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.

Apple Intelligence Beyond Email Summaries - What Accessibility APIs Unlock

Fazm Team·March 17, 2026·2 min read

apple-intelligence accessibility-api siri macos automation

Apple Intelligence Beyond Email Summaries - What Accessibility APIs Unlock

Apple Intelligence shipped with email summaries, notification grouping, and some writing tools. Useful features, but they barely scratch the surface of what on-device AI could do with macOS. The real power is in the accessibility APIs that Apple has maintained for decades - and that Apple Intelligence does not use.

What Siri Cannot Do

Siri can open apps, set timers, and send messages. It cannot fill out a form in a third-party app, navigate a complex settings panel, or chain together actions across multiple applications. It operates through a limited set of intents that each app developer must explicitly support.

The accessibility API has no such limitation. Every button, text field, menu item, and UI element in every macOS application is exposed through the accessibility tree. An AI agent with accessibility access can interact with any app the same way a human user does - by reading what is on screen and clicking the right elements.

The Context Window Problem

The real constraint right now is the context window. An accessibility tree for a complex app can be thousands of elements. Fitting that into a prompt alongside conversation history and instructions requires careful management. But this is a solvable engineering problem, not a fundamental limitation.

Techniques like filtering irrelevant elements, caching static UI structures, and using hierarchical summaries can reduce the token cost of accessibility tree traversal dramatically.

What This Enables

With accessibility API access, an AI agent can automate workflows that currently require human attention - data entry across systems, form filling, report generation from multiple apps, testing UI flows. These are the repetitive tasks that eat hours every week and that no existing automation tool handles well.

Apple has the pieces. The accessibility APIs exist. The on-device models exist. The missing step is connecting them in a way that lets an AI agent act on your behalf across any application, not just the ones that opted into Siri Shortcuts.

Apple Intelligence Beyond Email Summaries - What Accessibility APIs Unlock

Apple Intelligence Beyond Email Summaries - What Accessibility APIs Unlock

What Siri Cannot Do

The Context Window Problem

What This Enables

More on This Topic

Related Posts

Automate macOS App Testing With Accessibility APIs Instead of Manual Clicking

Giving Claude Code Eyes and Hands with macOS Accessibility APIs

Skip MCP for Native Mac Apps - Use the Accessibility API Instead