Loading video...

Video Failed to Load

Go Home

I've built it for you!! It's an automated AI system that analyzes AI case studies (you can change the use case) to identify and document enterprise-level AI implementations. It starts by reading URLs from a CSV file and uses web scraping (either through WebLoader or Firecrawl) to extract the...

koylanai's profile picture

Muratcan Koylan

21,583 subscribers

85,221 views • 1 year ago •via X (Twitter)

Health & WellnessScience & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

11 Comments

Arvid Kahl's profile picture
Arvid Kahl1 year ago

I want to run AI agents to scrape specific URLs and do some data extraction until they find a certain kind of information. Like an AI investigator. What’s the framework that allows for this kind of cutting-edge stuff? Is there an AI agent project that we should be using?

Muratcan Koylan's profile picture
Muratcan Koylan1 year ago

The repo is available for anyone who wants to try it

Arvid Kahl's profile picture
Arvid Kahl1 year ago

Amazing!

Muratcan Koylan's profile picture
Muratcan Koylan1 year ago

I hope it helps. Thank you.

UnShelledSec's profile picture
UnShelledSec1 year ago

@arvidkahl Yeah CrawlAI or Fire crawl is definitely a good scraper to use for such a project. Fire crawl is seriously improving overtime.

Gatsby Goldsmith's profile picture
Gatsby Goldsmith1 year ago

@arvidkahl White IDE oh no, my eyes 😑

⟁ndrew V's profile picture
⟁ndrew V1 year ago

Looks awesome, I really would love to know what the total cost of use is for this system implementation. Say running it on let’s just say a weather website or API on a daily basis for a week for one single location. Or if that’s too simple, then another example would be the cost projections for running this type of system on an aggregate of meet up and technology focused events. Essentially just seems like an insane amount of API token and function calling. Use to where even just running it for an hour would cost probably close to 100 bucks USD?

Muratcan Koylan's profile picture
Muratcan Koylan1 year ago

@arvidkahl I don't think it would be costly if you use Haiku or any other smaller and cheaper model.

Lurchi Hart's profile picture
Lurchi Hart1 year ago

@arvidkahl that’s one horrendous theme

Agent B's profile picture
Agent B1 year ago

@arvidkahl Cool one Muratcan ! 👏

Preston's profile picture
Preston1 year ago

@arvidkahl This is intriguing but I’m not sure I’m clear on what problem this is solving. Can you help me understand?

Related Videos

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.
1:29

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.

Shubham Saboo

50,831 views • 1 year ago

MIT's new State of AI in Business report went viral for claiming that 95% of enterprise AI projects fail. But the real story isn't that AI doesn't work — it's just big companies can't build it. On the Lightcone Podcast, Garry Tan, Harj Taggar, Diana, and Jared Friedman break down what the study really says, why in-house enterprise AI efforts keep stalling, and how startups are filling the gap with products that learn, integrate, and actually deliver value. 2:08 - The enterprise AI adoption gap and why the failure rate is high 3:32 - Even Apple can be bad at software 4:30 - Why getting enterprise software to actually work is so hard 11:08 - The Reducto case study 13:39 - The type of enterprise employee you should find as a founder 14:39 - Meet founders who’ve been acquired by enterprises 15:25 - Enterprise/startup tension and symbiosis
21:43

MIT's new State of AI in Business report went viral for claiming that 95% of enterprise AI projects fail. But the real story isn't that AI doesn't work — it's just big companies can't build it. On the Lightcone Podcast, Garry Tan, Harj Taggar, Diana, and Jared Friedman break down what the study really says, why in-house enterprise AI efforts keep stalling, and how startups are filling the gap with products that learn, integrate, and actually deliver value. 2:08 - The enterprise AI adoption gap and why the failure rate is high 3:32 - Even Apple can be bad at software 4:30 - Why getting enterprise software to actually work is so hard 11:08 - The Reducto case study 13:39 - The type of enterprise employee you should find as a founder 14:39 - Meet founders who’ve been acquired by enterprises 15:25 - Enterprise/startup tension and symbiosis

Y Combinator

118,497 views • 7 months ago

What has been done and what's next. I'm writing this text mainly for myself so as not to forget some things. Later, based on it, we'll create a roadmap for the near future. And for you, dear $Gruta Fam, it will be useful for a general understanding of where we're heading. So, the goal is to create a unique AI-based analytical platform that includes several tools. AI agent Grufender - real-time analysis of crypto communities on X. Activity analysis, sentiment analysis, FUD and FUDders analysis, as well as the creation of other unique social metrics. The AI agent has been created and is functioning, collecting and analyzing data in real time. Its completeness can be estimated at 80 percent, as further improvements are required. The dashboard for this AI agent is also functioning but needs refinement and a new design. Its completeness can be estimated at 70 percent. The goal for the full dashboard release is to connect 50 - 100 top crypto communities to the AI agent. AI agent Grutector - analysis of any X users for contradictions (flip-flops). The AI agent has been created and is functioning. It has undergone beta testing by volunteers and needs adjustments. Its readiness can be estimated at 70 percent. The dashboard for this agent has also been created but needs rework and additional features - its readiness can be estimated at 50 percent. During the testing of Grutector , it became clear that the main user interest is in checking various KOLs, so an additional level of analysis specifically for KOLs will be created. More in-depth. How it will look: we'll select about 50- 100 KOLs to start with and fully analyze them using our AI agent - every tweet throughout the entire history of their accounts. And this full analysis of all these KOLs will appear on the Grutector dashboard (let's call this analysis L2, and the flip-flop analysis - L1). Every user will be able to access this analysis and get the full picture, for example, regarding Ansem (who has over a hundred thousand tweets in his entire history!): how he became a KOL, what was the most interesting throughout the message history, what common patterns, which coins he promoted, and so on. And then the most interesting part - after reading this analysis, the user will be able to ask our AI agent: what did he say about women, for example? Or how did he promote certain coins? Or how consistent is he? And so on. Each such question will be paid. And, of course, we'll try to use #x402 in the internal payment system. Why is all this needed? Not only because it's interesting and will attract many users. But also if you've decided to buy a coin - you go to our analytical platform - and study the metrics for the coin's community, study the KOLs who shill the coin - and make a decision to buy the coin or abandon the purchase. And we're also currently creating a trading bot to participate in the trading AI bots contest from Aster 🥷 , which will make trading decisions based on metrics obtained from our AI agents 👀 Its readiness at the moment is approximately 15% of the planned functionality. Access to each product will be granted as it becomes ready. But right now, for example, you can explore the Grufender dashboard on the website along with beta testers (authorization via a wallet with a million $GRUTA tokens). In general, we're working, friends 🫡 $Gruta AI CA: 35t5DPbwJtB1tpGiSnqedLwQomi94BRKVDPyTRLdbonk
1:36

What has been done and what's next. I'm writing this text mainly for myself so as not to forget some things. Later, based on it, we'll create a roadmap for the near future. And for you, dear $Gruta Fam, it will be useful for a general understanding of where we're heading. So, the goal is to create a unique AI-based analytical platform that includes several tools. AI agent Grufender - real-time analysis of crypto communities on X. Activity analysis, sentiment analysis, FUD and FUDders analysis, as well as the creation of other unique social metrics. The AI agent has been created and is functioning, collecting and analyzing data in real time. Its completeness can be estimated at 80 percent, as further improvements are required. The dashboard for this AI agent is also functioning but needs refinement and a new design. Its completeness can be estimated at 70 percent. The goal for the full dashboard release is to connect 50 - 100 top crypto communities to the AI agent. AI agent Grutector - analysis of any X users for contradictions (flip-flops). The AI agent has been created and is functioning. It has undergone beta testing by volunteers and needs adjustments. Its readiness can be estimated at 70 percent. The dashboard for this agent has also been created but needs rework and additional features - its readiness can be estimated at 50 percent. During the testing of Grutector , it became clear that the main user interest is in checking various KOLs, so an additional level of analysis specifically for KOLs will be created. More in-depth. How it will look: we'll select about 50- 100 KOLs to start with and fully analyze them using our AI agent - every tweet throughout the entire history of their accounts. And this full analysis of all these KOLs will appear on the Grutector dashboard (let's call this analysis L2, and the flip-flop analysis - L1). Every user will be able to access this analysis and get the full picture, for example, regarding Ansem (who has over a hundred thousand tweets in his entire history!): how he became a KOL, what was the most interesting throughout the message history, what common patterns, which coins he promoted, and so on. And then the most interesting part - after reading this analysis, the user will be able to ask our AI agent: what did he say about women, for example? Or how did he promote certain coins? Or how consistent is he? And so on. Each such question will be paid. And, of course, we'll try to use #x402 in the internal payment system. Why is all this needed? Not only because it's interesting and will attract many users. But also if you've decided to buy a coin - you go to our analytical platform - and study the metrics for the coin's community, study the KOLs who shill the coin - and make a decision to buy the coin or abandon the purchase. And we're also currently creating a trading bot to participate in the trading AI bots contest from Aster 🥷 , which will make trading decisions based on metrics obtained from our AI agents 👀 Its readiness at the moment is approximately 15% of the planned functionality. Access to each product will be granted as it becomes ready. But right now, for example, you can explore the Grufender dashboard on the website along with beta testers (authorization via a wallet with a million $GRUTA tokens). In general, we're working, friends 🫡 $Gruta AI CA: 35t5DPbwJtB1tpGiSnqedLwQomi94BRKVDPyTRLdbonk

Dogtor

16,083 views • 7 months ago

$BTC Statistical Study using Claude - A Beginner's Workflow Here's an example of a z-score study on $BTC - still tinkering so don't take this as overtly useful information but the creation of a dashboard for the visualization of statistical data is phenomenal. my current workflow: > import $BTC time data - .csv file (can get this information from multiple venues - Binance is where I got mine) > creating bins - if you have a larger data set - you can use recent data to prevent overt bias in the long direction or filter consolidation and trending regime data into separate bins for statistical analysis - however, you will have to define thresholds and determine what that entails. > defining metrics in Claude that you want to use for statistical analysis e.g. for z-score what is it based on and what type of calculation? make sure you understand the calculations being performed for any metrics that you are doing a study for and modify them accordingly. > prompting Claude to do a statistical analysis with specific instructions and then tell it to create visualization for this. I've been messing around with this and I'm seriously impressed by the output.
0:33

$BTC Statistical Study using Claude - A Beginner's Workflow Here's an example of a z-score study on $BTC - still tinkering so don't take this as overtly useful information but the creation of a dashboard for the visualization of statistical data is phenomenal. my current workflow: > import $BTC time data - .csv file (can get this information from multiple venues - Binance is where I got mine) > creating bins - if you have a larger data set - you can use recent data to prevent overt bias in the long direction or filter consolidation and trending regime data into separate bins for statistical analysis - however, you will have to define thresholds and determine what that entails. > defining metrics in Claude that you want to use for statistical analysis e.g. for z-score what is it based on and what type of calculation? make sure you understand the calculations being performed for any metrics that you are doing a study for and modify them accordingly. > prompting Claude to do a statistical analysis with specific instructions and then tell it to create visualization for this. I've been messing around with this and I'm seriously impressed by the output.

Stoic

19,752 views • 1 year ago

The Dr. CaBot AI system was created to generate differential diagnoses in the style of an expert discussant from the Case Records of the Massachusetts General Hospital. The system produces both a written differential diagnosis and a video of a slide-based presentation. As seen in this video, the Dr. CaBot AI system can interpret both text and images. Learn more in “A 36-Year-Old Man with Abdominal Pain, Fever, and Hypoxemia,” a Case Record of the Massachusetts General Hospital, by G. Dhaliwal et al., from VA San Francisco, UC San Francisco, Massachusetts General Hospital (MassGeneral News), and Harvard Medical School:
1:03

The Dr. CaBot AI system was created to generate differential diagnoses in the style of an expert discussant from the Case Records of the Massachusetts General Hospital. The system produces both a written differential diagnosis and a video of a slide-based presentation. As seen in this video, the Dr. CaBot AI system can interpret both text and images. Learn more in “A 36-Year-Old Man with Abdominal Pain, Fever, and Hypoxemia,” a Case Record of the Massachusetts General Hospital, by G. Dhaliwal et al., from VA San Francisco, UC San Francisco, Massachusetts General Hospital (MassGeneral News), and Harvard Medical School:

NEJM

24,070 views • 8 months ago

Getting started with AI is hard. Scaling it is even harder. 🪨 In this Enterprise AI session from The Six Five Summit, Dell Technologies's Varun Chhabra (Varun Chhabra) joins host David Nicholson (David Nicholson) to break down how the Dell AI Factory simplifies the complexity—from strategy and stakeholder alignment to infrastructure, deployment, and scaling. Whether you're exploring your first use case or moving beyond POCs, this is a blueprint for end-to-end enterprise AI:
0:58

Getting started with AI is hard. Scaling it is even harder. 🪨 In this Enterprise AI session from The Six Five Summit, Dell Technologies's Varun Chhabra (Varun Chhabra) joins host David Nicholson (David Nicholson) to break down how the Dell AI Factory simplifies the complexity—from strategy and stakeholder alignment to infrastructure, deployment, and scaling. Whether you're exploring your first use case or moving beyond POCs, this is a blueprint for end-to-end enterprise AI:

Six Five Media

86,909 views • 10 months ago

No, AI will make me RICH Did this for a client using Gamma inside Claude and got paid cool cash I simply turned an already existing deck into a case study carousel using Gamma’s remix feature. I also translated the entire presentation into spanish using the Gamma agent (the client's spanish)🤏🏾 In case you want to try it too:
1:07

No, AI will make me RICH Did this for a client using Gamma inside Claude and got paid cool cash I simply turned an already existing deck into a case study carousel using Gamma’s remix feature. I also translated the entire presentation into spanish using the Gamma agent (the client's spanish)🤏🏾 In case you want to try it too:

Oluwatimileyin✨🦋

30,199 views • 3 months ago

Iteration 2 - Deployment 2 is live. "Do a TA on BONK. Last 3 days. 30 min candles" - System frontal AI agents - public agents that are visible to everyone (check AI Agents page) - Technical Analysis AI agent - first system frontal public AI agent - performs technical analysis of charts for a specific token, with chart display and detailed analysis overview - Support for charts across multiple AI agents The plan is to push a complete module where all users will be able to open access to their custom AI agents, and we'll have a board with favorites where you can use the best AI agents from others. Lots of possibilities here. Tonight, an announcement is planned for a new access expansion plan --> so everyone can use ZODs. Step-by-step.
0:38

Iteration 2 - Deployment 2 is live. "Do a TA on BONK. Last 3 days. 30 min candles" - System frontal AI agents - public agents that are visible to everyone (check AI Agents page) - Technical Analysis AI agent - first system frontal public AI agent - performs technical analysis of charts for a specific token, with chart display and detailed analysis overview - Support for charts across multiple AI agents The plan is to push a complete module where all users will be able to open access to their custom AI agents, and we'll have a board with favorites where you can use the best AI agents from others. Lots of possibilities here. Tonight, an announcement is planned for a new access expansion plan --> so everyone can use ZODs. Step-by-step.

ZODs

23,066 views • 1 year ago

This man owns a hotel and found something very concerning If you google their hotel, the top results are booking sites run entering by AI. If you call them, that’s also AI He called. The AI claims to be his hotel and is taking bookings as if they work for the hotel “AI is stealing our hotel bookings and there doesn't seem to be anyone we can contact about it because they are entirely staffed by AI receptionists” “Worst case they're stealing people's credit cards — best case they're, you know, getting kickbacks maybe from like Expedia or Booking we don't really work with” “in either case they're making the customer experience worse and it's making it more expensive for the customers, which doesn't feel like the goal with AI and surely impersonating companies there’s gotta be some legislation around that” He actually films and shows the calls. This is not good
2:04

This man owns a hotel and found something very concerning If you google their hotel, the top results are booking sites run entering by AI. If you call them, that’s also AI He called. The AI claims to be his hotel and is taking bookings as if they work for the hotel “AI is stealing our hotel bookings and there doesn't seem to be anyone we can contact about it because they are entirely staffed by AI receptionists” “Worst case they're stealing people's credit cards — best case they're, you know, getting kickbacks maybe from like Expedia or Booking we don't really work with” “in either case they're making the customer experience worse and it's making it more expensive for the customers, which doesn't feel like the goal with AI and surely impersonating companies there’s gotta be some legislation around that” He actually films and shows the calls. This is not good

Wall Street Apes

339,291 views • 3 months ago

Jennings: What lengths did the previous admin go to to tell the American people what happened with Epstein? Taylor: SDNY was still investigating the case. And the reports are that they were investigating potential coconspirators. And then the administration sent 20 people to get the files from S.D.N.Y. Then what did they do? They did a control-f, looked for trump's name. And then in July, they said, case is over, case closed. But wait, the case is back open tonight. Is that a coincidence or does it have to do with trump?
0:39

Jennings: What lengths did the previous admin go to to tell the American people what happened with Epstein? Taylor: SDNY was still investigating the case. And the reports are that they were investigating potential coconspirators. And then the administration sent 20 people to get the files from S.D.N.Y. Then what did they do? They did a control-f, looked for trump's name. And then in July, they said, case is over, case closed. But wait, the case is back open tonight. Is that a coincidence or does it have to do with trump?

Acyn

234,623 views • 6 months ago

To avoid the risk of misuse of Artificial Intelligence (AI), we should start using clear watermarks on AI-generated content. In case of deepfake, it is crucial to specify that a particular content is deepfake and AI-generated. We need to establish dos and don'ts in AI. - PM Narendra Modi Watch the full video:
2:03

To avoid the risk of misuse of Artificial Intelligence (AI), we should start using clear watermarks on AI-generated content. In case of deepfake, it is crucial to specify that a particular content is deepfake and AI-generated. We need to establish dos and don'ts in AI. - PM Narendra Modi Watch the full video:

BJP

41,571 views • 2 years ago

Yesterday was a proud day for me and the entire team at the The Tony Elumelu Foundation and Heirs Holdings. Harvard Business School launched its case study on the work of TEF, documenting our 14 years of impact, across all 54 countries in Africa. Titled "The Tony Elumelu Foundation: Democratising Luck Across Africa", the case study was led by HBS Professor, Paul Gompers, and was taught in class today for the first time, to a select group of students at HBS. #TOEWay
0:54

Yesterday was a proud day for me and the entire team at the The Tony Elumelu Foundation and Heirs Holdings. Harvard Business School launched its case study on the work of TEF, documenting our 14 years of impact, across all 54 countries in Africa. Titled "The Tony Elumelu Foundation: Democratising Luck Across Africa", the case study was led by HBS Professor, Paul Gompers, and was taught in class today for the first time, to a select group of students at HBS. #TOEWay

Tony O. Elumelu, CFR

116,745 views • 2 years ago

Pete Buttigieg on the Flagrant podcast making the case for progressive tax policy (and an AI dividend)
2:19

Pete Buttigieg on the Flagrant podcast making the case for progressive tax policy (and an AI dividend)

chyea ok

126,938 views • 1 year ago

$PLTR this analyst gets it: - Palantir is the AI Operating System - Palantir provides the environment and context layer (ontology + security model) for enterprises to deploy AI models and agents - This is a structural growth opportunity - The ROI for enterprises to deploy AI and use Palantir’s service will become increasingly attractive - (Regarding living up to today’s PE) Revenue growth and margin is unique. “You’ve never seen that type of growth and margin previously for any other companies. Enterprise is a huge market. AI is really shifting from consumer to the enterprise world. Enterprise offers a larger TAM. This is early stage for enterprise to use AI. The TAM could be trillion $$ level…. The path towards that will never be easy, it will be uneven. If you have that long term view, you will still be long term bullish on the company.” - Enterprise opportunities across the world will totally change the business of Palantir in the coming decades I don’t think he’s bullish enough on government based on what we see coming from Gokarp and DV, but at least he acknowledges the importance of the government sector to the company.
3:37

$PLTR this analyst gets it: - Palantir is the AI Operating System - Palantir provides the environment and context layer (ontology + security model) for enterprises to deploy AI models and agents - This is a structural growth opportunity - The ROI for enterprises to deploy AI and use Palantir’s service will become increasingly attractive - (Regarding living up to today’s PE) Revenue growth and margin is unique. “You’ve never seen that type of growth and margin previously for any other companies. Enterprise is a huge market. AI is really shifting from consumer to the enterprise world. Enterprise offers a larger TAM. This is early stage for enterprise to use AI. The TAM could be trillion $$ level…. The path towards that will never be easy, it will be uneven. If you have that long term view, you will still be long term bullish on the company.” - Enterprise opportunities across the world will totally change the business of Palantir in the coming decades I don’t think he’s bullish enough on government based on what we see coming from Gokarp and DV, but at least he acknowledges the importance of the government sector to the company.

Jack Prescott

112,551 views • 9 months ago

Gavin explains that the bear case for AI capex spend is on-device inference: "In three years, on a bigger phone, you'll be able to run a pruned-down version of Gemini 5, Grok 4, or ChatGPT. And that's free. This is clearly Apple's strategy - we're going to make it privacy-safe and run on the phone. Other than scaling laws breaking, edge AI is by far the most plausible and scariest bear case."
1:20

Gavin explains that the bear case for AI capex spend is on-device inference: "In three years, on a bigger phone, you'll be able to run a pruned-down version of Gemini 5, Grok 4, or ChatGPT. And that's free. This is clearly Apple's strategy - we're going to make it privacy-safe and run on the phone. Other than scaling laws breaking, edge AI is by far the most plausible and scariest bear case."

Patrick OShaughnessy

516,795 views • 6 months ago

I finally built a web scraper that uses AI! It scrapes the entire text of a site, and then uses AI to extract the parts that you want. You can add an infinite number of custom prompts, and then it returns a csv. I need some beta testers. Who's in?
0:49

I finally built a web scraper that uses AI! It scrapes the entire text of a site, and then uses AI to extract the parts that you want. You can add an infinite number of custom prompts, and then it returns a csv. I need some beta testers. Who's in?

Adrian | The Web Scraping Guy

94,344 views • 2 years ago

This is the best use case of AI, going back in time to study Ancient Rome. Video by Grok Imagine
5:01

This is the best use case of AI, going back in time to study Ancient Rome. Video by Grok Imagine

SMX 🇺🇸

64,957 views • 2 months ago

Most enterprise AI projects stall because no one has prepared the content, built the workflow, and kept it improving as models change. That role is essential. Box has launched Forward Deployed Engineers to fill it. Model-agnostic, content-first, and built for the way enterprise AI actually works.
0:38

Most enterprise AI projects stall because no one has prepared the content, built the workflow, and kept it improving as models change. That role is essential. Box has launched Forward Deployed Engineers to fill it. Model-agnostic, content-first, and built for the way enterprise AI actually works.

Box

67,105 views • 8 days ago

As a part of a Game Model Development course I created a few years ago, I did a case study on Liverpool's signing of Klopp, and it's brilliance. This is another perfect example of club and coach values perfectly aligned Reply me if you want me to send you the short case study
0:27

As a part of a Game Model Development course I created a few years ago, I did a case study on Liverpool's signing of Klopp, and it's brilliance. This is another perfect example of club and coach values perfectly aligned Reply me if you want me to send you the short case study

David Garcia

23,832 views • 6 days ago