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.

100M Tokens Tracked: 99.4% Were Input and Parallel Agents Make It Worse

Fazm Team·March 17, 2026·2 min read

tokens api-costs parallel-agents claude-code claude-md optimization

100M Tokens Tracked: 99.4% Were Input and Parallel Agents Make It Worse

After tracking 100 million tokens across parallel Claude Code sessions, the numbers tell a clear story: 99.4% of all tokens were input. The model is reading far more than it is writing. And running 5 agents in parallel makes the problem five times worse.

The Input Token Problem

Every time a Claude Code agent starts a task, it reads your CLAUDE.md, scans relevant files, and builds context. That is all input tokens. The actual code it writes - the output - is a tiny fraction of the total.

With a single agent, this is manageable. With 5 parallel agents, each one is independently reading the same project context. Five agents reading the same CLAUDE.md, the same project structure, the same reference files. Your API bill becomes a second SaaS subscription.

The Numbers

At typical API pricing, 100M tokens is not cheap. When 99.4% of that is input, the cost optimization lever is obvious: reduce what each agent needs to read, not what it writes.

The math is simple. If you can cut each agent's input context by 40%, you save 40% on 99.4% of your total token usage. That is a meaningful reduction in your monthly bill.

How CLAUDE.md Scoping Helps

Aggressive scoping in CLAUDE.md is the highest-leverage cost optimization:

Per-folder scope files so each agent only reads context relevant to its task
Explicit file boundaries so agents do not scan the entire codebase for context
Concise specs that convey the same information in fewer tokens
Caching-friendly patterns that let the API cache repeated context across sessions

The goal is not to give each agent less information - it is to give each agent only the information it needs.

The Real Cost of Parallel Agents

Parallel agents are worth the cost when they save you time. But you should know what you are paying. Track your token usage, break it down by input vs output, and optimize the input side. That is where 99.4% of your money goes.

100M Tokens Tracked: 99.4% Were Input and Parallel Agents Make It Worse

100M Tokens Tracked: 99.4% Were Input and Parallel Agents Make It Worse

The Input Token Problem

The Numbers

How CLAUDE.md Scoping Helps

The Real Cost of Parallel Agents

More on This Topic

Related Posts

Running 5 Parallel AI Agents Is Making My API Bill a Second Rent Payment

Why Explicit CLAUDE.md Specs Beat Auto-Memory for Parallel Agents

Why CLAUDE.md Is the Entire Game for Parallel Claude Code Agents