Share

ConTejas Code
Jack Herrington: Model Context Protocol (MCP), Growing a YouTube Audience, Getting into Open Source
Links
- Codecrafters (sponsor): https://tej.as/codecrafters
- Jack on YouTube: https://www.youtube.com/@jherr
- Jack on X: https://x.com/jherr
- Jack on Bluesky: https://bsky.app/profile/jherr.dev
- Tejas on X: https://x.com/tejaskumar_
- create-tsrouter-app: https://github.com/TanStack/create-tsrouter-app
Summary
In this discussion, Jack Harrington and I explore the transition from being a content creator to an open source contributor, discussing the challenges and rewards of both paths. Jack shares his journey from being a principal engineer to a YouTuber, and now to a key player in the open source community with TanStack. We explore the intricacies of YouTube's algorithm, the importance of marketing oneself, and the unique features of Tanstack that allow for a progressive development experience. We also touch on the future of Tanstack, its cross-platform capabilities, and the potential integration with React Native.
We also discuss AI! Specifically, we discuss the Model Context Protocol (MCP) and how it provides tools and resources to AI, enabling seamless integration with applications. We explore the potential of local development with MCP, emphasizing its advantages over traditional cloud-based solutions.
Chapters
00:00 Jack Herrington
06:11 Transitioning from Influencer to Open Source Contributor
09:10 The YouTube Journey: Challenges and Growth
12:13 Navigating the YouTube Algorithm and Marketing Yourself
15:09 The Shift to Open Source and Community Engagement
18:18 Creating Tanstack: A New Era in Development
20:55 The Unique Features of Tanstack and Its Ecosystem
24:09 Progressive Disclosure in Frameworks
26:54 Cross-Platform Capabilities of Tanstack
30:16 The Future of Tanstack and React Native Integration
40:05 Navigating the Tanstack Ecosystem
42:21 Understanding Model Context Protocol (MCP)
54:04 Integrating MCP with AI Applications
01:05:09 The Future of Local Development with MCP
01:11:03 Creating a Winamp Clone with AI
01:17:07 The Future of Front-End Development and AI
01:24:49 Connecting Dots: The Power of MCP and AI Tools
01:33:27 The Entrepreneurial Spirit: Beyond Money
01:39:27 Closing Thoughts and Future Collaborations
More episodes
View all episodes
Shuhao Zhang, founder Tiny Fish: How to Turn Any Website into an API for AI Agents
01:36:33|Links- Codecrafters: https://tej.as/codecrafters- Tiny Fish: https://tinyfish.io- AgentQL: https://www.agentql.com/SummaryIn this conversation, we discuss AgentQL, a framework designed to enable AI agents to access the web using natural language. Together, we explore the technical aspects of AgentQL, its advantages over traditional web access methods, and the challenges faced in its development. The discussion also covers the role of TinyFish, the parent company of AgentQL, and the future direction of their products. Key use cases for developers are highlighted, showcasing how AgentQL can simplify web scraping and automation tasks. We deep dive into the integration of Playwright with AgentQL, the engineering decisions behind its development, and the importance of maintaining consistency across different SDKs. The conversation also touches on the challenges of remote browsing, security concerns, and the complexities of navigating data structures. Additionally, the various operating modes of AgentQL are explored, highlighting the trade-offs between speed and accuracy. Chapters03:25 Introduction to AgentQL06:33 The Technical Framework of AgentQL09:34 Challenges with Traditional Web Access12:35 The Role of TinyFish and Future Products15:25 Technical Hurdles in Building AgentQL18:26 Interacting with the DOM21:29 Use Cases for Developers24:21 Building with AgentQL27:35 Disambiguation and Query Context30:32 Balancing Precision and Flexibility33:30 Future Directions and Enhancements36:36 Integrating Playwright with AgentQL38:56 Building Infrastructure for Remote Browsing39:30 Engineering Decisions in AgentQL Development45:05 Web Test Automation and AgentQL45:55 SDK Development: Python vs JavaScript47:39 Maintaining Consistency Across Languages51:40 Cross-Browser Support with Playwright54:17 Security Concerns in Remote Browsing59:14 Navigating Complex Data Structures01:03:36 Operating Modes of AgentQL01:04:20 Understanding Browser Fingerprinting and Anti-Bot Measures01:06:31 Exploring AgentQL's Browser Toolkit for Langchain01:09:15 AgentQL's Potential in Automating Workflows01:10:17 The Future of Email Automation with AgentQL01:11:34 Navigating the Challenges of Building a Startup01:16:20 Achieving Success on Product Hunt01:19:30 Implementation Pitfalls for New AgentQL Developers01:21:37 Founder's Playbook: Lessons LearnedLiran Tal: How to Secure Your Apps and AI Agents
01:33:23|Links- Codecrafters (partner): https://tej.as/codecrafters- Snyk: https://snyk.io/- Liran on X: https://x.com/liran_tal- Tejas on X: https://x.com/tejaskumar_SummaryIn this conversation, we explore the complexities of software security, particularly focusing on the challenges posed by Node.js and the broader software supply chain. We discuss the evolution of security practices, the importance of awareness among developers, and the role of automation in enhancing security measures. The conversation highlights the need for a balance between automated tools and manual audits, emphasizing that human oversight remains crucial in high-risk environments. We also explore the vulnerabilities associated with open-source software and the trust developers place in third-party tools and extensions, specifically the importance of SBOMs in understanding software dependencies. We discuss the SolarWinds attack as a pivotal case in supply chain security and the role of tools like lockfile lint in enforcing security policies. Finally, we discuss AI and the role of LLMs in security, particularly regarding attack vectors and the reliability of AI-generated code.Chapters00:00 Liran Tal01:44 Introduction to Security in Software Development04:53 The Evolution of Node.js and Security Challenges07:29 Understanding Software Supply Chain Vulnerabilities10:49 The Role of Open Source in Security13:51 Exploring Security in Development Tools and Extensions16:40 The Importance of Security Awareness and Training19:40 Automating Security: Tools and Best Practices22:30 The Balance Between Automation and Manual Audits25:43 Conclusion and Future of Security in Software Development35:00 Balancing Automation and Human Intervention in Security38:08 Understanding S-BOMs and Their Importance41:14 The SolarWinds Attack: A Case Study in Supply Chain Security43:29 Lockfile Lint: Enforcing Security Policies in Code46:49 Generating SBOMs: A Practical Approach49:03 Demystifying CVSS: Understanding Vulnerability Scoring52:50 AI in Security: Attack Vectors and Defense Strategies59:52 Navigating Security in AI-Generated Code01:05:39 The Role of LLMs in Security Vulnerability Detection01:08:24 Integrating Agents for Secure Code Generation01:11:16 Challenges of LLMs in Security Validation01:14:42 The Complexity of Security in AI Systems01:20:56 Understanding Fuzzing and AI's Role01:24:08 Container Breakout Threats and Mitigation StrategiesChinar Movsisyan: How to Deliver End-to-End AI Solutions
01:30:16|Links- Codecrafters (sponsor): https://tej.as/codecrafters- Feedback Intelligence: https://www.feedbackintelligence.ai/- Chinar on X: https://x.com/movsisyanchinarSummaryIn this podcast episode, we talk to Chinar Movsisyan, the CEO and founder of Feedback Intelligence. They discuss Chinar's extensive background in AI, including her experience in machine learning and computer vision. We discuss the challenges faced in bridging the gap between technical and non-technical stakeholders, the practical applications of feedback intelligence in enhancing user experience, and the importance of identifying failure modes. The discussion also covers the role of LLMs in the architecture of Feedback Intelligence, the company's current stage, and how it aims to make feedback actionable for businesses. Chapters00:00 Chinar Movsisyan02:08 Introduction to Feedback Intelligence03:23 Chinar Movsisyan's Background and Expertise06:33 Understanding AI Engineer vs. GenAI Engineer09:08 The Lifecycle of Building an AI Application13:27 Data Collection and Cleaning Challenges16:20 Training the AI Model: Process and Techniques24:48 Deploying and Monitoring AI Models in Production27:55 The Birth of Feedback Intelligence31:58 Understanding Feedback Intelligence33:26 Practical Applications of Feedback Intelligence42:13 Identifying Failure Modes45:58 The Role of LLMs in Feedback Intelligence51:25 Company Stage and Future Directions57:24 Making Feedback Actionable01:01:30 Streamlining Processes with Automation01:03:18 The Journey of a First-Time Founder01:05:48 Wearing Many Hats: The Founder Experience01:08:22 Prioritizing Features in Early Startups01:13:09 Learning from Customer Interactions01:16:38 The Importance of Problem-Solving01:21:51 Handling Rejection and Staying Motivated01:27:43 Marketing Challenges for Founders01:29:23 Future Plans and Scaling StrategiesDaniel Lockyer: How to deploy and scale anything
01:40:41|Links- Codecrafters (partner): https://tej.as/codecrafters- Ghost: https://ghost.org/- Daniel on X: https://x.com/daniellockyer- Tejas on X: https://x.com/tejaskumar_SummaryIn this conversation, Daniel Lockyer (Ghost) and I explore the intricacies of DevOps, server management, and the balance between simplicity and complexity in software engineering. We discuss the ideal server setup for static sites, scaling considerations, the use of PHP and NGINX, and the challenges of manual server management. The conversation also touches on the debate around Kubernetes, cognitive load in software engineering, and the importance of monitoring and alerting. Ultimately, we emphasize the accessibility of server management and the common fears that prevent individuals from taking the plunge into this domain. Chapters00:00 Daniel Lockyer03:41 Introduction to DevOps and Server Management09:36 Simplicity in Server Setup15:38 The Kubernetes Debate21:37 Challenges of Manual Server Management27:33 Productizing Server Management33:29 The Fear of Failure in Server Management39:21 Navigating Server Management Challenges46:42 The Cost of Custom Solutions vs. Managed Services55:39 Building a Custom Platform as a Service01:03:31 AI Integration in DevOps Practices01:08:50 Cost-Effective Solutions in Kubernetes01:15:18 The Importance of Passion in Programming01:21:41 The Impact of Programming on Life Choices01:33:01 Simplicity as the Key to Problem SolvingEddy Vinck: How to Solve Your Own Problems with AI
01:27:13|Links- Codecrafters (partner): https://tej.as/codecrafters- Blog Recorder: https://blogrecorder.com/- Eddy on X: https://x.com/eddyvinckk- Tejas on X: https://x.com/tejaskumar_SummaryIn this conversation, we discuss Blog Recorder which allows users to create blog posts by speaking their thoughts. Eddy explains the technology behind the product, including the speech-to-text pipeline and the AI components involved. He shares insights into his journey as a software engineer, the balance between AI and UI development, and the importance of building a future-proof product. Chapters00:00:00 Eddy Vinck00:03:08 Introduction to Blog Recorder00:06:11 Understanding the Technology Behind Blog Recorder00:09:12 The Speech-to-Text Pipeline Explained00:12:05 Eddy's Journey as a Software Engineer00:15:07 Balancing AI and UI Development00:18:07 Building a Future-Proof Product00:20:54 Choosing the Right Hosting Solutions00:24:15 Lessons Learned from Building Blog Recorder00:31:02 Kubernetes and Cloud Infrastructure Insights00:40:32 Navigating Product Development and MVPs00:52:09 The Importance of Early Feedback in Product Launches01:00:21 Timing and Market Readiness01:01:37 Innovations in Blog Recording01:03:29 AI and Long-Form Content Creation01:10:35 Current State of Blog Recorder01:18:53 Future Aspirations and Marketing StrategiesDan Bochman: How to Create AI Image Generation Models
01:49:58|Links- Codecrafters (sponsor): https://tej.as/codecrafters- FASHN AI: https://fashn.ai- Dan on X: https://x.com/danbochman- Aya on X: https://x.com/ayaboch- Tejas on X: https://x.com/tejaskumar_SummaryIn this conversation, we dive deep into the intricacies of AI, focusing on concepts like latent space, diffusion, and the evolution of image generation techniques. We explore how latent space serves as a condensed representation of features, the challenges faced by GANs, and how diffusion models have emerged as a more effective method for generating images from noise. The discussion also touches on the importance of quantization in AI models and the iterative approaches used in image generation. Chapters00:00 Dan Bochman02:25 Introduction to AI and Latent Space07:24 Understanding Latent Space and Its Importance12:29 The Concept of Diffusion in AI17:21 From Noise to Image Generation22:32 Challenges with GANs and the Emergence of Diffusion27:28 The Role of Quantization in AI Models32:26 Iterative Approaches in Image Generation35:51 The Noise of Life and Image Clarity37:09 Exploring Diffusion Models in Creative Generation39:00 Understanding Latent Space and Its Importance40:27 Diving Deeper into Loss Functions and Image Quality43:32 Signal to Noise Ratio in Image Generation45:54 The Transition to Latent Space for Better Learning48:44 The Power of Variational Autoencoders53:01 Navigating the Uncanny Valley in AI Generated Images57:43 Guidance in Image Generation and Fashion Applications01:10:24 Understanding Architecture in AI Models01:14:40 Training Diffusion Models: Getting Hands-On01:21:18 Fine-Tuning Techniques and Challenges01:26:53 The Accessibility of AI Model Development01:34:10 Navigating Funding and Research in AI01:46:45 Lessons Learned: The Builder's JourneyMarisa Morby: How to Design Products with Nature in Mind
01:40:09|Links- Codecrafters: https://tej.as/codecrafters- Marisa on Bluesky: https://bsky.app/profile/marisamorby.com- Tejas on X: https://x.com/tejaskumar_- Tejas on Bluesky: https://bsky.app/profile/tej.asSummaryIn this conversation, we explore the profound relationship between design and nature: how nature serves as the ultimate inspiration for design, emphasizing that design is fundamentally about functionality. Marisa shares insights on how natural systems can inform technology and urban planning, and we digve into the concept of user interfaces in nature. The discussion also touches on the distinction between design and artistic expression, advocating for a deeper understanding of both in the context of modern technology and architecture.Chapters00:00 Introduction03:13 Understanding Design Through Nature13:20 The Connection Between Nature and Technology23:06 User Interfaces Inspired by Nature33:13 Design vs. Artistic Expression35:23 The Intersection of Design and Business38:31 Artistic Expression in Business41:50 Empathy and Connection in Branding45:18 The Importance of Presentation in Job Applications52:39 Understanding Gestalt Principles in Design01:01:38 Progressive Disclosure: A Key to User Experience01:04:18 Defining Problems and Understanding Users01:08:25 Exploring Biophilic Design in Engineering01:08:45 Exploring Biophilic Design01:15:09 Integrating Nature into Software Design01:21:05 Understanding the Law of Proximity in UI Design01:23:57 Making the Business Case for Design Principles01:31:44 Human-Centered Design and Urban SustainabilityCorbin Crutchley: How UI frameworks work in detail, thriving with mental health
01:34:26|Links- Codecrafters (partner): https://tej.as/Codecrafters- Playful Programming: https://playfulprogramming.com/- The Framework Field Guide: https://playfulprogramming.com/collections/framework-field-guide- Tejas' Story: https://www.youtube.com/watch?v=zOKCrgQOiME- Corbin on X: https://x.com/crutchcorn- Tejas on X: https://x.com/tejaskumar_SummaryIn this conversation, we explore the world of frontend frameworks, discussing the importance of reactivity, the evolution of frameworks like React, Angular, and Vue, and the nuances of choosing the right framework based on developer experience and team dynamics. Together, we explore the role of state management libraries, the challenges of framework migration, and the significance of maintaining a clean separation of concerns in application architecture. The discussion emphasizes the subjective nature of framework selection and the importance of incremental migration strategies to ensure smooth transitions between technologies.Chapters00:00 Introduction03:41 Introduction to Frontend Frameworks06:37 The Evolution of Reactivity in Frameworks09:37 Choosing the Right Framework12:45 Understanding Framework Differences15:41 Guiding New Developers in Framework Selection18:33 The Role of State Management Libraries21:47 Best Practices for Framework Migration32:35 Understanding Web Components and Reactivity36:28 Performance Metrics in Frameworks39:41 The Journey of Self-Publishing49:04 Motivation Behind Sharing Knowledge53:26 The Human Connection in Open Source01:04:11 Journey into Tech: A Personal Story01:08:07 The Birth of Open Source Projects01:10:38 From Design to Development: A Career Shift01:12:48 Building Playful Programming: Future Aspirations01:16:12 Learning from Failure: The OceanBit Experience01:20:31 Philosophy in Software Development01:32:31 Advice for Aspiring Developers