Videos

Autoresearch is an innovative autonomous framework released by Andrej Karpathy that utilizes AI agents to continuously improve code, marketing assets, and business processes through a self-reinforcing loop of hypothesis creation, experimental testing, and objective scoring. Originally developed for optimizing machine learning models, this system has transitioned into a powerful tool for general business growth, allowing for thousands of iterations to occur without human intervention. This articl...

This video provides a deep dive into the capabilities of Claude Fable 5, the latest powerhouse model from Anthropic, and explains how to leverage it to build a robust AI Operating System (AIOS). The presentation moves beyond simple prompting, showing viewers how to create a centralized, folder-based architecture that acts as a second brain for their personal and professional lives. By integrating context, live data connections, and specialized skills, users can transform Claude into a proactive ...

This video covers the strategic roadmap for building and scaling a high-value AI consulting agency in the era of agentic workflows. Devin Kearns explains the transition from simple AI automations to integrated production systems that provide measurable ROI, focusing on serving the mid-market to maximize enterprise value and prepare for a significant business exit. ## Key Takeaways * Pure development value is trending toward zero as AI makes coding more accessible. The real value now lies in st...

In this session, Meaghan Choi, Design Lead for Claude Code at Anthropic, demonstrates how to optimize development workflows using Claude AI through advanced features like work trees, custom prototyping skills, and automated pull request management. The video provides a deep dive into the internal practices used at Anthropic to speed up the shipping process while maintaining high design standards. ## Key Takeaways * Use Git work trees to run multiple Claude sessions in parallel without file syst...

This video provides a deep dive into the concept of an AI agent harness, which is a control layer or scaffolding designed to manage complex, long-running tasks for artificial intelligence agents. It explains how these harnesses enable agents to plan, execute, and save progress externally to overcome the limitations of standard context windows and one-shot prompting. By moving away from simple instructions and toward a structured architectural approach, developers can build AI systems that are si...

This video covers the implementation of a multi-provider frontend-mix workflow that leverages the specific strengths of Gemini 3.5 Flash for UI design and Claude Opus 4.8 for logic and reasoning. By routing different stages of a full-stack web application build to different AI models, developers can overcome the limitations of single-model development, such as hallucinations in page copy or poor visual aesthetics in generated interfaces. The process utilizes eight distinct stations and markdown-...

This video covers the transition from static AI harnesses to dynamic workflows in Claude Code, explaining how Anthropic uses multi agent systems to solve complex problems. By generating task specific architectures on the fly, users can bypass traditional limitations of large language models. The content explores the technical foundation of these workflows, the specific architectural patterns that make them effective, and practical ways to implement them for both coding and general knowledge work...

In this insightful interview set in the year 2026, Sarah Friar, the CFO of OpenAI, outlines the company's path toward becoming an all encompassing intelligence utility. The video covers OpenAI's record breaking 122 billion dollar funding round, their strategic approach to an IPO, the shift toward multi vendor infrastructure, and the upcoming launch of a human centric hardware device. It explores how OpenAI manages the massive capital requirements of compute while striving to make intelligence a ...

Claude Code Dynamic Workflows are a powerful tool for developers who need to manage massive, multi-part projects using the Anthropic Claude ecosystem. Introduced in the 0.4.8 update, this feature allows the model to generate and execute JavaScript-based scripts that orchestrate dozens of subagents to work in parallel. Instead of waiting for a single agent to process a large file structure linearly, a workflow can spin up worker agents (typically using the faster and cheaper Haiku model) to handl...

This video covers the practical mastery of Claude Code, Anthropic's terminal-based agentic AI assistant. It provides a deep dive into installation, environment optimization, advanced context management, and the use of the Model Context Protocol (MCP) and SDK for professional software development workflows. This guide is essential for engineers who want to move beyond simple code completion to full-feature agentic development. ## Key Takeaways * **Agentic vs. Completion:** Claude Code is not a c...

This video features Michael Grinich, founder of WorkOS, at MCP Night, where he outlines the transition from human-led AI development to autonomous agentic software. The presentation introduces auth.md, a new open specification designed to solve the critical problem of how AI agents register for and authenticate with web services without human intervention. By exploring the architecture of the 'Agent Harness' and demonstrating live agentic registration with partners like Cloudflare and Firecrawl,...

The video provides a deep dive into Redis Iris, a newly announced end-to-end context engine designed to power the next generation of AI agents. It covers how Redis Iris addresses the shortcomings of traditional RAG (Retrieval-Augmented Generation) by providing a high-speed, real-time knowledge layer that mirrors operational data. By moving away from simple vector search and toward a structured, navigable context layer, Redis Iris allows AI agents to reason over business entities like customers, ...