System-wide voice dictation that types where your cursor is — how trainers talk to Claude Code instead of typing.
| Session | Coverage | Moment | What happened |
|---|
| Session 13: Claude Code — Skills, Sub Agents & the Token Economy (posted as 'Beyond Vibe Coding — n8n & More') | demonstrated | 1:18:23 | Voice input to Claude Code; garbled the first business description — retyped |
| Day 1: The Magic Prompt Formula, a Toolkit Tour, Thinker-and-Doer Data Analysis, the Blind-Men-and-the-Elephant Research Method, and a Living Pitch Deck | demonstrated | | Dictation + snippets |
| AI Sprint: Claude Code with Antigravity — Day 1 (Taste as the Moat, the Muscle-and-Mirror Setup, and the Model Council Build) | demonstrated | | Dictation for the PRD interview — 'I can use Whisper Flow even inside Claude Code' |
| AI Sprint: Claude Code with Antigravity — Day 2 (CLAUDE.md, the 50% Context Rule, and the Sketch-to-App Build) | demonstrated | | Dictation through the brainstorm |
| AI Sprint: The Hermes Agent — Day 1 (Always-On Agents, the Employee-on-Day-One System, and the Self-Improving Ghostwriter) | demonstrated | | The dictation layer for the soul.md/user.md interviews |
| AI Sprint: Windsurf & Devin — Day 2 (Building Superplexity: Plan with Opus, Execute with Cascade, Review with Devin) | demonstrated | | Dictation for the spec interview answers |
| Learning Topics: Sessions 1–5 — Foundations to AI Director | explained | | Toolkit #1 dictation; investment-thesis roast prompt shipped verbatim |
| Basecamp 4: Introduction to n8n — II | mentioned | 1:34:00 | Trainer's open-source, on-device whisper dictation tool (Apple-silicon-only); name garbled, learner-identified in chat |
| 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 | mentioned | | Dictation option in settings; heard 'whisper flow' |
| Office Hours V: Paul's Compliance Scanner Meets Firecrawl, Painkillers vs Vitamins, What a Real Second Brain Costs, and Why Selling Got Harder | mentioned | | Dictate context for an email |
| Office Hours XIII: Ponytail, Ten Hermes Instances, a Web-MCP Verification Layer, and CodeRabbit | mentioned | 0:50 | Voice input on phone for TV agent |
| Session 16: GitHub 101 — Fundamentals & Essentials | mentioned | 1:16:58 | Trainer's dictation tool while composing the escape-room prompt ('I'm using Whisperflow') |
| Session 17: Facebook Ads Competitor Research & Replication | mentioned | 2:49:06 | Trainer's dictation tools aside: FreeFlow named as the free open-source option, slower than the paid one (ASR garbles the names; identities uncertain) |
| Session 19: Content Strategy Pipeline — the YouTube Growth Stack, Built by an Agent Team of Chats | mentioned | | Dictation mishap eats a long prompt — 'I'm using FreeFlow... the free application, not the best' (as-heard) |
| Session 22: Automate Admin Tasks — Advanced RAG (Enterprise 'Internal Perplexity' Built Live) | mentioned | | Voice-input aside — he clarifies which dictation tool he is (not) using (as heard: 'free flow') |
| Day 1: How a Model Learns (Teachable Machine Live), Context Engineering, CO-STAR, Artifacts, Connectors, and Claude Cowork Running a Daily Stand-up | mentioned | | Dictation; 125 wpm |
| Pillar 3 - Your One Person: Write for One, Attract Thousands (the Five Questions and the AI-Drafts-First Variant) | mentioned | | Dictate answers |
| Humanic Deep Dive: Prompt-First Email Marketing - Multi-Email Sequences, Contacts and Cohorts, Gmail Sending, and a Five-Day Course | mentioned | | |
| Day 1: What Makes an LLM an Agent - Planning, Tools, Memory, Actions; Five Design Patterns; and Cursor, Antigravity and Claude Code Live | mentioned | | Trainer's dictation tool |