150 TEMs selected by myself and a 2hr video of the open scope process this is the most comprehensive study to date

Jamie Andrews

25,131 просмотров • 11 месяцев назад

Omg, this is such a hack for vibecoding mobile apps This is an image with a video on the top. The video is a character with no backround. I'm using: > Masko AI to generate the video > vibecode.dev to build the app In masko all you need to do is provide an image, and it will give you a video without a background. And then all you need to do is give it to vibecode.dev which is the best mobile app builder.

Omg, this is such a hack for vibecoding mobile apps This is an image with a video on the top. The video is a character with no backround. I'm using: > Masko AI to generate the video > vibecode.dev to build the app In masko all you need to do is provide an image, and it will give you a video without a background. And then all you need to do is give it to vibecode.dev which is the best mobile app builder.

Emily Lambert

29,840 просмотров • 5 месяцев назад

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

Andrew Ng

297,131 просмотров • 2 лет назад

A quick 6-step workflow to take a trading idea from raw data to a validated edge with the help of Claude. Step 1 - Connect Dhan (MCP) Claude can place orders, fetch positions, and pull info across NSE, BSE, MCX Step 2 - Install the Dhan skill The MCP gives tools, the skill gives know-how (correct API calls, instrument IDs etc) Step 3 - Download historical data Ask Claude to pull EOD history. Step 4 - Build the ratio file Create a CSV with necessary data for backtest Step 5 - Define rules and backtest Ratio breaks above 20-day high → hold NIFTYBEES Ratio breaks below 20-day low → rotate into GOLDBEES Step 6 - Validate

A quick 6-step workflow to take a trading idea from raw data to a validated edge with the help of Claude. Step 1 - Connect Dhan (MCP) Claude can place orders, fetch positions, and pull info across NSE, BSE, MCX Step 2 - Install the Dhan skill The MCP gives tools, the skill gives know-how (correct API calls, instrument IDs etc) Step 3 - Download historical data Ask Claude to pull EOD history. Step 4 - Build the ratio file Create a CSV with necessary data for backtest Step 5 - Define rules and backtest Ratio breaks above 20-day high → hold NIFTYBEES Ratio breaks below 20-day low → rotate into GOLDBEES Step 6 - Validate

Kirubakaran Rajendran

25,398 просмотров • 29 дней назад