From skeptic to true believer: How OpenClaw changed my life | Claire Vo
- Source
- lennysnewsletter.com
- Author
- Lenny Rachitsky
- Date

Context
Separating an assistant's responsibilities can make its working easier to manage. Product builder Claire Vo describes using specialized OpenClaw agents for different parts of her life, including separate work and family assistants. Both handle scheduling and administration, but each receives the conversations relevant to its own responsibilities. She attributes the usefulness of this division to avoiding an overloaded, mixed-purpose conversation. It is an account of organizing work; she also notes that agents sharing a computer may access one another's files and tools.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
“In my first install, I truly spent eight hours getting Open Claw up and running. In return, for those eight hours, I got my personal family calendar deleted.”
Claire Vo
“I am a breathless Open Claw bro. It has changed my life.”
Claire Vo
“You really have to pull the thread on these tools and you have to spend enough time with them to see not where they are today, but where they are in a week and where they are in a month.”
Claire Vo
“I won't sugarcoat it. It's a pain to set up. It is not hands off, but the value is so high, I am willing to go through the pain.”
Claire Vo
“I am just hands for the AI at this point. I'm just a vessel of poly at this point.”
Claire Vo
- 00:00Introduction to Claire and OpenClaw
- 08:00The journey from OpenClaw skeptic to believer
- 11:50What OpenClaw actually does that's useful
- 13:35OpenClaw vs. other AI agent products
- 17:05How to actually install OpenClaw: the basics
- 18:49Setting up like you'd onboard a real assistant
- 20:41Security and privacy considerations
- 24:53Live demo: Installing OpenClaw step-by-step
- 28:47Setting up Q: an agent for her kids' homework
- 34:08Understanding soul, identity, and memory
- 40:40The unlock: multiple agents, not just one
- 45:02How to run multiple agents on one machine
- 47:28Jesse Genet's homeschooling use case
- 49:58Real examples and use cases
- 56:41Finn, Claire's family agent
- 1:00:05Sage the Course Bot
- 1:02:15Common issues and workarounds
- 1:08:08The Exa/Perplexity web search workaround
- 1:09:29Memory management and context overload
- 1:12:09Pro tip: Screen sharing to manage Mac Minis
- 1:14:18Using Google Workspace for agent collaboration
- 1:16:24What makes OpenClaw special
- 1:20:15The yappers API and ramble mode
- 1:22:04Using Claude Code as your OpenClaw brain surgeon
- 1:25:16Bringing management skills to AI agents
- 1:29:32Why this matters
- 1:32:37Lightning round and final thoughts
podcastThe 100-person AI lab that became Anthropic and Google's secret weapon | Edwin Chen (Surge AI)
podcastWhy humans are AI’s biggest bottleneck (and what’s coming in 2026) | Alexander Embiricos (OpenAI Codex Product Lead)
podcastThe coming AI security crisis (and what to do about it) | Sander Schulhoff
podcastWhy most AI products fail: Lessons from 50+ AI deployments at OpenAI, Google, and Amazon
videoOpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491Lex Fridman
podcastWhat happens after coding is solved? | Fiona Fung (Manager of the Claude Code and Cowork Teams)Lenny Rachitsky
blogOpenClaw went viral. Meet the maintainers building and securing it.Gregg Cochran
Checking sign-in…
Loading comments…