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

The Asymmetric Trust Problem - When Your AI Agent Has More Access Than You Intended

Fazm Team·March 17, 2026·3 min read

trustpermissionsaccessibility-apisecurityai-agent

Permission Granted Does Not Equal Permission Intended

When you enable accessibility permissions for an AI agent on macOS, you are granting access to an API designed for screen readers. Screen readers need to see everything - every button label, every text field value, every menu item, every piece of content on screen. That is the whole point.

The problem is that "everything" really means everything. Your password manager showing a credential in a text field. Your banking app displaying account balances. Your email client with the full body of every message. The accessibility API exposes all of it as structured, machine-readable data.

The Trust Asymmetry

When a user grants accessibility permissions, their mental model is usually "this app can control my mouse and keyboard." The reality is much broader. The app can read every piece of text displayed anywhere on the system, understand the structure of every application's UI, and interact with elements the user may not even be aware of.

This is asymmetric trust - the permission you think you granted is a small subset of what you actually granted. The constraints on what the agent does with this access are behavioral, not technical. The system prompt might say "only interact with Finder." But technically, the agent can read your email at the same time.

Why This Is Hard to Fix

You cannot easily scope accessibility permissions to specific apps. macOS grants it system-wide or not at all. This was fine when the only consumers were assistive technologies operated by humans who could see what the screen reader was accessing. It is less fine when the consumer is an autonomous agent making decisions about what to read and interact with.

What You Can Do

Minimize what is on screen during agent sessions. Close sensitive apps you are not actively using.
Use dedicated user accounts for agent workflows that do not need access to your full environment.
Audit agent logs to see what the agent actually read, not just what it acted on.
Prefer agents that log their accessibility tree reads so you can verify they are not reading unrelated apps.

The honest answer is that this is an unsolved problem. The accessibility API was not designed for this use case, and the permission model has not caught up.

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

The Asymmetric Trust Problem - When Your AI Agent Has More Access Than You Intended

Permission Granted Does Not Equal Permission Intended

The Trust Asymmetry

Why This Is Hard to Fix

What You Can Do

More on This Topic

Related Posts

What's the Difference Between Trusting an AI Agent and Verifying One?

Why Your AI Agent Needs a Firewall - And Why It Should Be Open Source

Privacy Controls Are the Real Story in AI Agent Frameworks