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.

The Five Logs Every Cron-Scheduled AI Agent Needs

Fazm Team·March 18, 2026·2 min read

ai-agent logging cron observability cost-optimization

The Five Logs Every Cron-Scheduled AI Agent Needs

Running AI agents on cron schedules means they execute without supervision. When something goes wrong - or quietly wastes money - you need logs that tell the full story. After months of iteration, we settled on five essential logs.

1. Action Log

What the agent actually did. Every file changed, every API called, every button clicked. This is the obvious one, and most teams get it right. But it is not enough by itself.

2. Rejection Log

What the agent decided not to do, and why. This is the log most teams skip, and it is arguably the most important one. When your agent rejects a valid task because of stale state from a previous session, the action log shows nothing - it looks like a quiet success. Only the rejection log reveals the missed opportunity.

3. Handoff Log

What the agent escalated to a human or another agent. Every handoff should include the context that triggered it, the state at the time, and what the agent expected the recipient to do. Without this, handoffs become black holes where context disappears.

4. Cost Log

Token usage, API calls, compute time - broken down per task. This is the log that exposed 40% waste in our pipeline. We discovered the agent was re-processing unchanged data on every cron run because it had no memory of previous runs. The cost log made the waste visible. The action log never would have.

5. Verification Log

Did the agent's actions produce the expected result? After completing a task, the agent should verify its own output and log whether the verification passed or failed. A file was written - does it parse correctly? An API was called - did the response confirm success?

The Pattern

These five logs together give you complete visibility into unsupervised agent behavior. Actions tell you what happened. Rejections tell you what did not happen. Handoffs track context flow. Costs track efficiency. Verification tracks correctness.

Skip any one of them and you have a blind spot that will eventually cost you.

The Five Logs Every Cron-Scheduled AI Agent Needs

The Five Logs Every Cron-Scheduled AI Agent Needs

1. Action Log

2. Rejection Log

3. Handoff Log

4. Cost Log

5. Verification Log

The Pattern

More on This Topic

Related Posts

Agent Logs as Open Letters to Nobody - Why Unread Documentation Has Value

The Rejection Log Is More Important Than the Action Log

AI Agent Decision Logging That Nobody Reads - The Audit Trail Gap