OpenAI's coding agent, run at GPT-5.5 'extra high' — the course's pick when back-end correctness matters more than looks.
| Session | Coverage | Moment | What happened |
|---|
| Basecamp 3: Introduction to n8n — I | demonstrated | 2:30:17 | GPT-5.5 'extra high' produced the better JSON with native Firecrawl nodes; also the error-fix loop; trainer mixes Codex with n8n to build workflows |
| Basecamp 4: Introduction to n8n — II | demonstrated | 2:21:38 | GPT-5.5 'extra high' with live preview; strong back end, average front end; repo pushed for learners; trainer's YC early access; also his n8n-local-install helper; has 'pets' feature |
| Community Session II: The Meta-Harness — Praful Thakkar on AgentGrid, Orchestrator-plus-Workers on One Canvas, Hand-Off Between Models, and OAuth Instead of API Keys | demonstrated | | Orchestrator pane, reasoning extra high |
| Build Reliable AI Apps Using LangGraph: The Travel Agent That Changes Its Mind — State, Nodes, Cycles, Interrupts, and Why the Vocabulary Is the Skill | demonstrated | | The build environment. GPT-5.6 on medium, then Saul Light, then a data model at extra-high effort. Screenshot attached as context, plan mode used belatedly, and TWO accounts exhausted on usage limits during the session. |
| Office Hours V: Paul's Compliance Scanner Meets Firecrawl, Painkillers vs Vitamins, What a Real Second Brain Costs, and Why Selling Got Harder | demonstrated | | GitHub connection in plain English |
| Session 3: Building Elegant Landing Pages | demonstrated | 0:09:38 | The session's workbench end-to-end: projects, GPT-5.5 reasoning tiers, files/browser/terminal panel, git auto-tracking, skill installs, automations, plugins; his team migrating to it from Claude Code |
| Session 4: How to Build Micro Prototypes | demonstrated | 1:37:55 | Open-existing-folder projects, 'enable git and push', run-the-server local preview (localhost:8080), commit/rollback demo, prompt queueing, multiple windows (4 apps at once) |
| Session 7: The Outreach Engine | demonstrated | 0:45:35 | Built both skills live ('GPT 5.5 extra high'); chosen because it writes files straight to his desktop — also organizes his desktop weekly |
| Session 8: The Conversion Playbook | demonstrated | 1:16:34 | Rebuilt his live /consulting page mid-session, created the /coaching short redirect, installed the tracking pixel (head injection), built the ICP-finder skill — all pushed live via GitHub |
| Session 14: Claude Code — Advanced Workflows | demonstrated | 0:09:22 | His own studio shown: one autonomous 1d 1h 17m run on 'GPT 5.6 Sol' (as heard); YouTube API auto-publish configured |
| Session 15: Loop, Harness & Graph Engineering (posted as 'Securing Vibe-Coded Apps') | demonstrated | 2:49:59 | /goal available; /loop not (as stated); starring as the different-model JUDGE in his graph — agent-evals bias argument |
| Session 18: Nano Banana + Veo 3.1 Multi-Shot Video — UGC Genie, an AI-UGC Product Built Live | demonstrated | | GPT-5.6 Sol light for speed; annotate tool, in-app browser (Atlas absorbed), side chat, agent's own cursor doing browser checks |
| Session 19: Content Strategy Pipeline — the YouTube Growth Stack, Built by an Agent Team of Chats | demonstrated | | Orchestrator + sub-chats + worktrees + /side chat + status mini-sites; running on API credits, not the app plan |
| Session 20: Complete LinkedIn Agency Automation — Carousels + Newsletter from One Content System | demonstrated | | GPT-5.6 extra-high for planning, Sol light for speed; multi-chat delegation incl. the GitHub force-push chat |
| Session 21: Advanced Data Extraction from PDFs — Parsing, OCR, and the Token-Free Product | demonstrated | | Build agent: brainstorming skill, writing-plan skill, spec docs, thin adapter, three parallel chats by session's end |
| Session 22: Automate Admin Tasks — Advanced RAG (Enterprise 'Internal Perplexity' Built Live) | demonstrated | | Primary build agent; queueing, steering, side chats, Connections-to-VPS all demonstrated; worktrees puzzled over live |
| Session 23: Automating AEO/GEO — Audits, the File Layer, and Evidence-Led AI Search | demonstrated | | The working agent throughout — skills, audits, fixes, the tool build; GPT-5.6 tier switching live |
| Session 24: Building a Marketing OS — Sector-Agnostic Command Center on an Open-Source Stack | demonstrated | | The recovering agent: reads the handover, one-shots the mini-site + Velora build, drives PostHog/dashboard integration |
| Session 25: Product Hunt Launch Playbook — Engineering as Marketing, Rules That Get You Banned, and a Real Launch Scheduled Live | demonstrated | 1:17 | 'Terra Lite' mode; built /apps page, brief, icon, embed |
| Session 26: Product-Led Activation & Lifecycle Growth — Turning a Free Tool into a Growth Machine | demonstrated | 0:41 | Primary build agent, 0.147->0.151, repeatedly stalling on stream |
| Session 27: Lead Magnets as Proof Artifacts — the Mega-Prompt Build, Four Live Magnets, and the Skill That Packages the Workflow | demonstrated | | Build engine for every magnet; Medium vs Ultra reasoning |
| Make Websites Agent-Ready with WebMCP: Front-End Tools for Browser Agents, the Tool Menu, MCP vs WebMCP, and a New Service Offer | demonstrated | 0:21 | Browser agent used for all three demo branches |
| Building a Mobile App with AI: React Native and Expo with Codex, One Screen at a Time, Clerk Login with Supabase Progress, and a Mascot That Makes It a Product | demonstrated | 0:12 | Coding agent for every build step; skill-creator used to make the mobile app skill |
| How to Build Vertical Harnesses: The Car Analogy, a Reusable Folder Template, and Live Builds that Print a Keycap, Replace a TV's Bloatware, and Reach Physical Devices Over SSH and Tailscale | demonstrated | 0:33:00 | CLI and app; main build tool; open-source harness |
| AI Sprint: The Hermes Agent — Day 1 (Always-On Agents, the Employee-on-Day-One System, and the Self-Improving Ghostwriter) | demonstrated | | The harness: installs Hermes, wires Ollama, researches file conventions, fixes keys, debugs, and finishes the image skill when Hermes stalls |
| Understanding Jev, the AI Built for Decisions (Sprint Day 2): Two Second-Brain Systems - a Leadership Self-Review Built Problem-First, and a Tag-Classifying Knowledge Base Where a Cheap Decision Model Replaces a Chat Model | demonstrated | | Project on a new folder; docs checks; builds the MVP |
| AI Sprint: Build Your Own AI Skills - Day 1 (Solve It Three Times Before You Build the Skill, Prompt / Skill / Project Rule, the Video-Restoration Walkthrough, and the Two-Skill Voice-Then-Deslop Pipeline) | demonstrated | | Both worked examples run in Codex / the ChatGPT app with GPT-6 Luna, 6.1 Sol and Astra |
| Office Hours I: Vetting an Idea, Niching Against the Frontier Labs, and Paul's Aircraft-Parts App (PWA, and 'What If I Get Hit by a Bus') | explained | | Recommended over the $20 Claude plan for coding |
| Mentor Session XV: Selling Beats Building - Paul's Referral-Network Platform, Phone-Book Outbound, Give-First Communities, One Use Case Not a Hundred, and 'Know Thyself' | explained | 1:08:00 | Harshit's daily agent on the Max plan |
| From Learner to Business Owner: an Alumnus on Interviewing the AI First, Criticising Plans, Free First Projects, and Working from Telegram | explained | 0:36 | His recommended builder for cost; used in the prompt and by his agent |
| Weekly AI Updates - October 2026 digest (Oct 7 so far: Gemini 4 'Argon', America.gov AI, Meta Muse, NVIDIA OpenShell, Grok Bot rewards, Copilot teammates, Claude Sonnet 5.5 deep dive; Mark Palmer's GBox showcase; Oct 14 so far: Google Health Coach, the White House frontier-AI accord, OpenAI Dev Day 2026, Anthropic's Oct 8 usage-policy update, Hark, Microsoft MAI voice models, Claude Haiku 5.5) | explained | | |
| Community Session 1: Causa Claims — a Non-Coder's Five-Agent Construction-Claims Pipeline, the Gate as the Product, and What RAG Really Costs | mentioned | | ~$100/week subscription, hackathon requirement |
| Office Hours III: Backing Up Claude Chats with Obsidian, Bridging Chat and Cowork, What Fable Is For, and the Context-Rot Problem | mentioned | | Token-heavy; '@codex' as a Claude Code sub-agent, untested |
| Office Hours IV: PostHog over Plausible, the Launch-Fast Loop, Scraping Ethics, Agent Swarms with Memory, and Why You Never Give Credits Away Free | mentioned | | GPT-5.5 extra-high, unattended for hours |
| Office Hours XII: Building Paul's Second Brain — the Full Project-Management System, Live | mentioned | 0:37 | Runs keyless in Hermes - the asymmetry the harness fixes |
| Office Hours XIII: Ponytail, Ten Hermes Instances, a Web-MCP Verification Layer, and CodeRabbit | mentioned | 0:32 | 28-hour hackathon build; slow |
| Office Hours XIV: Story Before Landing Page, Scoping an Agentic-Web Pitch, the Cost of Compute, Automating Past Google, and the Idea Bank | mentioned | 1:10 | Same; good compaction |
| Session 9: Introduction to Cursor & its principles | mentioned | 0:37:46 | This month's main; local-system access (no sandbox); can open its own browser past CAPTCHAs |
| Session 11: Overview of Claude Code & Key Concepts (Installs, Modes, Context Files, Skills, Hooks & MCPs) | mentioned | 2:09:02 | Named competitor (OpenAI); can't nest inside Claude Code, though GPT models can be used within it |
| Session 30: C3 Town Hall — Four Cohort Products Under the Knife, Outcome Selling, and the Rest of the Programme | mentioned | | Stephen runs a business premium plan alongside Claude Max; Syed uses it to verify skills before listing them. |
| Adding Beautiful Animations to Your App: Splash and Onboarding, State-Driven Micro-Interactions, an AI Layer That Never Blocks, PostHog Funnels and Feature Flags, and the Road to the Stores | mentioned | 0:11 | Same |
| Founder Stack Ep02 with Tanmay: Nothing Starts Where It Ends - Win the King, Start as a Service and Productise as You Go, Tech Is Not a Moat, Where Your Buyers Already Are, and Throw More Darts | mentioned | 2:18:00 | |
| Founder Stack Ep03 with Shai Krishna: Why Wrappers Make AI Slop - CLAUDE.md as the Brain and DESIGN.md as the Art Direction, Founder-Led UGC with AI Avatars, Trial Reels, and Email Journeys | mentioned | 0:47:00 | |
| Business - Five Steps to Paid Work, Specialise 90/10, Hormozi's Four Ways to Get Clients, the Free-Video Offer, Cold Outreach With Claude Cowork, the Pricing Calculator ($100/$200/$300 an Hour), a Website on Netlify in Half an Hour, and Keywording Stock Footage With ChatGPT | mentioned | | Named as the ChatGPT alternative to Cowork |
| AI Sprint: Meet GrokBot — Stop Prompting, Start Delegating (One Cloud Computer, a Chief of Staff, Four Specialist Bots, and the Reversible/Irreversible Rule) | mentioned | | Supervised coding comparison |
| AI Sprint: The Hermes Agent — Day 2 (Loop Engineering: the Scheduling Loop, the Delegation Loop, and the Skill Auditor) | mentioned | | Sub-agent delegation target in Hermes' skill pack; 'Codex doesn't have sub-agents, I think' aside |
| AI Sprint: The Open Source Playbook — Day 2 (Weights 101, OpenCode, and the Subsidy Math) | mentioned | | The other 50%; also 'does parallel sub-agents very well' |
| AI Sprint: AI Evals & Reliability — Day 2 (Testing Systems That Never Answer Twice) | mentioned | | The other tool behind the certificate generator |
Codex (OpenAI)