---
id: "concept-background-execution"
type: "concept"
source_timestamps: ["00:03:47", "00:10:25"]
tags: ["ux", "os-integration", "parallel-processing"]
related: ["concept-computer-use", "entity-sky-team", "claim-openai-acquired-sky"]
definition: "The ability of an AI agent to perform GUI automation tasks invisibly in the background without hijacking the user's active cursor or window focus."
sources: ["s03-apps-no-api"]
sourceVaultSlug: "s03-apps-no-api"
originDay: 3
---
# Background Agent Execution

## Definition

The ability of an AI agent to perform GUI automation tasks **invisibly in the background**, without hijacking the user's active cursor or window focus.

## The Hijacking Problem

Historically, UI automation tools and early AI agents required complete control of the user's machine. When the agent moved the mouse, the human had to **stop touching their keyboard and mouse** — the agent effectively hijacked the workstation. This made parallel work impossible and turned agents into demo-ware rather than daily tools.

## How [[entity-codex-d3]] Solves It

Alexander Embiricos and the [[entity-sky-team]] built deep OS-level integrations so the agent can:

- Click through one application (e.g. a legacy dashboard or browser) on a virtual desktop or background window
- While the user continues typing in another window (e.g. a Word document) without interruption

This is the architectural unlock that converts [[concept-computer-use]] from theoretical parallelism into a usable, daily workflow.

## What It Required

The speaker argues this is **not a trivial feature update**. It demands deep OS-level wizardry — specifically, mastery of Apple's accessibility frameworks and screen-recording permissions — which is why OpenAI made the acquisition described in [[claim-openai-acquired-sky]].

## Enrichment Caveat

Independent verification of OpenAI's *non-hijacking* Mac GUI automation has not been published. The capability is plausible (Apple's Accessibility APIs and ScreenCaptureKit can support it) but undocumented in OpenAI's public materials at the time of this video.