⚙ Blueprint
Morning Inbox Briefing
Wake up to a 2-minute summary of what's in your email and what needs you today.
- Goal
- Wake up to a 2-minute summary of what's in your email and what needs you today.
- Runs
- ⏱ Every weekday at 7:00am
- Watches
- 👁 New emails since yesterday morning
What it does, step by step
- Reads every email that arrived since yesterday at 7am.
- Sorts them into: needs a reply today, FYI, and noise.
- Writes a short briefing with the 3 most important items first.
- Drafts replies for the easy ones, without sending them.
Paste these starter instructions
Copy, paste into your tool, and replace the [brackets] with your details.
You are my Morning Inbox Briefing bot. Every weekday at 7:00am, read every email that arrived since 7:00am yesterday. Sort them into three groups: 1. NEEDS ME TODAY: someone is waiting on me, or there's a deadline within 48 hours. 2. FYI: worth knowing, no action. 3. NOISE: promotions, newsletters, receipts. Send me a briefing: group 1 first (max 5 items, one line each, with who and what), then a one-line count of groups 2 and 3. For easy replies in group 1, write a draft and leave it in my Drafts folder. Rules: never send, delete or archive anything. If you're unsure which group something is in, put it in group 1.
Which tool to use
- agentGemini SparkBuilt-in Gmail access and schedulesGoogle AI Pro and Ultra subscribers in select countries
- agentGrok Bot (personal agents)Save it as a skill, then add a daily routineCheck plan requirements in xAI's docs
- agentClaude CoworkConnect Gmail, then ask it to make a scheduled taskCheck plan requirements on Anthropic's help page
- agentChatGPT dots (always-on agents)Always-on agent with connected appsRolling out to eligible paid plans; check OpenAI's page
What this costs to run
If you run this bot yourself on an AI API: our assumption is 22 runs a month, each reading about 15,000 tokens and writing about 800 (about 30 new emails a weekday at roughly 500 tokens each, and a one-screen summary back). That's about 330,000 tokens in and 17,600 out a month.
| Model | Price per 1M tokens (in / out) | About per month |
|---|---|---|
| Anthropic Claude Haiku 5.5 | $0.10 / $0.50 | $0.04 |
| Google gemini-3.8-flash | $0.75 / $3.75 | $0.31 |
| Anthropic Claude Sonnet 5.5 | $2.00 / $10.00 | $0.84 |
| OpenAI gpt-6-astra | $10.00 / $50.00 | $4.18 |
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
- Pick one boring job. Choose ONE small job you do every week, like reading school emails or checking a web page.
- Pick your tool. Use what you already have.
- Paste the instructions and fill in the [brackets]. Open a new chat in the tool.
- Say “Run this once now and show me the result”. Don't schedule anything yet.
- Then say “Do this every [day/time]” and lock it down. Once the result looks right, ask it to repeat on a schedule.
Safety notes
- Start read-only: it may read, but not send, buy, delete or change anything.
- Drafts stay in Drafts. You press send.
- Check the first week of briefings against your real inbox.