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 Web App vs API: The Privacy Difference You Need to Know

Fazm Team·March 17, 2026·2 min read

claude api privacy data-security ai-tools

Claude Web App vs API: The Privacy Difference You Need to Know

Most people start with the Claude web app because it is free and convenient. But there is a critical privacy difference that most users never learn about - the API does not train on your data.

How the Web App Handles Your Data

When you use Claude through the web app at claude.ai, your conversations may be used to improve future models. Anthropic's terms of service for the free and Pro tiers allow them to use your inputs and outputs for training purposes. For casual questions, this is fine. For anything involving proprietary code, client data, or sensitive business logic, this is a real problem.

The API Is a Different Product

The Claude API operates under separate terms. Your data sent through the API is not used for model training. Period. This makes the API the correct choice for any workflow involving:

Proprietary source code and architecture details
Client information or business-sensitive documents
Internal communications and strategy discussions
Medical, legal, or financial data

The API costs money per token, but the privacy guarantee is worth it for professional use.

Why This Matters for AI Agents

AI agents like Fazm send a lot of context to the model - screen content, file contents, clipboard data, system information. When an agent is running on your machine and processing your daily workflow, the privacy of that data pipeline is not optional. It is foundational.

This is why local-first agents that use the API directly are the right architecture. Your data flows from your machine to the API and back. It is not stored, not trained on, and not accessible to anyone else.

The Practical Setup

If you are still using the web app for work tasks, switch to API access. You can use Claude Code (the CLI), connect through an AI agent like Fazm, or build your own integration. The cost per token is small compared to the risk of feeding proprietary information into a training pipeline.

The web app is great for learning and casual use. The API is for real work.

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

Claude Web App vs API: The Privacy Difference You Need to Know

Claude Web App vs API: The Privacy Difference You Need to Know

How the Web App Handles Your Data

The API Is a Different Product

Why This Matters for AI Agents

The Practical Setup

More on This Topic

Related Posts

ChatGPT vs Claude vs Gemini - Which AI for What Task

Claude Subscription vs API Pricing - Why Heavy Users Get an Incredible Deal

I Switched from ChatGPT to Claude and Haven't Looked Back