Loop/Prompt Library / Loops from builders on X
🔁 Idea to spec to build to review
Three AI helpers pass work along a board: one turns ideas into plans, one builds them, one tests them, and you just approve the final result.
Use it when: You have lots of feature ideas and want them built in order without managing every step.
🛑 Stops when: Each idea ends as a tested change waiting for your approval. Nothing merges until you say yes.
Copy this loop
We'll run three helpers on [project board]. Helper 1 (Planner): for each new idea card, ask me up to [5] questions, then write a plan with 'done when' and move the card to 'Ready to build'. Helper 2 (Builder): take the oldest 'Ready to build' card, build it on a new branch, and move it to 'Ready to test'. Helper 3 (Tester): take the oldest 'Ready to test' card, check it for security and speed, click through it with screenshots, and list how I can test it myself. If it fails, send it back to the Builder (at most [3] times, then flag it for me). When it passes, mark it 'Waiting for approval' and tell me. Never merge or publish without my yes. Stop each helper when its column is empty, or after [5] cards per day.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @AlexFinn. 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.