ConTejas Code

LINKS - Codecrafters: https://tej.as/codecrafters - Tejas on X: https://x.com/tejaskumar_ - JSHeroes conference: https://jsheroes.io - Attention is All You Need Paper: https://scispace.com/pdf/attention-is-all-you-need-1hodz0wcqb.pdf - Google Agents paper: https://ppc.land/content/files/2025/01/Newwhitepaper_Agents2.pdf - Jack Herrington episode about implementing MCP server: - YouTube: https://www.youtube.com/watch?v=0zXyCQV4A84 - Apple: https://podcasts.apple.com/nz/podcast/jack-herrington-model-context-protocol-mcp-growing/id1731855333?i=1000698551942 - Spotify: https://open.spotify.com/episode/5u7ReU2AMnS3TOYuiSwVY1?si=HrBzavRGThOITtYdXDloTA - John McBride episode about fine-tuning Mistral 7B at OpenSauced - YouTube: https://www.youtube.com/watch?v=ipbhB3k0ik0 - Apple: https://podcasts.apple.com/us/podcast/1731855333?i=1000663298584 - Spotify: https://open.spotify.com/episode/77UWTis0TxCd1uPOZhGAnJ?si=CUGmHtJ2RxWhmW5MI3XYbg SUMMARY This episode is a long-form lecture on AI innovation in 2025. We cover a wide range of topics. For more details, see chapters below. CHAPTERS 00:00:00 Intro 00:02:31 What is AI? 00:07:30 Limitations of AI 00:14:29 Solving AI Problems with RAG 00:22:51 Embeddings and Vector Databases Explained 00:31:23 Hybrid Search: Vectors and Keywords (BM25) 00:38:17 Rerankers for Maximum Accuracy 00:43:51 RAG vs. Fine-Tuning 00:54:29 AI Agents 01:13:12 Model Context Protocol (MCP) 01:26:12 How to Get Started 01:34:04 Conclusion ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.

Links - Codecrafters: https://tej.as/codecrafters - Tiny Fish: https://tinyfish.io - AgentQL: https://www.agentql.com/ Summary In 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. Chapters 03:25 Introduction to AgentQL 06:33 The Technical Framework of AgentQL 09:34 Challenges with Traditional Web Access 12:35 The Role of TinyFish and Future Products 15:25 Technical Hurdles in Building AgentQL 18:26 Interacting with the DOM 21:29 Use Cases for Developers 24:21 Building with AgentQL 27:35 Disambiguation and Query Context 30:32 Balancing Precision and Flexibility 33:30 Future Directions and Enhancements 36:36 Integrating Playwright with AgentQL 38:56 Building Infrastructure for Remote Browsing 39:30 Engineering Decisions in AgentQL Development 45:05 Web Test Automation and AgentQL 45:55 SDK Development: Python vs JavaScript 47:39 Maintaining Consistency Across Languages 51:40 Cross-Browser Support with Playwright 54:17 Security Concerns in Remote Browsing 59:14 Navigating Complex Data Structures 01:03:36 Operating Modes of AgentQL 01:04:20 Understanding Browser Fingerprinting and Anti-Bot Measures 01:06:31 Exploring AgentQL's Browser Toolkit for Langchain 01:09:15 AgentQL's Potential in Automating Workflows 01:10:17 The Future of Email Automation with AgentQL 01:11:34 Navigating the Challenges of Building a Startup 01:16:20 Achieving Success on Product Hunt 01:19:30 Implementation Pitfalls for New AgentQL Developers 01:21:37 Founder's Playbook: Lessons Learned ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.

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_ Summary In 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. Chapters 00:00 Liran Tal 01:44 Introduction to Security in Software Development 04:53 The Evolution of Node.js and Security Challenges 07:29 Understanding Software Supply Chain Vulnerabilities 10:49 The Role of Open Source in Security 13:51 Exploring Security in Development Tools and Extensions 16:40 The Importance of Security Awareness and Training 19:40 Automating Security: Tools and Best Practices 22:30 The Balance Between Automation and Manual Audits 25:43 Conclusion and Future of Security in Software Development 35:00 Balancing Automation and Human Intervention in Security 38:08 Understanding S-BOMs and Their Importance 41:14 The SolarWinds Attack: A Case Study in Supply Chain Security 43:29 Lockfile Lint: Enforcing Security Policies in Code 46:49 Generating SBOMs: A Practical Approach 49:03 Demystifying CVSS: Understanding Vulnerability Scoring 52:50 AI in Security: Attack Vectors and Defense Strategies 59:52 Navigating Security in AI-Generated Code 01:05:39 The Role of LLMs in Security Vulnerability Detection 01:08:24 Integrating Agents for Secure Code Generation 01:11:16 Challenges of LLMs in Security Validation 01:14:42 The Complexity of Security in AI Systems 01:20:56 Understanding Fuzzing and AI's Role 01:24:08 Container Breakout Threats and Mitigation Strategies ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.

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 ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.

Links - Codecrafters (sponsor): https://tej.as/codecrafters - Feedback Intelligence: https://www.feedbackintelligence.ai/ - Chinar on X: https://x.com/movsisyanchinar Summary In 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. Chapters 00:00 Chinar Movsisyan 02:08 Introduction to Feedback Intelligence 03:23 Chinar Movsisyan's Background and Expertise 06:33 Understanding AI Engineer vs. GenAI Engineer 09:08 The Lifecycle of Building an AI Application 13:27 Data Collection and Cleaning Challenges 16:20 Training the AI Model: Process and Techniques 24:48 Deploying and Monitoring AI Models in Production 27:55 The Birth of Feedback Intelligence 31:58 Understanding Feedback Intelligence 33:26 Practical Applications of Feedback Intelligence 42:13 Identifying Failure Modes 45:58 The Role of LLMs in Feedback Intelligence 51:25 Company Stage and Future Directions 57:24 Making Feedback Actionable 01:01:30 Streamlining Processes with Automation 01:03:18 The Journey of a First-Time Founder 01:05:48 Wearing Many Hats: The Founder Experience 01:08:22 Prioritizing Features in Early Startups 01:13:09 Learning from Customer Interactions 01:16:38 The Importance of Problem-Solving 01:21:51 Handling Rejection and Staying Motivated 01:27:43 Marketing Challenges for Founders 01:29:23 Future Plans and Scaling Strategies ---------------------------------------- Hosted on Acast. See acast.com/privacy [https://acast.com/privacy] for more information.