# Use private AI for sensitive topics

Practice ID: 9
Topic: `ai` (AI: Boundaries that keep AI useful without surrendering sensitive context, memory, or system access.)
Added: 2026-09-01
Journey entry point: `optimize` (Improve ownership, resilience, privacy, portability, and maintenance across the chosen system.)
Start with: `technical` (technical)
Supports: `privacy-clarity` (privacy clarity; group: `digital-control` / My data and digital setup), `visible-ai-boundaries` (AI with visible, owned boundaries; group: `ai-boundaries` / My use of AI)

## Pattern

Sensitive context belongs only in AI systems with privacy boundaries that match the risk.

## Practice

Use private, preferably local AI for sensitive topics, or remove the sensitive details before involving a remote model.

## Start small

For one sensitive task, use a privacy-first AI assistant or a model that runs on your own device.

## Watch out

Local execution still depends on the security of the model, interface, logs, extensions, and host system.

## Concepts

- [local-first](https://live.freewith.tech/concepts/local-first.md): Sensitive or durable information stays under personal control before remote convenience is added.

## Related videos

- [things I don’t tell AI](https://fwt.wtf/ai-is-not-a-friend?utm_source=live.freewith.tech)

## Continue

- [See more in AI.](https://live.freewith.tech/?topic=ai#practices)
- [Journey](https://live.freewith.tech/journey.md)
- [Concepts](https://live.freewith.tech/concepts.md)
- [Complete agent-readable database](https://live.freewith.tech/llms.txt)