⚙ Blueprint

Travel Day Guardian

Hear about schedule changes and delays first, with your options and a request ready to send.

MediumAbout 20 minutes (editor's estimate)
Goal
Hear about schedule changes and delays first, with your options and a request ready to send.
Runs
⏱ Daily while you have upcoming trips, plus every 2 hours on travel day
Watches
👁 Airline and booking emails

What it does, step by step

  1. Finds your upcoming bookings in your email.
  2. Watches for schedule changes, delays and cancellations.
  3. When something changes, tells you the old and new time and your options.
  4. Drafts a rebooking or cancellation request for your OK.

Paste these starter instructions

Copy, paste into your tool, and replace the [brackets] with your details.

Starter instructions
You are my Travel Day Guardian.
Every morning, look in my email for upcoming flights, trains and hotel bookings in the next 30 days and keep a list.
Watch for any change: new times, delays, gate or terminal changes, cancellations.
When something changes, message me: what changed, by how much, and my options (wait, rebook, or ask for a refund under the airline's published rules).
Draft any refund or rebooking request, but never cancel, book or pay without my YES.

Which tool to use

What this costs to run

If you run this bot yourself on an AI API: our assumption is 30 runs a month, each reading about 10,000 tokens and writing about 300 (one daily check of your bookings and airline emails while a trip is coming up). That's about 300,000 tokens in and 9,000 out a month.

ModelPrice per 1M tokens (in / out)About per month
Anthropic Claude Haiku 5.5$0.10 / $0.50$0.03
Google gemini-3.8-flash$0.75 / $3.75$0.26
Anthropic Claude Sonnet 5.5$2.00 / $10.00$0.69
OpenAI gpt-6-astra$10.00 / $50.00$3.45

Token counts are our editor's estimates, not measurements. Real use can be several times higher if the agent browses the web or uses tools: Anthropic says its browser toolset alone adds about 6,600 input tokens per request.

Try other models and numbers in the cost calculator →

Prices are standard API rates from each provider's official pricing page, checked Oct 21, 2026 (full price table). If you use an app plan (Grok Bot, ChatGPT, Claude, Gemini, Meta Muse) the bot runs inside your plan's limits instead of being billed per token. How to run your bots for less →

How to set it up

  1. Pick one boring job. Choose ONE small job you do every week, like reading school emails or checking a web page.
  2. Pick your tool. Use what you already have.
  3. Paste the instructions and fill in the [brackets]. Open a new chat in the tool.
  4. Say “Run this once now and show me the result”. Don't schedule anything yet.
  5. Then say “Do this every [day/time]” and lock it down. Once the result looks right, ask it to repeat on a schedule.

Full 5-step guide with examples →

Safety notes

  • Cancelling can lose your seat. Decide first.
  • Use a single-use virtual card if you let it book.

Based on