Strunk connects Claude™, Codex™ and ChatGPT™ to Google Docs™. You write in the AI tool that already holds your repo, your data and the rest of your context, and your reviewers read and comment in Google Docs™, where they already work. Neither side has to move.

Ask your AI tool to publish, and the draft becomes a Google Doc™ you can share. When the comments come in, ask it to pull them: each one arrives with the exact span your reviewer highlighted, so the tool knows what the remark was about rather than guessing. You decide what to do with each, and it drafts the revision, replies in the thread, and resolves what you have settled.

Existing comments and their anchors survive a re-publish, and revisions land as targeted edits instead of a full replace. A thread your reviewer opened last week still points at the text it was about. Google Docs™ stays the source of truth, and its version history is the revert path.

You approve every substantive change before it lands, and every reply goes out under your name.

Your saved writing rules reach the model before it drafts, and Strunk checks each publish, revision and reply on the way out for the tells that give AI writing away: em dashes, contrastive antithesis, transition scaffolding, repeated sentence openings and hedge words. It reports what it found and leaves the decision to you.

Strunk works over MCP, so there is nothing to install: add one server URL to Claude™, Codex™, ChatGPT™ or any other MCP client, then connect your Google account once. Strunk uses Google's drive.file permission, so it only touches documents it created or ones you open with it, and it never stores your document text.

Google Docs™ and Google Drive™ are trademarks of Google LLC. Claude™ is a trademark of Anthropic, PBC. ChatGPT™ and Codex™ are trademarks of OpenAI. Strunk is an independent product of First Crack Studio Ltd and is not affiliated with, endorsed by, or sponsored by Google LLC, Anthropic or OpenAI.