FixKit AI

Loop/Prompt Library / Loops from builders on X

๐Ÿ” Nightly tidy-up of shared AI notes

When several AI helpers share one notebook as memory, a nightly pass fixes outdated facts and connects loose notes.

Use it when: Your AI helpers keep reading old, wrong notes from a shared folder.

๐Ÿ›‘ Stops when: Tonight's pass is done, or the change limit is hit.

Copy this loop

Each night, read the shared notes in [folder]. Look for: facts that newer notes contradict, notes that say 'current' or 'latest' but are old, duplicate notes, and notes with no links. For each outdated fact, don't delete it: mark it as outdated with today's date and link to the newer note. Merge exact duplicates only. Add links between clearly related notes. Never store passwords, keys, or personal details. Log every change in [changelog]. Stop after one pass, or after [30] changes, whichever comes first.

Review every change the agent makes before you keep it. Set a budget or round limit โ€” the prompt includes one.

Found on X ยท by @eugeniu_ghelbur. 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.