Jack Roberts

Jack demonstrates a GitHub-based system using Claude Code to generate professional slide decks from any website URL by codifying 20 universal design principles. The system uses Firecrawl to extract brand DNA from websites and can integrate AI-generated images via APIs like Krea.ai. The result is polished, brand-consistent HTML presentations created in minutes with minimal input.

The speaker reflects on their first job at McDonald's at age 17, earning £5 an hour. The most valuable takeaway was the realization that they never wanted to work such a job again, reinforced by calculating how long it would take to earn a million pounds at that wage.

Jack Roberts presents a three-tier Claude memory system designed to give AI tools persistent context across all platforms and sessions. The system consists of short-term identity memory, mid-term project memory via structured folders and claude.md files, and long-term memory using either Obsidian or Pinecone for archiving conversations and expert knowledge. The goal is to eliminate the 'amnesia' problem where AI loses context between chats.

The speaker argues that ads in ChatGPT are not inherently bad, particularly when users are actively seeking product recommendations. They distinguish this as 'pull advertising,' where the user initiates the request and ChatGPT synthesizes results based on provided context.

The speaker argues that AI will not kill agencies because there has always been a gap between possessing knowledge and executing it. People have historically paid others to perform tasks they could learn but choose not to, and this dynamic will continue regardless of the technology involved.

Jack Roberts presents a custom Claude-based AI agent system called 'Gravity Claw' as an alternative to the Hermes AI agent framework, demonstrating how to cherry-pick the best features from multiple AI frameworks rather than being locked into one. He shows how to integrate capabilities like self-generating skills, multi-tier memory, and voice-activated research using tools like Firecrawl and Railway for hosting.

Jack Roberts introduces Open Design, an open-source, locally-run alternative to Claude Artifacts with an Apache 2.0 license, allowing users to use any AI model they choose. The tool replicates Claude's design capabilities while removing usage limits, supporting 71+ brand design systems, and enabling multi-model workflows. Roberts demonstrates building a SaaS analytics dashboard and integrating ChatGPT image generation within the local environment.

The video demonstrates how to combine Claude Code with DeepSeek V4 to reduce AI coding costs by up to 100x. The presenter walks through setting up a proxy repo that lets developers run Claude Code alongside DeepSeek simultaneously, using each model for its strengths: Claude for UI/design and DeepSeek for backend/algorithmic work.

The video demonstrates how to combine Claude Code with OpenAI Codex and Google Gemini CLI to overcome Claude Code's recent performance regression. The presenter shows how to install both tools, connect them via plugins, and use a custom 'three-brain auto-router skill' that automatically delegates tasks to the most appropriate model.

The video outlines a framework for building effective Claude Code applications using 'super skills' inspired by Andrej Karpathy's four limitations of language models. It covers a three-tier system involving skill creation, data connectors, and a memory operating system to improve AI-driven builds.

Jack Roberts explains how to build 'super skills' in Claude Code using Andrej Karpathy's four guiding principles as a foundation. Unlike basic markdown skill files, super skills feature persistent memory, self-improvement loops, and real data connections. The video walks through a four-pillar methodology: proper skill creation, data connectors, a memory operating system, and a refinement loop.

Jack Roberts demonstrates five Claude Code tools that reduce costs and improve AI development workflows: Karpathy's Graphify for codebase knowledge graphs, Firecrawl for clean web scraping, NotebookLM integration for research, Awesome Design for pre-built design systems, and Claude Code Router for routing tasks to cheaper AI models.

The speaker outlines a launch strategy requiring 150 people to express interest before starting, paired with a time-limited discount offer. They emphasize building content and an audience iteratively, arguing that the ability to capture attention is the most valuable skill for any online venture.

A Harvard study found that 15,000 simulations across seven major AI models all produced the same trendy—but not necessarily correct—business advice. The speaker argues this finding is partially valid but misses the point: AI is only as useful as the questions you ask it, and users must critically engage with it rather than blindly delegate decisions to it.

The speaker argues that Gemini is uniquely positioned among AI models because Google doesn't rely on it as a primary revenue source. Unlike OpenAI and Anthropic, Google can treat Gemini as a loss leader, allowing it to focus on building superintelligence without monetization pressure.

The speaker argues that passion is the foundation of sustainable entrepreneurship or creative work. They suggest that loving what you do makes you unbeatable, and recommend keeping a day job while building something meaningful on the side.

The speaker discusses the cognitive bias of falsely transferring expertise from one domain to another. Using a doctor as an example, they argue that being an expert in one field can lead to overconfidence in unrelated fields. The core message is that recognizing the limits of one's knowledge is essential to self-improvement.

The speaker argues that major trends like AI and coding skills are already obvious to those paying attention in 2026. The key differentiator between those who succeed and those who don't is not knowledge, but the willingness to act on clear signals.

The video demonstrates how to integrate Google's NotebookLM with Claude (both Code and Co-work versions) to create a persistent memory system. This combination allows Claude to remember conversations across sessions without token costs while unlocking content creation and research capabilities through NotebookLM's AI features.

Anthropic's Claude Code has experienced a massive leak revealing 5 major unreleased features including Kairos (an always-on monitoring agent), Ultra Plan (30-minute deep thinking mode), a gamified buddy system, Dream memory management, and an undercover mode that hides AI contributions.