# The Three Ways of Working
Source: https://humanspark.ai/frameworks/three-ways-of-working/

*You use a product, you direct a tool, you run a service - whose hands are on the work, and are you in the room?*

**When to use:** When placing any piece of AI work - and weighing what you take on if you move it: whether it acts or only produces (Produce vs Act), and where it runs.

Use → *Product* · Direct → *Tool* · Run → *Service*

Nothing about the model changes. Your relationship to it does.

Use → Product

Your hands on the work, AI advising.

Direct → Tool

Its hands on the work, your eyes on it.

Run → Service

Its hands on the work, nobody watching live.

Same engine, three arrangements: Claude in the chat app is a product; Claude Code under your direction is a tool; Claude Code on a schedule is a service.

> **The unattended tool:** A tool left running unattended is not yet a service - it carries a service's risks without a service's checks. A service is built for your absence from the start: checking designed in, permissions bounded, escalation defined.

> **A map, not a ranking:** Most work belongs at product and tool, some of it permanently; services suit narrow, high-volume, well-bounded work. Judge each piece of work from where you sit.

> **Not to be confused with:** Not the [Permission Ladder](https://humanspark.ai/frameworks/the-permission-ladder/): the Ladder sets how much autonomy you permit a task to have; the Ways say who does the work and who watches. They cross - deep research is Run-level permission inside a product. Not the [Implementation Tiers](https://humanspark.ai/frameworks/three-implementation-tiers/): the Tiers say how you source AI; the Ways say how you work with it once it's there. Not [Where Does It Run](https://humanspark.ai/frameworks/where-does-it-run/): the Ways describe your relationship to the system; venue describes where its two parts sit.