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.

Passing Tests Don't Mean Your AI Agent Actually Works

Fazm Team·March 18, 2026·2 min read

testing ai-agent reliability qa production

Passing Tests Don't Mean Your AI Agent Actually Works

The test suite was green. All 47 tests passed. Then nine features were broken in production.

The problem was obvious in hindsight - the tests mocked the OS file picker. They mocked the accessibility tree responses. They mocked the clipboard. Every system interaction that could fail in the real world was replaced with a predictable stub that always returned exactly what the test expected.

The Mocking Trap

When you build an AI agent that interacts with a desktop operating system, the interesting failures happen at the boundary between your code and the OS. The file picker dialog that takes 800ms to appear. The accessibility tree that returns stale data after a window resize. The clipboard that gets overwritten by another process between your copy and paste.

Mocking all of these boundaries means you are testing your logic in isolation from the environment where it actually runs. Your tests verify that your code handles the happy path correctly. They say nothing about whether the happy path actually exists on a real machine.

What to Test Instead

Integration tests against real OS APIs are slow and flaky. That is the point - they are flaky because the real environment is flaky, and your agent needs to handle that.

Run a subset of tests against actual system APIs. Let the file picker open and close. Let the accessibility tree return whatever it returns. Record and replay real interactions instead of writing synthetic mocks.

The goal is not 100% pass rate. The goal is knowing which failures your agent will encounter in production before your users encounter them first.

Coverage Is Not Confidence

Test coverage measures what code paths your tests execute. It does not measure whether those code paths produce correct behavior in the real world. An agent with 95% test coverage and zero integration tests is less reliable than one with 60% coverage and a real-world test suite.

Passing Tests Don't Mean Your AI Agent Actually Works

Passing Tests Don't Mean Your AI Agent Actually Works

The Mocking Trap

What to Test Instead

Coverage Is Not Confidence

More on This Topic

Related Posts

Testing AI Agents Against Real User Scenarios, Not Developer Assumptions

Three Patterns Where AI Agents Silently Abandon Work

How to Monitor AI Agent Health in Production