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.

When AI Agents Choose Not to Know - Ignorance as a Security Boundary

Fazm Team·March 18, 2026·3 min read

ai-agent security privacy least-privilege design-patterns

When AI Agents Choose Not to Know

Choosing not to know is underrated. In security design for AI agents, deliberate ignorance is one of the most powerful patterns available - and one of the least used.

The Problem with Knowing Everything

Most agent architectures give the agent access to everything it might need. Database credentials, API keys, user tokens, file system access - all available in case the agent needs them. The reasoning is practical - you do not want the agent to fail because it lacks a permission.

But every piece of information the agent has access to is information it can leak. Through prompt injection, through error reporting, through unexpected tool use, through context that persists across sessions. The attack surface grows with every secret the agent knows.

Ignorance as Architecture

The alternative is to design ignorance into the system. An agent that never sees a database password cannot include it in an error report. An agent that accesses APIs through a proxy that injects credentials never has those credentials in its context window.

This is not about restricting the agent after giving it access. It is about architecturally ensuring certain information never reaches the agent at all. The agent calls a function that says "read from database" and the credential injection happens in a layer the agent cannot see or influence.

Practical Patterns

Credential proxies - the agent calls an API through a gateway that adds authentication headers. The agent sees the response but never sees the credentials.

Scoped file access - instead of giving the agent access to the entire file system, mount only the directories it needs. It cannot read what it cannot see.

Redacted context - when passing conversation history or logs to the agent, strip sensitive values before they enter the context window. The agent works with sanitized data.

The Counterintuitive Benefit

Less knowledge makes the agent more trustworthy, not less capable. When users know the agent architecturally cannot access their passwords, trust increases. When security auditors see that credentials never enter the agent's context, the audit gets simpler.

The best security boundary is one the agent cannot cross because it does not even know the boundary exists.

When AI Agents Choose Not to Know - Ignorance as a Security Boundary

When AI Agents Choose Not to Know

The Problem with Knowing Everything

Ignorance as Architecture

Practical Patterns

The Counterintuitive Benefit

More on This Topic

Related Posts

Privacy Controls Are the Real Story in AI Agent Frameworks

12 CVEs Indexed - Dependency Security in AI Agent Toolchains

HTTP Requests as Unaudited Data Pipelines - When Error Reporting Leaks API Keys