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

From Writing Code to Reviewing Code - The AI Shift

Fazm Team·March 17, 2026·3 min read

code-reviewclaude-codeai-workflowdeveloper-experiencespecs

The Job Changed

Six months ago, I wrote code. Now I review code from five Claude agents running in parallel on the same codebase. My primary output is CLAUDE.md specs - detailed instructions that tell agents what to build, how to build it, and what constraints to respect.

This is not a subtle shift. The core skill changed from "can I implement this?" to "can I specify this precisely enough that an AI implements it correctly, and can I review the result fast enough to keep up?"

What Writing Specs Looks Like

A good CLAUDE.md spec is not a vague description of what you want. It is a precise contract:

What the feature should do - with specific edge cases called out
What it should not do - constraints are more important than requirements
How to verify it works - test cases the agent should validate
What existing code to respect - patterns, conventions, architectural decisions

The spec is the product now. If the spec is ambiguous, the agent will make plausible but wrong decisions. If the spec is precise, the agent produces correct code on the first try.

What Reviewing at Scale Looks Like

With five agents running in parallel, you get a lot of code to review quickly. The review process changes:

Focus on architecture, not syntax. The syntax will be correct. The question is whether the approach fits the system.
Check the boundaries. Where does this code interact with other code? Are the interfaces clean?
Look for what is missing. Agents are good at implementing what you asked for. They are bad at noticing what you forgot to ask for.
Run the tests. Do not trust that it "looks right." Execute it.

The New Skills

The developers who thrive in this model are the ones who can context-switch quickly between reviewing different agents' work, write specs that leave no room for misinterpretation, and have strong enough architectural intuition to catch structural problems in a quick scan.

Writing code is becoming a smaller part of the job. Thinking clearly about what code should do is becoming the whole job.

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

From Writing Code to Reviewing Code - The AI Shift

The Job Changed

What Writing Specs Looks Like

What Reviewing at Scale Looks Like

The New Skills

More on This Topic

Related Posts

Reading Extended Thinking from 5 Parallel Claude Code Agents

Has AI Ruined Software Development? No - It Shifted the Work to Specs

Claude Code Agents Gave Me a Healthier Life - When the Hard Part Is Specs