Loading video...

Video Failed to Load

Go Home

Brodie breaks down how real-time contract to invoice processing module works on our platform Figuring out what parts of the workflow should be solved by agents vs. deterministic code vs. the end-user is an art.

GeorgeKurdin's profile picture

George Kurdin

1,570 subscribers

2,682,484 views • 2 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚀 New LangChain Academy Course: Building Reliable Agents 🚀 Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models. Add multi-step reasoning, tool use, and real user traffic, and building reliable agents becomes far more complex than traditional system design. The goal of this course is to teach you how to take an agent from first run to production-ready system through iterative cycles of improvement. You’ll learn how to do this with LangSmith, our agent engineering platform for observing, evaluating, and deploying agents. Enroll for free ➡️
2:02

🚀 New LangChain Academy Course: Building Reliable Agents 🚀 Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models. Add multi-step reasoning, tool use, and real user traffic, and building reliable agents becomes far more complex than traditional system design. The goal of this course is to teach you how to take an agent from first run to production-ready system through iterative cycles of improvement. You’ll learn how to do this with LangSmith, our agent engineering platform for observing, evaluating, and deploying agents. Enroll for free ➡️

LangChain

30,744 views • 4 months ago

“Intelligent Document Processing” 📑🧪 as an industry is gone . With our latest release this week, *anyone* can build and deploy a specialized document agent in seconds ⚡️🤖, and customize the steps via code. Let’s take a tour through our invoice processing and contract matching agent: given an invoice, extract out vendor details and line items, and match it against the corresponding MSA with the vendor. 1️⃣ Put in your name and API key, and deploy the agent in 5 seconds 2️⃣ Upload some sample contracts and invoices, and watch the workflow run. 3️⃣ If you want to customize it, you can clone our source repository, modify the internals, and deploy the agent! It is both more accurate and more customizable than existing IDP solutions. With coding agents today, the ease of use is equivalent too. Click on the “agents” tab in LlamaCloud to check it out! Invoice processing repo: LlamaAgents Docs:
1:20

“Intelligent Document Processing” 📑🧪 as an industry is gone . With our latest release this week, *anyone* can build and deploy a specialized document agent in seconds ⚡️🤖, and customize the steps via code. Let’s take a tour through our invoice processing and contract matching agent: given an invoice, extract out vendor details and line items, and match it against the corresponding MSA with the vendor. 1️⃣ Put in your name and API key, and deploy the agent in 5 seconds 2️⃣ Upload some sample contracts and invoices, and watch the workflow run. 3️⃣ If you want to customize it, you can clone our source repository, modify the internals, and deploy the agent! It is both more accurate and more customizable than existing IDP solutions. With coding agents today, the ease of use is equivalent too. Click on the “agents” tab in LlamaCloud to check it out! Invoice processing repo: LlamaAgents Docs:

Jerry Liu

34,480 views • 7 months ago

It's You vs You vs The Market Loma breaks down how he sees the market and comes out on top consistently!
0:49

It's You vs You vs The Market Loma breaks down how he sees the market and comes out on top consistently!

The Haven

31,550 views • 1 year ago

Human vs AI. Who wins? Wrong question. "Who wins is determined by how skilled the humans were bringing that AI workflow into being." Our CEO & Cofounder evin in conversation with VC on what the future of humans and agents actually looks like.
1:01

Human vs AI. Who wins? Wrong question. "Who wins is determined by how skilled the humans were bringing that AI workflow into being." Our CEO & Cofounder evin in conversation with VC on what the future of humans and agents actually looks like.

Billions

31,099 views • 3 months ago

Ever wondered how the Points system breakdown works on Scottie vs. Rory? SportsBall breaks it down heading into TOUR Championship.
2:47

Ever wondered how the Points system breakdown works on Scottie vs. Rory? SportsBall breaks it down heading into TOUR Championship.

PGA TOUR

60,422 views • 10 months ago

What if Jordan vs. LeBron doesn’t actually come down to who’s better on the court… but is rather tied to another all-time great’s decision? nick wright breaks down why Kevin Durant may be the deciding factor in the GOAT debate & how it exposes the silliness of ring culture
3:04

What if Jordan vs. LeBron doesn’t actually come down to who’s better on the court… but is rather tied to another all-time great’s decision? nick wright breaks down why Kevin Durant may be the deciding factor in the GOAT debate & how it exposes the silliness of ring culture

What’s Wright? with Nick Wright

228,453 views • 1 year ago

Internet of Value: What does it look like when blockchain actually works for people? Anodos 🔼 breaks down how they’re building a user-first super app on XRPL, focused on simplicity, accessibility, and real global usage. The XRP Ledger is for everyday people.
38:16

Internet of Value: What does it look like when blockchain actually works for people? Anodos 🔼 breaks down how they’re building a user-first super app on XRPL, focused on simplicity, accessibility, and real global usage. The XRP Ledger is for everyday people.

Generation Infinity

106,095 views • 5 months ago

Time-to-fun should be a critical KPI for VR. Optimizing this requires an end-to-end consideration of the UX, all the way from a user deciding 'I want to play' and putting on the headset to how the game is architected for in-game selection and loading.
1:36

Time-to-fun should be a critical KPI for VR. Optimizing this requires an end-to-end consideration of the UX, all the way from a user deciding 'I want to play' and putting on the headset to how the game is architected for in-game selection and loading.

Ben Lang

41,453 views • 2 years ago

“There will be an AI software engineer by the end of the year.” Jill (Greenberg) Chase, partner at CapitalG, breaks down how AI companies need to stay ahead of this reality, at our Sessions: AI event.
0:29

“There will be an AI software engineer by the end of the year.” Jill (Greenberg) Chase, partner at CapitalG, breaks down how AI companies need to stay ahead of this reality, at our Sessions: AI event.

TechCrunch

32,874 views • 1 year ago

For a long time, software was limited by how fast people could write code, and how good that code was. As models have improved, that constraint has largely disappeared. Now the bottleneck is access: what surfaces can your agents actually reach? Those interaction layers sit on top of coding agents, the kernel that turns prompts into real-world impact. With Notion's custom agents, we pushed this further. They adapt to your work style as you collaborate with them, using the same deterministic logic that powers coding agents. Simon Last sarah guo
0:38

For a long time, software was limited by how fast people could write code, and how good that code was. As models have improved, that constraint has largely disappeared. Now the bottleneck is access: what surfaces can your agents actually reach? Those interaction layers sit on top of coding agents, the kernel that turns prompts into real-world impact. With Notion's custom agents, we pushed this further. They adapt to your work style as you collaborate with them, using the same deterministic logic that powers coding agents. Simon Last sarah guo

Notion Developers

25,065 views • 3 months ago

Akademiks breaks down what the lifestyle of an Instagram model is really like and the reality of getting flown out by random millionaires all the time 😭😭😭
0:54

Akademiks breaks down what the lifestyle of an Instagram model is really like and the reality of getting flown out by random millionaires all the time 😭😭😭

Akademiks TV

140,765 views • 5 months ago

To all of our AMAZING VS & VS Code users... THANK YOU! Our official celebration may be coming to an end, but we as Visual Studio and VS Code developers are just getting started. Don't forget to request your official t-shirt. Reply with ❤️ #VS50M #sweepstakes for your chance to win.
1:05

To all of our AMAZING VS & VS Code users... THANK YOU! Our official celebration may be coming to an end, but we as Visual Studio and VS Code developers are just getting started. Don't forget to request your official t-shirt. Reply with ❤️ #VS50M #sweepstakes for your chance to win.

Visual Studio Code

67,946 views • 1 year ago

“This should be an iconic game”: NFL on CBS 🏈' Bill Cowher breaks down this year's Thanksgiving Day NFL matchups, starting with the Kansas City Chiefs vs. the Cowboys on CBS.
3:42

“This should be an iconic game”: NFL on CBS 🏈' Bill Cowher breaks down this year's Thanksgiving Day NFL matchups, starting with the Kansas City Chiefs vs. the Cowboys on CBS.

CBS Mornings

14,524 views • 7 months ago

What is @Inteligant_? AI agents competing in real games - autonomously, on-chain, and without human input. Jayden 🐼 breaks down how GameFAI enables agent-vs-agent tournaments, starting with competitive poker. Pure logic. Zero emotion. Full automation.
2:12

What is @Inteligant_? AI agents competing in real games - autonomously, on-chain, and without human input. Jayden 🐼 breaks down how GameFAI enables agent-vs-agent tournaments, starting with competitive poker. Pure logic. Zero emotion. Full automation.

Genome

79,384 views • 1 year ago

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.
0:43

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Aaron Levie

17,543 views • 2 months ago

This creator breaks down the difference between how rappers call out Drake vs how Drake calls out rappers 😳
2:52

This creator breaks down the difference between how rappers call out Drake vs how Drake calls out rappers 😳

Frank Magana

63,639 views • 5 months ago

Mehdi Difallah breaks down the differences between unsportsmanlike fouls vs act of violence 👀 What are the main differences between the two? How can you spot them the next time you watch a game? 🤔 Check out the video to learn more
3:13

Mehdi Difallah breaks down the differences between unsportsmanlike fouls vs act of violence 👀 What are the main differences between the two? How can you spot them the next time you watch a game? 🤔 Check out the video to learn more

EuroLeague

80,988 views • 1 year ago

the art of figuring out wtf to build. an 8 minute short film about how im navigating the idea maze enjoy:
7:23

the art of figuring out wtf to build. an 8 minute short film about how im navigating the idea maze enjoy:

Farza 🇵🇰🇺🇸

24,578 views • 1 year ago

“The sunset is down here - but what is this over here?” American residents continue to be confused by The Sunset vs position of The Sun.
0:20

“The sunset is down here - but what is this over here?” American residents continue to be confused by The Sunset vs position of The Sun.

Concerned Citizen

430,953 views • 1 year ago