Context-grounded reply suggestions
Chalked reads the conversation you are currently in and prepares a reply based on that thread rather than starting from a blank prompt.
Chalked
Chalked is a Mac reply assistant that drafts context-grounded responses in the conversation you are already using. It helps people answer faster across Mac apps without sending messages automatically.
Overview
Chalked is a Mac reply assistant that prepares context-grounded suggestions in the conversation you are already using. It is designed to help you answer faster without taking over sending or hiding how the reply was formed.
The product reads the current thread, can incorporate calendar and working context when relevant, and places a suggested response where you are typing. The site says replies are inserted with Tab, can be adjusted by holding fn and giving a different instruction, and are never sent automatically.
Core features
Uses calendar and work context
Suggestions can use your calendar and working context when that information matters to the reply, helping keep commitments and timing aligned.
Insert with Tab
Press Tab to place a prepared reply into the field where you are writing, then review it before sending.
Modify the reply with fn input
Hold fn and describe what you want instead if the default suggestion is close but needs a different outcome.
Works across common Mac apps
Chalked is shown working across Messages, Gmail, LinkedIn, Slack, and other Mac text fields, so the same reply layer can follow the user between apps.
Inspectable memory for commitments
Captured commitments keep their source and status, and the product says you can inspect, correct, export, or remove them.
Common use cases
Answering time-sensitive thread questions
When a client or coworker asks about timing, Chalked can draft a reply that reflects the current conversation and any relevant calendar or work context.
Protecting commitments in ongoing work
When a message includes a commitment, budget, or dependency, the product can surface a response that keeps those details consistent across later replies.
Replying across multiple Mac apps
If you are moving between apps like Messages, Gmail, Slack, and LinkedIn, Chalked gives you the same reply layer instead of forcing a separate workflow in each place.
Adjusting a near-match reply
When the default suggestion is close but not exact, holding fn lets you steer the outcome with a plain-language instruction before inserting the reply.
Drafting without automatic sending
If you want to stay in control of sending, you can review the drafted text at your cursor and decide whether to edit it, ignore it, or send it yourself.
Pros and Cons
Pros
- Works in the conversation you are already replying to, which reduces copy-paste and retyping.
- Uses calendar and working context when helpful, instead of only generating generic text.
- Keeps captured commitments inspectable, with options to inspect, correct, export, or remove them.
- Does not send messages on its own; the user keeps control over review and sending.
- Covers multiple text fields and apps on Mac, including Messages, Gmail, LinkedIn, and Slack.
Cons
- The site says replies need macOS 26 plus Apple Intelligence, which narrows the supported setup.
- Chalked is Mac-first, and the site describes Windows as a future platform rather than a current one.
- The product relies on Accessibility to read the current window, so users must grant that access for the app to work.
FAQ
Do I have to talk to use Chalked?
No. The site says Chalked can wait quietly in the notch while you type as usual. Voice is optional and is mainly described as a faster way to change a reply or explain what you want it to accomplish.
Does Chalked send messages automatically?
No. Chalked does not send messages for you. It inserts a suggestion at your cursor with Tab, and you can edit it, ignore it, or send it yourself.
What does Chalked remember?
Chalked remembers sourced commitments and working context that can improve later replies. The site says captured items keep their source and status, while uncertain context does not silently alter a reply.
What does it require to run?
Chalked is presented as a Mac product. The site says replies need macOS 26 plus Apple Intelligence, and dictation needs macOS 15+.
Which apps or platforms does it support?
The homepage lists Messages, Gmail, LinkedIn, Slack, and thousands of other text fields across Mac. The site also says Windows is the natural next platform after the Mac experience.
Quick Facts
- Category
- Productivity / AI assistant
- Platform
- Mac
- Availability
- Free in beta
- Requirements
- Replies need macOS 26 + Apple Intelligence; dictation needs macOS 15+
- Supported apps
- Messages, Gmail, LinkedIn, Slack, and other Mac text fields
- Source domain
- usechalked.com
Alternativas a Chalked
Goldfish
Goldfish is an AI memory app for macOS that helps you reply, write, summarize, and continue using the context already on your Mac. It stores memory locally and writes in your tone.
dirac
Dirac is an AI email assistant that prepares a morning brief, prioritizes important threads, and drafts replies in your voice. It is positioned for founders and other busy professionals who use Gmail and want to reduce morning inbox triage.
ArtDeck
ArtDeck is a visual reference board app for iPhone, iPad, and Mac that lets artists collect mixed reference material on one canvas and study it with ToolBox lenses. It works offline, supports optional iCloud sync, and is sold as a one-time purchase with no account required.
Biji
Biji es una plataforma versátil diseñada para mejorar la productividad a través de herramientas y características innovadoras.
Malyatko
Malyatko is a baby tracker for logging feeding, sleep, growth, teething, and milestones in one app. It works on iPhone, Apple Watch, and widgets, with no sign-up, offline use, and family sharing through iCloud.
Redline
Redline is a budgeting tool for Claude Code that paces sessions to stay within time, token, cost, or plan-percentage limits. It uses Claude Code’s native hooks and statusline to help sessions finish with a usable result instead of stopping abruptly.