Build your own local AI hardware setup by choosing the right machines (Mac, DGX, custom PC) and connecting them with Tailscale and an AI agent like OpenClaw for automated model deployment across your network.
Source episode · 13:24
How I AI: Alex Finn's Local AI Fleet and Automated Software Factorywith Claire Vo
From 13:24 to 20:41, Alex Finn connects local machines with Tailscale, has an agent select and install suitable models, and shows the fleet control dashboard. Clip range: 13:24 to 20:41.
A connected local AI fleet with centrally managed model deployments across multiple machines.
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Select machines based on the tradeoff between memory and speed. A Mac Studio with high unified memory can run very large models but with slower response times. A DGX Spark offers a balance for midsize models that need more speed. A custom Nvidia build, like one with an RTX 5090, delivers high-speed inference but is limited to smaller models.
Install Tailscale on all your machines. This creates a virtual private network that allows them to communicate securely, making them accessible to each other and to you from anywhere.
Choose a multi-agent framework like OpenClaw or Hermes to act as the central controller for your fleet. The agent is responsible for inspecting hardware, selecting and installing appropriate models, and coordinating work across all connected machines.
Use a natural language command to instruct your agent to configure a new machine on the network. The agent should connect to the machine over Tailscale, inspect its hardware, select a model that fits its capabilities, and then handle the complete installation and setup.
Hey, OpenClaw, check out the new Mac Studio I just bought. See what the hardware is, find an appropriate model for my use cases, and load it up.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
Log your workouts effortlessly without ever opening a spreadsheet. This workflow uses the Claude mobile app to parse a simple voice note and automatically update your workout tracking spreadsheet in the background.
Create a custom email management interface within Claude to read, triage, and draft replies without opening the Gmail tab. This workflow helps you reclaim focus and compound your learnings by training your AI on every interaction.
Build a fully automated system in Claude to generate personalized, interactive HTML proposals and client onboarding materials, saving hours on administrative work and creating a high-touch experience.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.