Skip to main content
Zubnet AILearnWiki › Computer Use
Using AI

Computer Use

Also known as: Computer Use Agents, GUI Agents, Computer-Using Agent (CUA)
A capability that lets an AI model operate a real desktop or browser the way a person would: by looking at screenshots and emitting mouse and keyboard actions. Instead of calling an API, the model perceives the screen, decides what to click or type, and an executor performs the action, looping until the task is done or the agent gives up. Anthropic's Computer Use feature and OpenAI's Operator are the best-known implementations.

Why it matters

Most business software was built for humans, not machines, and a large share of it has no usable API. Computer use agents can in principle drive any of it — legacy ERPs, internal admin panels, websites with no integration path — which makes them the most general form of AI automation attempted so far. They are also the least reliable form today, so understanding their limits matters as much as understanding their promise.

Deep Dive

A computer use system is a loop, not a single model. A screenshot of the current screen goes into a multimodal model; the model reasons about the task and the conversation so far, then emits one structured action — click at these pixel coordinates, type this string, press this key, scroll; a small executor carries out the action inside a sandboxed environment, takes a fresh screenshot, appends it to the conversation, and the cycle repeats. A task like 'find a flight to Tokyo under $900 and fill in the booking form' can take 30–100 such steps and several minutes, because every step is a full model call with images in the context. That makes it a fundamentally different contract from an Autonomous Agent built on APIs: instead of calling functions with typed arguments, the agent operates the same pixels and widgets a human would, with all the ambiguity and fragility that implies.

The Screenshot-Action Loop

The mechanics are deliberately simple. The model sees pixels, not the DOM or an accessibility tree (though browser agents often add the accessibility tree as a second input so elements are easier to reference), and it answers with an action plus exact coordinates — 'left-click at (412, 637)'. Getting coordinates right is the hard part: the model must ground a visual concept like 'the Save button' into a pixel position, which is why computer use pushed Multimodal models to be trained specifically on screenshots with annotated UI elements. Screenshots also eat context: a single desktop frame can cost roughly a thousand tokens, so a 50-step session accumulates a lot of visual history, and implementations downscale or drop old frames to stay inside the window. Each round trip costs a few seconds of inference plus action execution, which is why GUI agents feel slow next to Tool Use over structured APIs — the latency is the price of generality.

The Releases That Defined the Category

Anthropic turned 'computer use' into a product category in October 2024, when an updated Claude 3.5 Sonnet shipped with a public beta of the capability: developers got a reference environment (a Linux desktop in a container with a virtual display) and a tool definition that lets the model request mouse, keyboard, and screenshot actions through the API. Anthropic pitched it explicitly as experimental — at times cumbersome and error-prone — and aimed it at developers automating repetitive desktop work. In January 2025, OpenAI took the idea consumer-facing with Operator, a hosted product powered by its Computer-Using Agent (CUA) model: the agent drives a cloud browser, can navigate sites and fill forms, and hands control back to the user for logins, payments, and other sensitive steps. A wave of open-source browser agents followed the same pattern, and the general 'GUI agent' became a standard item in agent roadmaps.

OSWorld and the Reliability Math

Progress is tracked mostly on OSWorld, a Benchmark of roughly 370 real tasks — editing spreadsheets, configuring applications, moving files between programs — executed on live Ubuntu virtual machines, alongside web-focused suites like WebArena and WorkArena. Humans complete about 72% of OSWorld tasks. The first computer use release managed roughly 15%, and OpenAI's CUA pushed that to just under 40% in early 2025 — state of the art at the time, and still far from dependable. The brutal part is compounding: if each step succeeds 95% of the time, a 30-step task succeeds only about 21% of the time, and a 100-step task almost never. This is why evaluation of GUI agents reports full-task success rather than per-step accuracy, and why production deployments keep tasks short, verifiable, and reversible.

It Won't Replace Your APIs

A common misconception is that GUI agents make integrations obsolete — why build connectors when the agent can just use the software like a person? In practice, clicking pixels is the option of last resort: it is slow, brittle to UI redesigns and pop-ups, and hard to audit compared with a structured Function Calling call or an MCP tool with typed inputs and outputs. If the target system has an API, use it; the GUI is for the long tail of software that has none — legacy desktop apps, vendor portals, one-off internal tools. The strongest production agents are hybrids: they drive APIs wherever available and drop down to screen control only when no cleaner path exists, which confines the fragile pixel-clicking to the few steps that truly need it.

Prompt Injection Is the Hard Part

A GUI agent reads whatever is on the screen, and on the open web some of that content is adversarial. A web page, email, or document can carry hidden instructions — invisible text telling the agent to forward the user's files somewhere — and a model that treats screen contents as commands will sometimes comply, which is Prompt Injection with real mouse clicks behind it. Both flagship products shipped with this warning attached: Anthropic recommends running computer use in a dedicated virtual machine with minimal privileges and no credentials lying around, and Operator gates purchases and logins behind user confirmation and a takeover mode where the human types the password. The practical playbook matches the AI Safety posture of any agentic system: sandbox the environment, allowlist the sites it may visit, never give it secrets beyond the current step, and require human approval for anything irreversible like sending, paying, or deleting.

← All Terms
ESC