# EP.001 - The Tools We Actually Use
## Show Notes
Chris Shanku and Sash Mohapatra kicked off Human in the Loop by doing what the show is built around: opening their actual systems and walking through them live. No slides, no pitch decks, no sanitized demos. Just the real thing.
Sash showed Nuro - his Claude Code-based personal assistant that runs on his Mac. CLAUDE.md as a master identity file, Claude-managed memory, domain-organized working files, and real integrations: email, Granola for meeting notes, n8n for automations, Perplexity and X for search. The newsletter automation alone was worth the episode - Nuro drafts his Sunday edition on Saturday night and posts it to Slack for review. The whole thing runs while he is asleep.
Chris showed TheGrove - a personal AI operating system running on a Mac Mini. Organized into domains covering everything from client work to life admin to co-parenting. A full SDLC workflow baked in: scope, plan, build, test, close. Specialized agents for front-end, back-end, design, red team breaking, and fresh-eyes review. Every sprint auto-documented and pushed to GitHub. What made this interesting was the reveal: Sash and Chris had never seen each other's systems before going live. They independently landed on nearly identical architectures - central agent identity, domain organization, specialized sub-agents, skills in Git. That was not planned. That was the whole point of the episode.
## Takeaways
- Structure your AI system around domains that match how your life actually works, not how a productivity book says it should - Use a CLAUDE.md or equivalent identity file as your central agent's source of truth - it holds context everything else inherits from - Automate the review step, not just the output - Nuro writes the newsletter, but Sash reviews it in Slack before it sends - Put your skills and working files in Git - it keeps multiple machines in sync and gives you a recoverable history of how your system evolved - Build specialized agents for distinct roles rather than asking one agent to do everything; a red team agent with no context will catch what a helpful agent never will
## Key Moments
- 05:20 - Sash walks through the Nuro system architecture: CLAUDE.md, memory files, project organization - 07:30 - Nuro's newsletter automation - Saturday night draft, Slack review, Sunday send - 09:50 - Chris shows TheGrove, starting with the domain structure and the Mac Mini setup - 11:30 - The SDLC workflow and agent roster, including the red team breaker agent - 13:30 - Neither host had previewed the other's system - they compare them live and find near-identical designs
Key takeaways:
- Structure your AI system around domains that match how your life actually works
- Use a CLAUDE.md or equivalent identity file as your central agent source of truth
- Automate the review step, not just the output
- Put your skills and working files in Git for sync and history
- Build specialized agents for distinct roles rather than one agent for everything
Watch the video version on YouTube · Full show notes, transcript + takeaways
