What it does: Writes the prompt for Lovable to build a small app where your crew sees today's jobs, marks them done and adds a photo.
Use it when: Jobs live in texts and a whiteboard, and things get missed.
You get: One Lovable prompt, the screens and fields, who can see what, and 6 tests to run before the crew uses it.
You are my app planner, a pro who has planned simple phone apps for small crews. I'll build it in Lovable. Goal: plan a small job tracker and write ONE prompt for Lovable to build it, so I have a prompt ready to paste for an app where my crew sees today's jobs, marks them done and adds a photo, plus 6 tests to run before they use it. Context: I run a service business with a small crew. Jobs live in texts and a whiteboard, and things get missed. The crew needs something simple on a phone, because they won't use an app that takes more than a few taps. First, check that you can read the details I gave you about my business and crew. Tell me how many crew members and job fields you found. If any are missing, use the defaults below and say so, or ask me to paste them instead. If I already have a Lovable project for this, check that you can read its files and tell me how many pages it has. If you can't read them, stop and ask me to paste the page list instead. Ask me these, then run. Skip any I already answered. 1. What do you do, and who uses it? (Default: a service business, me plus 4 crew members.) 2. What does a job have? (Default: customer, address, date, what to do, notes.) 3. What does the crew do in it? (Default: see their jobs, mark done, add a photo.) Do this: 1. List the screens: for the crew, and for me. 2. List the fields for a job, and which are required. 3. Say who can see and change what: crew see only their own jobs, I see all. 4. Keep it simple. Check each screen and field against what I listed. If it's not on my list, leave it out. If something I listed needs chat, payments or maps, leave it out and tell me. 5. Write ONE prompt for Lovable with all of this. Ask for: log in, phone first, big buttons, a "Today" view, a "Done" button that saves the time, photo upload. 6. Write 6 tests: crew can't see another person's job, a photo saves, done time saves, I can add a job, it works on a phone, log out works. 7. Tell me how to use it: paste the prompt into a new Lovable project, look at the preview, then run the 6 tests before the crew sees it. Example line for the Lovable prompt, match this: "Each crew member logs in and sees a Today list with only their own jobs, biggest button first." Give me: the screens as a list, the fields as a table (field, required yes or no), who sees what in 3 lines, the Lovable prompt in one block under 250 words, and the 6 tests as a check list. Before you show me, check: - Every screen and field in the plan is in the Lovable prompt, and nothing is in the prompt that isn't in the plan. - All 6 tests are there, and "crew can't see another person's job" is first. Rules: - Keep it to what I listed. No chat, no payments, no maps, no extra fields unless I ask. The one field you may add is "assigned to", so crew see only their own jobs. Mark it (suggested). - The Lovable prompt uses the same plan, word for word where it can. - If you have to pick something I didn't give you (a name, a time, a setting, a day), mark it (suggested). - Drafts only. Never publish, deploy, delete or share the app, and ask me before you change anything in Lovable. - Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise. - If something you need is missing, write [check: what is missing] in that spot and keep going. Last, save these steps as a skill called 'Job Tracker App' so you do it this way each time I build a job tracker. To run it again, just say: "Run my Job Tracker App skill."
You needLovable
![]()
Any AITested on sample data
Built on Extreme Ownership's keep it simple.
Copilot version
There is no separate Copilot version of this one yet. Paste the prompt above into Microsoft 365 Copilot Chat.
See a real example
Tested on sample data Oct 29 2026, after the rewrite: a Claude agent ran it on made-up sample input (tool results simulated). A separate Claude agent judged the run and the card.
Watch: no video for this one yet.
AuthorCorey Leon