Online, limited
10 campaigns · up to 20 rounds eachIncludes:
- Runs on our machines — zero setup
- Full live monitoring as it runs
- Bring your own API key when free runs end
- Take your results with you anytime
Your labelled examples go in; a prompt that scores higher on them comes out. Here is what the loop does with them, and the manual that walks it end to end. No license keys, no setup ceremony.
New to this? Read where PromptPotter sitsPromptPotter treats your prompt as a program with tunable axes. Each round it mutates one axis at a time — with a cited reason, never a random guess — and breeds a population of candidates to test.
{
"persona": "You are solving a grade-school math word problem.",
"task_intent": "Read the problem carefully and produce one exact numeric answer.",
"problem_description": "",
"instruction": "Work through the problem step-by-step. Track quantities and units explicitly. Double-check each arithmetic operation before continuing.",
"thinking_style": "Deliberate chain-of-thought. Do not skip intermediate computations; verify each against the problem statement."
} {
"thinking_style": [
"Think step-by-step: break the problem into smaller arithmetic steps.",
"Work backwards from what the question asks to what you need to compute.",
"Write out each calculation explicitly before giving the final answer.",
"Double-check your arithmetic at each step before proceeding."
],
"instruction": [
"Solve the math problem step by step. End your answer with #### followed by the numeric answer.",
"Show your work clearly. The final answer must be a single number after ####.",
"Break this into steps. After solving, verify by re-reading the question."
],
"persona": [
"You are a patient math tutor who shows all work.",
"You are a careful problem solver who double-checks calculations."
]
} Real config from the GSM8K dataset in the PromptPotter repo. The origin is the conservative floor; every variant changes exactly one axis.
The full walkthrough lives in the optimizer repo, where it stays in step with the code. Each chapter opens on GitHub.
It’s just in and out. Hand over what you’re running and the examples you already have, then leave it alone. Five minutes later there’s a better version waiting with its score beside it. Watch every round if you like, or none of them. No schemas, no special code, nothing to wire up.
Includes:
Includes:
Everything above, plus: