How much time will I actually save with Fazm?

Most users report saving 45-90 minutes per day on repetitive tasks. The biggest time savings come from email management (drafting replies, sorting, archiving), form filling (expense reports, CRM updates, applications), research (comparing products, gathering data from multiple sites), and social media (cross-posting, scheduling, replying). For example, booking a flight that normally takes 10 minutes of clicking through airline sites takes a single voice command with Fazm. Filing an expense report that requires opening a PDF, extracting numbers, and entering them into a spreadsheet becomes one spoken sentence. The more repetitive and multi-step your daily work is, the more time you get back.

What exactly can Fazm control?

Fazm controls everything you can do manually on your Mac. That includes mouse movements and clicks, keyboard typing, browser navigation and form filling, app switching, file management in Finder, and system-level actions. It uses direct browser DOM control for web interactions - meaning it reads and manipulates the actual page structure rather than taking screenshots and guessing where to click. For native macOS apps, Fazm uses accessibility APIs to interact with buttons, menus, text fields, and other UI elements. This works across any application: Chrome, Safari, VS Code, Slack, Figma, Terminal, Mail, Calendar, and more.

How is Fazm different from ChatGPT or Claude?

Chatbots like ChatGPT and Claude give you answers in a conversation window. Fazm takes action directly on your computer. When you say 'reply to Sarah's email,' Fazm opens your email app, finds Sarah's message, writes a contextual reply, and sends it. A chatbot would tell you what to write, but you still have to do all the clicking and typing yourself. Fazm moves your mouse, types on your keyboard, clicks buttons, and navigates between apps. It is a computer agent, not a chat assistant.

How does the memory layer work?

Fazm builds a personal knowledge graph by extracting information from your files, browsing history, conversations, and daily activity. Over time, it learns your contacts (names, emails, relationships), accounts and credentials, preferences (formatting, tone, scheduling habits), and frequently used workflows. In your first week, you might say 'Reply to Sarah's email, she's my cofounder, her email is sarah@acme.com.' By week four, you just say 'Reply to Sarah' because Fazm already knows who she is. By week eight, Fazm can draft the reply before you even ask. All of this data stays locally on your Mac - your knowledge graph never leaves your machine or gets sent to any cloud service.

Is Fazm safe? Can it mess up my computer?

Safety is built into every layer of Fazm. You watch every action in real-time on your screen - Fazm moves your mouse and types visibly, so there is nothing hidden. You can stop any action at any point by pressing a keyboard shortcut. Fazm also shows you what it plans to do before executing destructive actions like deleting files or sending emails, giving you a chance to confirm or cancel. Because Fazm is open source, the code is fully auditable on GitHub. There is no hidden behavior, no background processes making changes you cannot see, and no actions that bypass your screen.

What platforms does Fazm support?

Fazm currently supports macOS, running natively on both Apple Silicon (M1, M2, M3, M4) and Intel Macs. It is built with Swift and uses macOS-specific frameworks like ScreenCaptureKit for screen analysis and Accessibility APIs for app control, which is why macOS is the primary platform. Windows and Linux support are on the roadmap but do not have release dates yet. You can also control your Mac remotely from your phone using Fazm Remote, which gives you voice access to your desktop while you are away from your computer.

How does Fazm voice input work?

One keyboard shortcut activates push-to-talk. Hold the key, speak naturally about what you need done, and release. Fazm transcribes your speech locally using on-device models, so there is no network latency for the voice recognition step. You do not need wake words like 'Hey Siri' or 'OK Google' - just press and talk. You can also type commands into the floating toolbar if you prefer text input. Fazm understands natural language, so you do not need to memorize specific commands. Say 'book me a flight to Tokyo next Thursday' or 'find the cheapest AirPods on Amazon' and Fazm figures out the steps.

Is my data sent to the cloud?

Fazm processes screen analysis and memory entirely on your machine. The personal knowledge graph, file indexing, and screen capture all run locally. The only data that leaves your Mac is the intent - a text description of what you want to accomplish, which is sent to the AI model (Claude or GPT) for action planning. Your actual screen content, file contents, browsing history, and personal knowledge graph never leave your computer. Fazm is also open source, so you can verify exactly what data is transmitted by reading the code on GitHub. For users who need complete air-gapped operation, local model support is planned.

Back to Blog

Screenshot-Based Agents Guess - Accessibility API Agents Know

Fazm Team·March 17, 2026·2 min read

screenshotsaccessibility-apidataprecisionautomation

Screenshot-Based Agents Guess - Accessibility API Agents Know

There are two ways an AI agent can understand what is on your screen. It can take a screenshot and analyze the pixels, or it can query the Accessibility API and get structured data about every element. The difference matters more than most people realize.

The Screenshot Approach

Screenshot-based agents capture an image of your screen and feed it to a vision model. The model identifies buttons, text fields, menus, and other elements by their visual appearance. Then it calculates coordinates and clicks where it thinks the right element is.

This works surprisingly well for simple interfaces. But it breaks down fast. A button that looks like a link, a text field that blends into the background, a custom UI component that does not look like anything standard - these trip up vision models regularly.

The bigger problem is confidence. When a vision model says "I think this is a submit button," it is making a probabilistic guess. It might be 90% sure, but that 10% uncertainty compounds across multi-step workflows.

The Accessibility API Approach

The Accessibility API provides structured data about every UI element on screen. Not pixels - actual metadata. The element's role (button, text field, menu item), its label, its current value, its available actions, and its exact position.

This is the same API that screen readers use, which means it is well-supported across macOS applications. When an agent queries the Accessibility API, it does not guess that something is a button - it knows it is a button because the application declared it as one.

Why This Matters for Reliability

Desktop automation needs to be reliable. If you tell an agent to submit a form and it clicks the wrong button because the vision model misidentified an element, that is a real problem. Accessibility API agents eliminate an entire category of errors by working with structured data instead of visual approximations.

The best approach combines both - use the Accessibility API as the primary data source and fall back to vision when accessibility data is incomplete.

Fazm is an open source macOS AI agent. Open source on GitHub.

Screenshot-Based Agents Guess - Accessibility API Agents Know

Screenshot-Based Agents Guess - Accessibility API Agents Know

The Screenshot Approach

The Accessibility API Approach

Why This Matters for Reliability

Related Posts

Accessibility APIs vs Pixel Matching - Why Screenshots Miss So Much Context

Accessibility APIs vs OCR - Two Approaches to Desktop Agent Vision

Testing AI Agents with Accessibility APIs Instead of Screenshots