
Non-Technical Founder: Don’t Need to Know How To Code. You Need to Start - Ben Tossell
Ben Tossell thinks of his personal AI agent as a folder: context he can open, inspect, edit, and take to another model. When its memory started holding on to too much old information, he pared it back. In this outdoor conversation with Michael Galpert, Ben explains how he makes AI useful through small experiments. They discuss the animated mascot on his personal site, learning coding concepts visually, and an email client he built before realizing that labels and archiving were what he actually wanted. In this episode: • Learning by playing and asking basic questions • Building prototypes you can throw away • Making technical vocabulary easier to understand • Steering coding agents as the work develops • Keeping personal context portable and inspectable • Deciding what an agent should remember or forget • Starting instructions with one line and adding only what is needed • Building small tools for yourself without turning every idea into a company Ben’s examples show how experimenting can lead to a smaller, more useful system than the one you first imagined. This is his evolving approach to personal AI, including the friction and bugs that come with it. About Already Here: Michael meets people already living with personal AI in everyday life. The conversations explore what changes in how people work, make decisions, and direct their attention. Follow him on x: https://x.com/msg Subscribe for more conversations with people already living with personal AI. What small tool would you build for yourself? Referenced tools, people and background: Ben's Bites: https://www.bensbites.com/ Ben personal site: https://bentossell.com/ Josh Puckett: https://joshpuckett.me/ Matt Pocock dictionary: https://github.com/mattpocock/dictionary-of-ai-coding Index: https://index.how Pi coding agent: https://github.com/earendil-works/pi Factory / Droid: https://factory.com/ Codex: https://openai.com/codex/ BB: https://getbb.app/ Claude / Opus: https://claude.com/product/overview Claude Code: https://claude.com/product/claude-code ChatGPT: https://chatgpt.com/ GLM / Z.ai: https://chat.z.ai/ OpenRouter: https://openrouter.ai/ Latent Space / OpenRouter episode: https://www.latent.space/p/openrouter Pragmatic Engineer / Matt Pocock: https://newsletter.pragmaticengineer.com/p/ai-skills-with-matt-pocock Matt Pocock skills: https://github.com/mattpocock/skills ASD Simplified Technical English: https://www.asd-ste100.org/about_STE.html Muse: https://about.fb.com/news/2026/09/introducing-muse-personal-ai-agent/ Dots: https://help.openai.com/en/articles/20001530-getting-started-with-your-dot Grok Bot: https://x.ai/bot Karpathy LLM Wiki: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f Instinct: https://instinct.com/ Google Drive: https://workspace.google.com/products/drive/ Makerpad background: https://techcrunch.com/2021/03/08/zapier-buys-no-code-focused-makerpad-in-its-first-acquisition/ Superhuman: https://superhuman.com/ Gmail: https://workspace.google.com/products/gmail/ Google Workspace CLI: https://github.com/googleworkspace/cli Cognition: https://cognition.com/ OpenAI Sol models: https://openai.com/index/introducing-gpt-6-1-sol/ OpenAI Astra: https://openai.com/index/gpt-6-astra/ AGENTS.md: https://agents.md/ Model Context Protocol: https://modelcontextprotocol.io/








