Engineering
One QA bot per app, woken by Basecamp cards in "QA Needed"
QA is the bottleneck between "done" and "ready for review".
What hurt
Scott Reyes (@scottdreyes) has a QA bot for each of his three software applications. In one day they QA'd 27 cards over 43 rounds and left 65 notes. Not affiliated with xAI.
What to install or create
Each bot gets the QA manual (including training videos), Basecamp access and logins to the software. When a card lands in QA Needed, it wakes up, does experiential QA in the browser and code-level QA in the terminal, then moves passing cards to Ready for Human Review and failed or blocked cards back to In Progress.
Bots
QA bot (one per app)
Tests cards in QA Needed and moves them on.
Plugins
Browser
Required
GitHub
Optional
Routines
None on the first run. Watch one manual pass first.
The prompt
This is a tip, not a pasteable system prompt. The author did not publish one. Follow the first-run steps.
First run
- 1Read https://x.com/scottdreyes/status/2108292028853518531 (credit @scottdreyes).
- 2Write or collect your QA manual and give it to one bot per app.
- 3Give it Basecamp (or your board) access and test logins.
- 4Tell it: when a card lands in QA Needed, test in the browser and terminal, leave notes.
- 5Passing cards go to Ready for Human Review; failed or blocked go back to In Progress.
Approval fence
Give the bots test logins, not admin accounts. Nothing ships until a human reviews the card.
What to tweak
Bots move cards between columns; a human still does the final review.
Source
Scott Reyes @scottdreyes · Original post
Not affiliated with xAI. We did not write this prompt. Third-party template terms still apply.
Pro pack
Want the full setup, not just the idea?
Pro packs give you the job text, prompts, schedules and pitfalls for popular use-cases.