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.

Claude Opus Rummaging Through Personal Files - 5x Worse with Parallel Agents

Fazm Team·March 17, 2026·3 min read

claude-opus parallel-agents privacy file-access ai-agents

Claude Opus Rummaging Through Personal Files - 5x Worse with Parallel Agents

Claude Opus has a well-known habit. You give it a coding task and it decides to "understand the project better" before doing anything. That usually means reading files you never asked it to look at. Your dotfiles. Your shell history. Your notes directory.

With a single agent, this is mildly annoying. With five agents running in parallel, it becomes a real problem.

The Little Adventures Scale Linearly

When you run one agent, it might spend a few turns reading your .zshrc and ~/.ssh/config before getting to work. Annoying, but manageable. You lose maybe 30 seconds of context window.

Now multiply that by five. Each agent independently decides it needs to "explore the project structure." Five agents simultaneously reading your entire home directory. Five context windows filling up with irrelevant personal files. Five sets of API tokens burned on reading your .gitconfig and browsing through ~/Documents.

The cost is not just wasted tokens. It is wasted time, wasted context window space, and a privacy concern when those files contain sensitive information.

Why It Happens

Opus models are trained to be thorough. When given a task, the model wants to build a complete mental model of the environment before acting. This is generally a good instinct for complex reasoning - but terrible for parallel execution where you need agents to stay focused.

The problem compounds because each agent has no awareness of what the others have already explored. There is no shared "already looked at this" signal.

How to Fix It

The solution is constraining your agents upfront:

Explicit CLAUDE.md rules: Add "Do not explore files outside the project directory" to your instructions
Scoped working directories: Pin each agent to a specific subdirectory
Allowlists over blocklists: Tell the agent exactly which files to read rather than hoping it stays in bounds
Pre-load context: Give each agent the project structure upfront so it does not feel the need to discover it

The best parallel agent setup treats each agent like a new hire on their first day - hand them exactly the files they need and nothing else.

Claude Opus Rummaging Through Personal Files - 5x Worse with Parallel Agents

Claude Opus Rummaging Through Personal Files - 5x Worse with Parallel Agents

The Little Adventures Scale Linearly

Why It Happens

How to Fix It

More on This Topic

Related Posts

Running AI Agents as Actual Employees in Real Workflows

AI Agents Move Faster Than Strategy - The Management Gap

Anchoring Bias in Multi-Agent Systems - When One Agent's Output Biases All the Others