Codex 2.0: NEW AI SEO Super Agent is INSANE!
The video demonstrates how to use OpenAI's updated Codex tool for AI-driven SEO, including building websites, automating blog post creation, conducting keyword research, and deploying content via Netlify. The presenter claims to have grown multiple websites from near-zero to hundreds of daily clicks using this method. Five specific use cases are outlined: keyword research, website building, blog post automation, SEO tool creation, and client presentation generation.
Summary
The presenter opens by showcasing real-world SEO results attributed to the methods being demonstrated, including websites growing from near-zero to 100 and 498 clicks per day respectively. The core tool being featured is OpenAI's Codex, which received a major update that the presenter says makes it accessible to non-coders for the first time — a significant shift from its previous developer-focused identity.
The first major use case covered is building SEO tools directly within Codex, such as a keyword difficulty and traffic value calculator. The presenter walks through setting up a project folder inside Codex, which acts as a repository for generated website files and blog posts. The new update is highlighted as being 27% faster, and a 'full access' autonomy setting is introduced that allows Codex to code, write, and deploy content without manual intervention.
The presenter then demonstrates creating a blog and landing page from scratch by feeding Codex product or service details, showing how it generates a complete website in approximately 3 minutes. An automated scheduling feature is also showcased, allowing users to set daily tasks — such as publishing a new blog post targeting a low-competition keyword every morning at 9 a.m. — without any ongoing manual effort.
For keyword research, the presenter uses Codex's 'computer use' capability to navigate to Ahrefs in a browser autonomously, perform keyword searches, and extract ranking opportunities — all without requiring a paid Ahrefs login, by utilizing the free keyword generator tool. The presenter notes that multiple Codex agents can run in parallel, handling keyword research, blog design, and tool creation simultaneously.
Content creation is further refined by injecting first-person perspective prompts and real case study data into Codex, resulting in more personalized, business-specific blog content. Deployment is handled via Netlify, where a personal access token is given to Codex so it can autonomously publish and update websites. The presenter also mentions building a custom indexing tool using Omega Indexer's API to ensure new content gets indexed by Google quickly.
A fifth use case — creating PowerPoint presentations for SEO agency client meetings — is briefly demonstrated. The video closes with a promotion for the presenter's paid community, the AI Profit Boardroom, and a free SEO strategy session offer.
Key Insights
- The presenter states that the new Codex update is specifically designed for non-coders, marking a fundamental shift from its original developer-only audience, which he argues makes it extremely powerful for anyone pursuing Google and AI search engine traffic.
- The presenter claims Codex can generate a complete blog and landing page from a product description in approximately 3 minutes, attributing this to the update being over 27% faster than the previous version.
- The presenter demonstrates that Codex's 'computer use' feature can autonomously navigate to Ahrefs in a real browser, run keyword searches, and extract ranking opportunities — and that it found and used Ahrefs' free keyword generator without requiring a paid account login.
- The presenter argues that injecting first-person perspective prompts and real case study data into Codex produces more customized, higher-quality SEO content that is more closely tied to the creator's actual business results.
- The presenter recommends using Netlify with a personal access token given directly to Codex, allowing the AI agent to autonomously publish and update website content across multiple sites without any manual CMS interaction like WordPress.
Topics
Transcript
[0:00] Codeex has a massive update from open today. It makes it insanely powerful for AI SEO. I'm going to show you exactly how this works. And this is based on what's working for me. You can see, for example, this website has gone from like pretty much zero clicks a day all the way up to here. Like so. Here's another example of a website popping off using the same method. You can see this website went from like two clicks a day all the way up to nearly 100 a day. And this website as well has gone from pretty much nothing to over 498 clicks [0:33] per day. So I'm going to break down exactly how you…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
NEW Nvidia Autonomous AI is WILD!! 🤯
Nvidia announced Nemo Clo, a new autonomous AI agent system that operates independently without continuous prompting. Powered by Nemotron 3 Ultra (a 550 billion parameter model), the system is five times faster and cheaper than previous versions, with OpenShell providing secure sandboxed execution.
Laguna XS 2.1: New FREE + Opensource Local AI!
Julian reviews Laguna XS 2.1, a new free open-source local AI coding model from Poolside that performs comparably to Qwen 3.6 and outperforms Claude Haiku on benchmarks. He demonstrates its practical capabilities by building landing pages and functional apps, highlighting its speed, offline functionality, and multiple deployment options through local setup, Claude Code, or OpenRouter's free API.
How to Run Hermes FREE Forever!
The video demonstrates how to run the Hermes AI agent for free using Gemma 4, a local open-source model from Google, with significant speed improvements through MLX optimization. The setup works on Apple Silicon Macs or via free APIs on Open Router, enabling autonomous agents to work offline and privately without subscription costs.
This NEW Chinese AI is INSANE! (FREE + Open Source!)
Long Cap 2.0 is a new open-source Chinese AI model from a food delivery app company that offers 1 million tokens of free context memory, beats GPT-4.5 on SWE bench pro benchmarks, and uses efficient parameter activation to reduce computational overhead while maintaining high performance.
Claude Code is now FREE: Here’s how…
Google's new Gemma 4 model running on Ollama is 90% faster on Apple Silicon, enabling free Claude Code usage locally without token costs. The setup requires three simple steps: downloading Ollama, Gemma 4, and installing into Claude Code, with alternatives available via OpenRouter API for non-Mac users.