Build to Launch

Build to Launch

By Jenny OuyangTechnology
Download on the App Store

Build to Launch episodes

  • ChatGPT dots vs Grok Bot vs Meta Muse: Which AI Agent Wins?

    I tested all three new personal AI agents, ChatGPT dots, Grok Bot and Meta Muse, on my real Gmail, X, Instagram and calendar accounts to find out which one is worth trying first. A personal agent is different from a coding agent like Codex or Claude Code: it works across your accounts, remembers you, and keeps running when you are away. This audio edition covers what each one did well, where each one broke, what each one costs, and which one I would start with. The complete written guide has every screenshot and the exact prices. The video version is on YouTube: https://youtu.be/3RxfWltw8zg

    Episode resource

    Watch the optional video companion

    18 min
  • The ChatGPT App: Four Jobs Claude Couldn't Do

    OpenAI folded Codex into the ChatGPT desktop app, so I handed it four real jobs I hadn't been able to finish reliably in Claude: editing my first YouTube video, turning that video into an automated podcast, making my short-form Notes system visible enough to debug, and finding and restoring a task I had buried by accident. This audio edition walks through what each job produced, the interface details that made me stay, and why I kept both ChatGPT and Claude on one shared system underneath instead of switching. The full written build is in the companion Build to Launch article.

    Episode resource

    Watch the optional video companion

    13 min
  • Obsidian + Claude: The Second Brain That Remembers

    I turned my Obsidian vault into a connected memory layer Claude can read and update. This audio edition explains why Markdown, WikiLinks, properties, and Obsidian's index matter; how a 4,663-file test ran about 60 times faster through the index; and what changed when Claude could retrieve decisions, link new work, and write results back. The full implementation stays in the companion Build to Launch article.

    Episode resource

    Watch the optional video companion

    14 min
  • Hermes Agent Review: 3 Real Tests That Changed My Mind

    I gave Hermes Agent three real jobs: research, a 47-task backlog, and a broken tool setup. This episode covers what kept working after I stepped away, where the run failed, and the three rules I now use before handing Hermes a bigger job.

    Episode resource

    Watch the optional video companion

    15 min

About Build to Launch

From the publisher's feed

Build to Launch follows Jenny Ouyang as she tests AI tools on real work, keeps the receipts, and turns each result into a system you can use. Episodes cover AI agents, Claude Code, vibe coding,…