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

Wearing a Mic So Your AI Agent Acts as Chief of Staff

Fazm Team·March 16, 2026·2 min read

voice-controlchief-of-staffai-agenthands-freeproductivity

Wearing a Mic So Your AI Agent Acts as Chief of Staff

A post about wearing a microphone throughout the day so an AI agent system could act as a "chief of staff" sparked a lot of discussion. The idea: speak naturally during your workday, and the agent picks up on actionable items - updating your CRM after a call, drafting follow-up emails, creating tasks, logging notes.

It sounds futuristic, but the pieces are all available today.

Voice as the Natural Input

Typing is great for precision work. But a huge amount of your workday involves things you could just say out loud. "Remind me to follow up with Sarah on Thursday." "Log that call with Acme Corp - they are interested in the enterprise plan." "Draft a reply to that email from marketing saying we will have the numbers by Friday."

With a local speech-to-text model like Whisper running on Apple Silicon, transcription happens on-device in real-time. The transcript feeds into a language model that extracts intents and entities, then triggers actions through your actual apps.

The Chief of Staff Pattern

A human chief of staff listens in meetings, takes notes, identifies action items, and makes sure they get done. An AI version of this pattern does the same thing: it listens to your ambient speech, filters for actionable content, and executes through whatever tools you have connected.

The key difference from a voice assistant like Siri is that a chief of staff agent has persistent context. It knows your ongoing projects, your contacts, your priorities. When you say "send the proposal to David," it knows which David, which proposal, and which channel David prefers.

Making It Practical

The practical version of this today is a macOS agent with always-on voice input. Whisper handles transcription locally. The agent uses accessibility APIs to interact with your apps - adding entries to your CRM, creating calendar events, drafting emails in your actual mail client.

Privacy is handled by keeping everything local. Your voice data is transcribed on-device, processed on-device, and the actions happen on your own machine through your own apps.

The chief of staff is not a single app. It is an agent layer that sits on top of all your existing tools and responds to your voice.

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

Wearing a Mic So Your AI Agent Acts as Chief of Staff

Wearing a Mic So Your AI Agent Acts as Chief of Staff

Voice as the Natural Input

The Chief of Staff Pattern

Making It Practical

Related Posts

Claude CoWork Gives Extraordinary Leverage - Local Agents Give Even More

What People Actually Use Claude For Daily - Tool Use, Voice Control, and Desktop Automation

The Auth Problem for AI Agents - OAuth, Rate Limiting, and Dry Run Modes