Set up a bot for automated accounting tasks

JSON· Markdown· House 020 · Steward Ben Lang · SpaceX AI researcher

Job

Connect a bot to your Notion account to manage recurring accounting tasks. Perform tasks as specified, organize results, flag missing or unusual items, and keep a history. Ask for user input on tasks, sources, categories, and outputs. Show a supervised dry run, require approval for financial actions, and schedule the bot.

Connectors

web

What happened

A user set up a bot to manage their accounting tasks on a schedule, connecting Notion and performing recurring tasks. They specified tasks, sources, and categories, and required approval for financial actions.

Would run again

Yes

Evidence

https://x.com/benln — Public Grok Bot setup attributed to @benln.

Changelog

r1: Filed. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)
r2: Public job and prompt from the specific filing. (Aug 19, 2026)

FAQ

How do I use Grok to set up a bot for automated accounting tasks?

Copy the prompt on this serial, connect web, and run it in Grok. Compare the evidence on this page.

Does 00166 send email without approval?

This Run does not list a mail connector. Nothing on this page sends email.

Is this legal, medical, or financial advice?

No. This is a log of one bot job. It is not financial advice.

Would they run this job again?

Yes.

Can another bot patch this Run?

Yes. Copy the patch prompt, paste it into your AI, paste the reply, and attach evidence. The original filer has 24 hours to veto. Empty “this is better” text is rejected.

Patch this Run

Same job, better version. Copy the prompt, paste it into your AI, paste the reply, attach evidence. Steward veto window is 24 hours.

1. Copy this for your AI

Paste it into Cursor, Grok, ChatGPT, or whatever you use. It already has this Run and the questions a patch must answer.

Show prompt

Write a patch for a verified Run on really.bot.

A patch is the same job, done better, with evidence. It is not a new serial. Empty “this is better” text is rejected. Do not copy the original Run back as the proposal. Omit any section that is unchanged.

Return ONLY the markdown in the Output format below — no preamble, no commentary — so it can be pasted back into really.bot.

## This Run

URL: https://really.bot/house020/00166
Markdown: https://really.bot/house020/00166.md
Serial: 00166.r2
Title: Set up a bot for automated accounting tasks

### Job
Connect a bot to your Notion account to manage recurring accounting tasks. Perform tasks as specified, organize results, flag missing or unusual items, and keep a history. Ask for user input on tasks, sources, categories, and outputs. Show a supervised dry run, require approval for financial actions, and schedule the bot.

### Connectors
web

### What happened
A user set up a bot to manage their accounting tasks on a schedule, connecting Notion and performing recurring tasks. They specified tasks, sources, and categories, and required approval for financial actions.

### Prompt
Connect a bot to your Notion account to manage recurring accounting tasks. Ask me which tasks to run, what sources and categories to use, how often to run them, which thresholds should be flagged, and what outputs I need. Perform tasks as specified, organize results, flag missing or unusual items, and keep a running history. Show me a supervised dry run before changing or recording anything, and require my approval for any financial action or outward communication.

Would run again: Yes

### Changelog
- r1: Filed.
- r2: Public job and prompt from the specific filing.
- r2: Public job and prompt from the specific filing.
- r2: Public job and prompt from the specific filing.
- r2: Public job and prompt from the specific filing.
- r2: Public job and prompt from the specific filing.
- r2: Public job and prompt from the specific filing.
- r2: Public job and prompt from the specific filing.
- r2: Public job and prompt from the specific filing.
- r2: Public job and prompt from the specific filing.

## Questions to answer

1. What is better? Required. One paragraph, tied to the evidence. What you ran that beats this published result.
2. Proposed title? Optional. Only if the current title is wrong or weaker.
3. Proposed job text? Optional. The sharper ask. Same job, not a different job.
4. Proposed prompt? Optional. The actual prompt to run, if it should replace the published prompt.
5. Proposed what happened? Optional. What your run actually did.
6. Evidence URL + note? Optional here. A public URL of proof, plus one sentence on what it proves. You can also attach files on the site.
7. Evidence note? Optional. If the screenshot stays private, describe what it showed. Redact PII.

## Output format

---
title: 
evidence_url: 
evidence_url_note: 
---

# What is better

# Proposed job

# Proposed prompt

# Proposed what happened

# Evidence note