Loop/Prompt Library / Loops from builders on X

🔁 Try old AI failures again when new models arrive

Q: How do I run the try old ai failures again when new models arrive with an AI agent?

Keep a list in [file] of tasks AI failed at for me: the exact request, the date, which model, and what went wrong. When a new model is released, run each task again with the new model using the same request. Judge each result against what went wrong last time. Only tell me about tasks that now clearly work, with the old and new results side by side. Don't include private details in the saved tasks. Stop after one pass through the list, or after [20] tasks.

Keeps a list of things AI couldn't do for you, re-tries them when a new model comes out, and only tells you about the ones that now work.

Use it when: You've given up on some AI tasks, but models keep getting better.

🛑 Stops when: Each new-model run ends with a short list of newly solved tasks, or nothing.

Copy this loop

Keep a list in [file] of tasks AI failed at for me: the exact request, the date, which model, and what went wrong. When a new model is released, run each task again with the new model using the same request. Judge each result against what went wrong last time. Only tell me about tasks that now clearly work, with the old and new results side by side. Don't include private details in the saved tasks. Stop after one pass through the list, or after [20] tasks.

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

Found on X · by @BradleyYoungjr. 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.