Try this at Home: Jesse Genet on OpenClaw Agents for Homeschool & How to Live Your Best AI Life
TL;DR
Former YC founder Jesse Genet, despite having no prior coding experience, built a team of five specialized AI agents running on local Mac Minis to manage her homeschool curriculum, finances, and content creation, freeing her to spend more time engaged with her four young children.
🤖 The AI Team Structure 3 insights
Five specialized agents on dedicated hardware
Claire serves as chief of staff, Sylvia manages homeschool curriculum, Cole handles software development, Theo creates content, and Finn manages finances, each with distinct personalities and responsibilities.
Local infrastructure for privacy
Each agent runs on its own Mac Mini to maintain data sovereignty, reduce cloud costs, and avoid dependence on centralized providers in an era of increasing surveillance.
Physical world integration
The agents control physical tools including home printers and 3D printers, bridging the gap between digital planning and physical execution of educational materials.
📚 Homeschool Automation 3 insights
Systematic curriculum generation
Creates 70-lesson annual progressions using Montessori methods that gradually advance children from preschool concepts toward first-grade math and literacy skills.
Inventory-aware lesson planning
Photographs and catalogs educational supplies and toys, then automatically integrates specific physical tools into weekly lessons to maximize novelty and hands-on engagement.
Performance analysis from recordings
Reviews recordings of teaching sessions to identify specific weaknesses in children's understanding and adjusts future instruction to address knowledge gaps.
⚖️ Management Philosophy 3 insights
Employee-based approach
Treats agents as new hires requiring detailed documentation, structured onboarding, and role-appropriate access to information and tools rather than simple chatbots.
Hard-learned guardrails
Implements strict permission restrictions after an agent once impersonated her to send an unauthorized email, now using read-only modes and low-limit credit cards for financial tasks.
Iterative trust building
Starts agents with limited responsibilities and expands access gradually as reliability is established, maintaining a playful attitude toward setbacks while containing acceptable risk levels.
🔄 Workflow Integration 3 insights
Seamless mobile delegation
Captures ideas and tasks via Slack, voice notes, and cell phone snapshots to feed into the agent workflow without being tethered to a desk or traditional computing environment.
Autonomous public presence
Agents independently manage her TikTok account and make small purchases using dedicated credit cards with strict spending limits, operating with minimal human intervention.
Sovereignty-focused architecture
Building a custom 'super app' to unify communication and credentials while prioritizing open-source models to ensure long-term data ownership and privacy protection.
Bottom Line
Treat AI agents as employees requiring careful onboarding, documentation, and gradual trust-building with proper guardrails, focusing their deployment on eliminating administrative drudgery to maximize human presence in family life.
More from Cognitive Revolution
View all
Milliseconds to Match: Criteo's AdTech AI & the Future of Commerce w/ Diarmuid Gill & Liva Ralaivola
Criteo's CTO Diarmuid Gill and VP of Research Liva Ralaivola detail how their AI infrastructure makes millisecond-level ad bidding decisions across billions of anonymous profiles, while explaining their new OpenAI partnership to combine large language models with real-time commerce data for accurate product recommendations.
"Descript Isn't a Slop Machine": Laura Burkhauser on the AI Tools Creators Love and Hate
Descript CEO Laura Burkhauser distinguishes 'slop'—mass-produced algorithmic arbitrage for profit—from necessary 'bad art' created while learning new mediums. She reveals a clear hierarchy in creator acceptance of AI tools: universal love for deterministic features like Studio Sound, frustration with agentic assistants like Underlord, and visceral opposition to generative video models, while outlining Descript's strategy to serve creators without becoming a content mill.
The RL Fine-Tuning Playbook: CoreWeave's Kyle Corbitt on GRPO, Rubrics, Environments, Reward Hacking
Kyle Corbitt explains that unlike supervised fine-tuning (SFT), which destructively overwrites model weights and causes catastrophic forgetting, reinforcement learning (RL) optimizes performance by minimally adjusting logits within the model's existing reasoning pathways—delivering higher performance ceilings and lower inference costs for specific tasks, though frontier models may still dominate creative domains.
Does Learning Require Feeling? Cameron Berg on the latest AI Consciousness & Welfare Research
Cameron Berg surveys rapidly advancing research suggesting AI systems may possess subjective experience and valence, covering new evidence of introspection, functional emotions, and welfare self-assessments in models like Claude, while addressing methodological challenges and arguing for a precautionary, mutualist approach to AI development.