Create invoice PDFs, review them, then send after approval
An agent built invoice PDFs for billing or reimbursements, sent the draft to the user, and mailed the final version only after approval.
- What they did
- A user would send a request such as billing a client for completed work or reimbursing costs. The agent put together an invoice PDF on its own, using the user’s saved identity and recipient details, and emailed that draft back for review. It then paused until the user answered with yes or asked for edits.
- How it went
- After approval, the agent delivered the final invoice to the recipient already stored in the system. The process worked as intended, and no failures or numbers were reported.
- Tips
- Make sure the recipient and billing info are already entered correctly before using this. Keep a clear review step so the invoice does not go out until you confirm it.
Try it yourself with Lindy
I’m going to tell you about [work completed] or [costs I need repaid] for [client or company]. Build an invoice PDF with my saved information [name, address, payment details] and the item details [line items, rates, amounts]. Send the draft PDF to me by email and stop. Do not forward anything to [client email] until I reply "yes." If I send changes, update the invoice, email the revised draft back to me, and wait again. Only send the final invoice after I approve it.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Build an invoice sorter for email attachments
They made a tool that scans inbox invoices, pulls out key fields, and stores them in a searchable system for teams that still use email for billing.
Set up an overnight Shopify monitor and fixer
A five-agent system watched a Shopify store after hours, handled simple repairs, and asked before making sensitive changes.
Turn screen recordings into repeatable procedures
They used Screenpipe to log screen and audio locally, then had an agent convert repeated work into SOPs and automations.
Build a 7am daily brief from inbox, calendar, and tasks
A personal agent gathers morning updates from email, calendar, and Todoist and sends one concise brief instead of forcing a full inbox scan.
Use a voice agent for oral exams
A professor used a voice agent to run oral finals, then had an LLM panel grade the transcripts and flag shared weak spots.
Let an agent help run a small business
Andon Labs used a persistent agent to operate real businesses with company tools and oversight.