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.

Teaching AI Agents Taste Through Examples - Five Good, Five Bad

Fazm Team·March 18, 2026·3 min read

ai-agent prompt-engineering claude-md code-quality best-practices

Teaching AI Agents Taste Through Examples - Five Good, Five Bad

Showing examples works better than abstract guidelines. Five good and five bad examples teach an AI agent more about your preferences than two pages of written rules ever will.

Why Abstract Guidelines Fail

"Write clean, maintainable code" means nothing to an AI agent. It is too vague to act on. Every model thinks its output is clean and maintainable. "Use descriptive variable names" is slightly better but still leaves enormous room for interpretation. What counts as descriptive? How long is too long?

Compare that to showing the agent five actual function names from your codebase that you consider good and five that you consider bad. Now it has a concrete reference point. It can pattern match against real examples rather than interpreting abstract advice.

The Five-and-Five Pattern

In your CLAUDE.md or project instructions, include concrete examples of what you want and what you do not want. This works for almost everything.

For code style, show five functions that exemplify your preferred patterns and five that violate them. For commit messages, show five good ones and five bad ones from your actual git history. For error handling, show five cases where the agent handled errors the way you like and five where it did not.

The agent does not need you to explain the pattern. It will extract the pattern from the examples. And its extracted pattern will often be more nuanced than what you could articulate in words.

Why This Works

Language models are fundamentally pattern-matching systems. They are better at learning from examples than from descriptions. This is the same reason children learn language from hearing sentences, not from studying grammar rules.

When you give an agent abstract guidelines, it has to interpret the guideline and then generate matching output - two steps where errors can enter. When you give it examples, it just needs to match the pattern - one step, less room for drift.

The Maintenance Cost

Examples need updating as your codebase evolves. A set of example functions from six months ago might no longer reflect your current style. Review your examples quarterly and swap in fresh ones that represent your current preferences.

Teaching AI Agents Taste Through Examples - Five Good, Five Bad

Teaching AI Agents Taste Through Examples - Five Good, Five Bad

Why Abstract Guidelines Fail

The Five-and-Five Pattern

Why This Works

The Maintenance Cost

More on This Topic

Related Posts

Personality Is a Luxury Tax on AI Agents - How Trimming CLAUDE.md Improved Output

CLAUDE.md Structure for Lossy Context Compression - Top and Bottom Wins

Put 'Challenge My Assumptions' in Your CLAUDE.md