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

The HANDOFF.md Pattern - How to Keep Claude Code Productive Across Sessions

Fazm Team·March 14, 2026·3 min read

claude-codedeveloper-toolsproductivityarchitecture

The HANDOFF.md Pattern

There is a point in every AI-assisted project where the codebase outgrows the context window. When that happens, prompt quality stops being the bottleneck. Context management becomes everything.

We hit this building Fazm, a macOS desktop agent with separate Swift UI, accessibility API, and LLM pipeline modules. Each Claude Code session would waste 10-15 minutes re-discovering what was already done before it could make progress. We describe the overall experience of building a macOS agent with Claude in a separate post.

The Pattern

After each agent session, it writes a summary of what changed and what is pending into a HANDOFF.md file. The next session reads this file first and picks up where the previous one left off.

A typical handoff looks like:

## Last Session (2026-03-14)
- Added accessibility tree caching for repeated queries
- Fixed race condition in ScreenCaptureKit frame handler
- PENDING: Cache invalidation when focused window changes
- PENDING: Unit tests for the cache layer

This is not documentation in the traditional sense. It is a conversation between your past agent and your future agent. Short, specific, focused on what matters for the next session.

Post-Edit Hooks

The other pattern that made a huge difference: hooks that run swift build after any .swift file change. This catches 80% of issues before they compound.

Without the hook, an agent might make three changes that each introduce a small type error. By the time it runs a build, there are six errors to untangle. With the hook, each error surfaces immediately after the change that caused it. This kind of fast feedback loop was essential when we were building the Swift ScreenCaptureKit pipeline, where type errors in async code could cascade quickly.

Context Window Management

The biggest lesson was that context window management matters more than prompt quality once you are past a certain project size.

A beautifully crafted prompt means nothing if the agent does not have the right files loaded. And loading too many files means the agent loses focus on the task at hand.

The practical approach:

CLAUDE.md describes the project structure and conventions (loaded every session)
HANDOFF.md describes the current state of work (loaded every session)
Relevant source files get loaded on-demand as the agent needs them

This three-layer context strategy keeps each session productive without overwhelming the context window. When you combine this with running multiple agents in parallel, the handoff file becomes even more critical - each agent needs to know what the others have already completed.

Based on our experience building Fazm and discussions in r/ClaudeCode.

The HANDOFF.md Pattern - How to Keep Claude Code Productive Across Sessions

The HANDOFF.md Pattern

The Pattern

Post-Edit Hooks

Context Window Management

Related Posts

How to Manage Multiple Claude Code Sessions with tmux

Using Claude as an Execution Layer - Markdown Specs, MCP Tools, No Traditional Code

You Do Not Need an MCP Server for Every Mac App - Accessibility APIs as a Universal Interface