A beginner wants local AI agents without exposing private data
A beginner wants to learn how to build and agents without sending personal data to outside tools or services by mistake. The goal is to gain real hands-on knowledge and use the setup for business work such as financial reports, , analytics, and faster project processing.
The main worry is privacy during the learning process, especially when trying unfamiliar tools. A separate MacBook is being considered so AI experiments stay away from personal files.
A cheap dedicated device feels risky because it may hit limits quickly. The specific hardware under consideration is a MacBook M5 with 64GB memory, an 18-core CPU, and a 20-core GPU, or something stronger.
Key points
- The aim is to build and agents while protecting personal data.
- The intended uses include financial reports, , analytics, and project processing.
- A separate machine is being considered to keep experiments away from personal files.
- A cheap device may not be powerful enough for larger local AI work.
- Local AI can reduce API use, but the hardware cost comes first.