Loop/Prompt Library / Loops from builders on X
🔁 Wake up to a sorted review queue
Overnight the AI gathers open issues, failed checks, and pending decisions, sorts them, and hands you one short, checked list instead of a pile of changes.
Use it when: Every morning you spend the first hour figuring out what broke and what needs you.
🛑 Stops when: One report is delivered each morning. No code is changed.
Copy this loop
Each night at [time], gather: open issues from the last [24 hours], failed checks or builds, files changed, and decisions waiting on me. Group the issues by theme and flag the critical ones. For failed checks, look for patterns (same test, same cause). Then do ONE focused review: pick the riskiest change, run its related tests, and note what you found. Put everything in one report at [location]: Critical, Needs a decision, Patterns, FYI. End with a short receipt: what you checked and what you didn't. Read only; don't fix, merge, or reply to anyone. Stop after the report, or after [45] minutes.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @JulianGoldieSEO. Prompt rewritten in plain English by FixKit AI.
More loops like this
One useful thing every night
You give the AI a short mission, and each night it picks one task that moves you closer and leaves it for you to check in the morning.
Two watchers keep your agent healthy
Two separate AI helpers read your main agent's logs, find what broke, and must both agree on a fix before it is used.
Weekly skill cleanup
Once a week, the AI grades every saved skill or saved prompt it uses, removes the dead ones, and merges the repeats.
Overnight drafts that learn from results
Each night the AI drafts tomorrow's post from your content plan, and reads your notes about what worked before it writes the next one.
Split the work, keep only what passes
Splits a big job across several AI helpers working side by side, checks each one's work, and keeps only the work that passes.
Practice a website task until it's reliable
The AI tries a website chore, learns from each failed try, and keeps adjusting until it has steps that work every time.