Nate Herk | AI Automation
Hi 👋 I'm Nate Herk. I’m passionate about helping businesses unlock the power of AI Automations to save time, cut costs, and stay competitive. I believe that businesses that don’t adopt AI will struggle to keep up, and I’m here to make sure you’re ahead of the curve. Whether you’re new to AI or looking to refine your workflows, I’m here to guide you through it all. Let’s build a more efficient future together! Book a call on my website!
AGI is Here. Anthropic Just Proved It.
The video argues that artificial general intelligence is already here in practical, open-ended problem solving, driven by Enthropic’s internal data and the rapid capabilities of Claude. It explains how AI is moving beyond narrow tasks to autonomous research, code generation, and decision making, outlines three future scenarios (stagnation, continued gains, and true self-improving AI), and discusses societal impacts, the rush of labs to advance, and why alignment and cautious progress matter.
The Skill That 10x’d My Claude Code Projects
The speaker explains how to convert tacit knowledge into a reusable AI-enabled OS by using a 'grill me' workflow that relentlessly extracts details and checkpoints them into structured docs. He demonstrates creating QA logs, decision notes, and brainstorm folders, showing how upfront questioning and context-building improve skills, context, and project outcomes. The process emphasizes iteration, documentation, and linking prompts to ensure the AI reflects the user's voice and decisions.
I Tested Every Claude Code Feature, These 12 Are the Best
The speaker breaks down Claude features by tier (D to S) based on how much they actually affect daily work, then dives into his top 12 features with practical notes. He emphasizes Claude Code as his executive AI OS, praises tools like /goal, /loop, agent teams, sub-agents, status line, and skills, and shares how他 leverages cloud, desktop, and CLI workflows to streamline knowledge work, planning, and automation.
100 Years of Artificial Intelligence Explained
The video traces the 100-year arc of artificial intelligence, from early code-breaking and the birth of AI as a field, through the rivalry between symbolic and neural approaches, to the modern surge in deep learning driven by data, GPUs, and big tech investments. It highlights pivotal milestones—Enigma, perceptrons, backpropagation, ImageNet, AlexNet, transformers, and today’s AI tools like Claude, Copilot-like cloud coding, and large-scale consumer and developer AI platforms—showing how breakthroughs in both theory and hardware propelled AI from a fringe idea to a ubiquitous force.
How to Actually Use Claude Code Dynamic Workflows
The video dives into Claude Opus 4.8.8 and the new dynamic workflows feature, explaining how skills, sub-agents, agent teams, and workflows fit together to run many agents in parallel. It covers practical use cases, cost considerations, and how to choose between skills, sub-agents, agent teams, goals, and dynamic workflows, plus tips for managing scope, avoiding token waste, and safely coordinating large, multi-agent processes.
Opus 4.8 Just Dropped. Here's How To Actually Use It.
A quick analysis of Claude Opus 4.8, focusing on what's new over 4.7 and how it changes usage, pricing, and expectations. The video covers new features like dynamic workflows in Cloud Code, adjustable effort levels, and improved honesty and autonomy, while stressing that benchmarks aren’t the sole measure of usefulness for your specific use case. It also offers practical prompting guidance, emphasizes tuning effort levels, and advises validating with real workflows rather than relying solely on tests.
I Turned Claude Opus 4.8 Into My Entire AI Operating System
The video introduces Claude Opus 4.8 as a transformative AIOS (AI operating system) and explains how the speaker uses it as a second brain to run multiple businesses from a single VS Code workspace. It outlines the four Cs framework (context, connections, capabilities, cadence), discusses mindset shifts, and shares practical steps—like adopting cloud code, building reusable skills, and organizing files—to achieve peak productivity, plus a free GitHub repo and course to get started.
100 Hours Testing Claude Code vs ChatGPT Codex (honest results)
The video compares Claude Code and OpenAI Codex, evaluating which is better for coding across features, pricing, and three concrete use cases. It highlights Claude Code’s deeper customization and workflow capabilities versus Codex’s unified, end-to-end execution, and ends with practical guidance on when to use each tool based on your task.
The Playbook for a $100M AI Agency
This interview with Devin Karns explores the evolving economics of AI-enabled services, arguing that the value lies less in doing bespoke development and more in scalable, enterprise-oriented solutions and AI-native organizations. It covers how mid-market and SMB players can pivot from traditional agency models to higher-value offerings (workshops, discovery, fixed-price playbooks, and performance-based models), the importance of upfront business cases, repeatable processes, and building an exit-ready enterprise, while emphasizing credibility, specialization, and strong client relationships.
The AI Offer You Can Sell Tomorrow Morning
Nate argues that in 2026 AI consultants should start by selling hours—helping business owners set up an AI operating system—before aiming for audits, projects, or retainers. He reframes the AIOS as a repeatable product, lays out a seven-step ladder to land clients, and shares practical strategies for onboarding, pricing, client relationships, and building in public while managing impostor syndrome.
The One Habit That Doubles Your Claude Code Session Limit
The video explains how prompt caching and token caching work in Claude and Claude Code, showing how cached tokens can dramatically reduce input costs and speed up responses within TTL windows. It covers the architecture of caching at system/project/conversation levels, what factors break caches (like model switches and long gaps), practical tips to manage sessions (including /compact, /clear, and session handoffs), and points to a free token dashboard and resources to help users optimize token usage.
What Karpathy Joining Anthropic Actually Means For Claude
The video analyzes Andre Carpathy’s move to Enthropic and what it signals about the AI industry, arguing the real story is how wrappers around models—data, context, and workflows—become the true products. It highlights Enthropic’s momentum (including a new enterprise services venture) and three predictions: Enthropic will build a context/app-store ecosystem, offer an education layer to package workflows, and enable broad participation from domain experts to enrich a context marketplace. The speaker emphasizes that success hinges on transforming data and processes into usable, ROI-driving automation rather than focusing solely on model performance.
Get daily AI recaps from
Nate Herk | AI Automation in your inbox
Get AI-powered summaries delivered to your inbox. Save hours every week while staying fully informed.