⚙ Blueprint
Follow-Up Finder
Never let a client, lead or friend go cold because you forgot to reply.
- Goal
- Never let a client, lead or friend go cold because you forgot to reply.
- Runs
- ⏱ Every Monday at 8:00am
- Watches
- 👁 Your sent mail, calendar and task list
What it does, step by step
- Looks at the last 30 days of sent email, meetings and tasks.
- Finds threads where you owe something or nobody replied for 7+ days.
- Drafts a short, friendly nudge for each.
- Sends you the list; you choose which to send.
Paste these starter instructions
Copy, paste into your tool, and replace the [brackets] with your details.
You are my Follow-Up Finder. Every Monday at 8:00am, look at my sent email and calendar from the last 30 days. List: (a) things I promised and haven't sent, (b) questions I asked with no reply after 7 days, (c) meetings with no follow-up email. For each, write a 2-sentence friendly follow-up in my style and leave it as a draft. Rules: never send. Skip anything marked personal or anything with lawyers, doctors or HR.
Which tool to use
- automationn8nA shared 8-node workflow exists (see source)Free to self-host; paid cloud plans
- automationZapierScheduled Zap + AI stepFree plan; paid plans add more
- agentGemini SparkGmail + Calendar accessGoogle AI Pro and Ultra subscribers in select countries
- agentGrok Bot (personal agents)Weekly routineCheck plan requirements in xAI's docs
What this costs to run
If you run this bot yourself on an AI API: our assumption is 4 runs a month, each reading about 30,000 tokens and writing about 1,000 (a week of sent mail and threads scanned once a week). That's about 120,000 tokens in and 4,000 out a month.
| Model | Price per 1M tokens (in / out) | About per month |
|---|---|---|
| Anthropic Claude Haiku 5.5 | $0.10 / $0.50 | $0.01 |
| Google gemini-3.8-flash | $0.75 / $3.75 | $0.10 |
| Anthropic Claude Sonnet 5.5 | $2.00 / $10.00 | $0.28 |
| OpenAI gpt-6-astra | $10.00 / $50.00 | $1.40 |
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
- Drafts only.
- Some threads went quiet for a reason. Read before sending.