Skip to content

Reply watch with next step approval cards

Watches the email threads you started for replies and lines up the next step, such as a booking or a follow up, as a card. Nothing is sent or booked until you tap approve.

PersonalWorks with Claude Code · Claude Desktop with MCP+2Community example
Build your promptSee requirements

What it does

  • Checks threads you started for new replies
  • Works out the next step from the reply and your calendar
  • Drafts the reply or proposed booking as an approval card
  • Holds health, legal, financial and card like details back from the cloud model

Your approval boundaries

Approval required

These actions always wait for your yes:

  • Sending any email, which is written in your name
  • Booking or changing any calendar event

You decide what happens next.

More about this workflow

This setup is for busy people who want their own day to run a little smoother. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it checks threads you started for new replies. Next, it works out the next step from the reply and your calendar. Then it drafts the reply or proposed booking as an approval card. Finally, it holds health, legal, financial and card like details back from the cloud model. It works with your email and calendar, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before sending any email, which is written in your name and booking or changing any calendar event, and says plainly if a step cannot be undone.

“Every send or booking is an approval card.”
shipleta90 shipleta90 on GitHub · Oct 5, 2026
Before you startEmail · Calendar accessScoped permissionsClaude Code or Claude Desktop with MCP
Explore required tools and model recommendations

Tools and access

  • Gmail

    Handles the email part of this job. Grant read-only plus compose (drafts) scopes.

    API required: Yes. Needs a Google Cloud project with an OAuth app and the Gmail API turned on. The agent signs in through OAuth with only the scopes you pick.

    Sign up: Google Workspace

  • Google Calendar

    Handles the calendar part of this job. Grant read-only calendar scope.

    API required: Yes. Needs a Google Cloud OAuth app with the Calendar API turned on.

    Sign up: Google Workspace

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Claude Sonnet 5.5

Fast and careful with your inbox and calendar.

$2 per million input tokens, $10 per million output tokens.

Anthropic docs as of October 11, 2026

Cheaper backup

Claude Haiku 5.5

Cheapest Claude option for daily sorting.

From $0.10 per million input tokens and from $0.50 per million output tokens.

Anthropic docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

topics never sent to the model

e.g. phone web app

2Your prompt

4 of 4 still empty
Fill these in before you run it: [EMAIL ACCOUNT TO WATCH] [CALENDAR FOR BOOKINGS] [PRIVACY FILTER: topics never sent to the model] [WHERE APPROVAL CARDS APPEAR: e.g. phone web app] You are the Reply watch with next step approval cards agent. Watches the email threads you started for replies and lines up the next step, such as a booking or a follow up, as a card. Nothing is sent or booked until you tap approve. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Checks threads you started for new replies - Works out the next step from the reply and your calendar - Drafts the reply or proposed booking as an approval card - Holds health, legal, financial and card like details back from the cloud model What you must never do without a yes from a person: - Sending any email, which is written in your name - Booking or changing any calendar event Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: Claude Code, Claude Desktop with MCP, n8n, LangGraph

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect Gmail with its own login, not yours. Grant read-only plus compose (drafts) scopes.
  2. 2Connect Google Calendar with its own login, not yours. Grant read-only calendar scope.
  3. 3Paste the prompt where your harness takes instructions. See the note under the Copy button.
  4. 4Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  5. 5Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access18 / 30

Can draft things that send or spend, so it sits close to risky actions.

Human approval30 / 30

Waits for a yes on: sending any email, which is written in your name, booking or changing any calendar event.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope18 / 20

Runs on its own login across 2 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Access: Take away its ability to send, post or spend. Let it only write drafts, and have a person press send or pay from their own account +6
  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
  • Scope: Run it on one tool only, with its own login that can see just what this job needs +2

Do all of these to reach 91, up from 80.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Reply watch with next step approval cards](https://trustcase.dev/badge/reply-watch-with-next-step-approval-cards.svg)](https://trustcase.dev/use-cases/reply-watch-with-next-step-approval-cards)
HTML
<a href="https://trustcase.dev/use-cases/reply-watch-with-next-step-approval-cards"><img src="https://trustcase.dev/badge/reply-watch-with-next-step-approval-cards.svg" alt="Trustcase trust score for Reply watch with next step approval cards" height="20"></a>

More personal workflows

Other workflows that use the same tools

  • Meeting prep

    Sales. Gives you a short brief on everyone in tomorrow's sales meetings.

  • Listing inquiry responder

    Sales. Answers buyer questions about property listings within a minute, any time of day. It checks how serious the buyer is and offers a showing time for the agent to confirm.

  • Weekly marketing report digest

    Marketing. Reads the week's marketing reports, decks and meeting notes, and tells you what actually changed. It keeps a log so slow trends stand out.