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.

Diffing Your AI Agent's Personality Over Time with SOUL.md

Fazm Team·March 17, 2026·2 min read

soul-md personality ai-agents version-control behavior claude-md drift

Diffing Your AI Agent's Personality Over Time with SOUL.md

Diffing your own personality over time is deeply honest work. For AI agents, this means version controlling their behavior configuration and watching how it changes - what gets added, what gets removed, and what subtly shifts.

What Is SOUL.md

A SOUL.md file (or CLAUDE.md, or any behavior configuration file) defines how your agent acts:

Communication style and tone
Decision-making preferences
Risk tolerance levels
Domain-specific knowledge
Formatting conventions
What to prioritize and what to skip

Over time, these files evolve. And tracking that evolution reveals patterns about how your relationship with the agent changes.

Running the Diff

git log --oneline -- CLAUDE.md
git diff abc123..def456 -- CLAUDE.md

A typical diff after 3 months shows:

Added rules: things the agent got wrong that you corrected
Removed rules: constraints you relaxed as trust grew
Refined rules: vague instructions replaced with specific ones
Contradictions: new rules that conflict with old ones

What the Diff Reveals

After 6 months of tracking one agent's CLAUDE.md, we found:

72% of additions were corrections for specific mistakes (reactive, not proactive)
18% of changes were refinements that made existing rules more precise
10% of changes were removals - constraints the operator decided were unnecessary

The file grew from 40 lines to 200+ lines. Most of that growth was error correction, not intentional design.

The Personality Drift Problem

Without version control, agent behavior drifts silently. A rule added in month 1 might conflict with a rule added in month 4. Nobody notices because no one reads the whole file end to end anymore.

The fix: periodic reviews where you read the entire behavior file, resolve contradictions, and trim rules that no longer apply. Treat it like code review for your agent's personality.

Intentional vs Reactive Evolution

The best agent operators design behavior changes intentionally - not just patching mistakes, but proactively defining how the agent should grow. That is the difference between an agent that accumulates patches and one that genuinely improves.

Diffing Your AI Agent's Personality Over Time with SOUL.md

Diffing Your AI Agent's Personality Over Time with SOUL.md

What Is SOUL.md

Running the Diff

What the Diff Reveals

The Personality Drift Problem

Intentional vs Reactive Evolution

More on This Topic

Related Posts

Fixing AI Goldfish Memory with CLAUDE.md Constraints

Put 'Challenge My Assumptions' in Your CLAUDE.md

Reducing Context Switching Cost with Running Notes - How AI Agents Solve the Same Problem