Provely

Questions

What does Provely actually do with my prompt?

It runs your exact prompt once on each of three models and shows you what came back. How the three runs work.

Why a count instead of a score out of 100?

A score out of 100 is an opinion. A count is a fact we can show you the runs for. Why the headline is a count.

What is the difference between Unfussy and Verbose?

Unfussy shows concise findings and model-answer summaries, with controls to open each explanation or full answer. Verbose opens these details together. The switch applies to Findings, Verdict and Models; it does not change the wording of an improved prompt, your selected fixes or your Context.

What do the numbers on my prompt mean?

Each mark on your prompt has a numbered note explaining it, reading left to right, top to bottom. The same numbers appear in the fix list so you can match a suggestion to the exact spot it touches.

Does Provely change my prompt without asking?

Never. Ticking fixes builds a draft you read and edit before anything runs. How fixes and re-runs work.

What does Check again do in my history?

It loads that prompt into the paste box on the start page so you can run a fresh check on it. It does not spend anything until you press the run button.

What do you store, and for how long?

An unsaved check is purged 30 days after you run it. A check you save, or one you run while signed in, stays until you delete it. Counts and categories stay so your history still makes sense.

Why are runs limited?

Every run costs us real model fees, so free checks have a daily allowance. The limits page explains how each allowance works and when it resets.

Which model should I trust?

Whichever one did what you asked. We name a best fit per prompt and have no stake in which model wins. What each run shows you.

How to use Provely

Here is the whole run, from a prompt you are unsure about to one you can use.

  1. Paste your promptPut the prompt you want to test into the box on the home page. Nothing runs until you press the button.
  2. Read the findingsYour prompt comes back marked up. Everything is measured against what Provely read it as asking for; if that reading is wrong, Edit the intent and the findings are rebuilt from your version.
  3. Read the runsYour exact prompt goes once to each model in the run. You get every answer in full, an estimate of what it cost, and marks on your own words showing what held and what did not.
  4. Answer the questionsThe findings come with short questions about the things only you know, such as the format you want or who the answer is for. Answering is optional, and each answer you give goes into the improved prompt.
  5. Pick your fixesTick the fixes you want and Provely writes an improved prompt from them. You get two of those rewrites per check. You can also edit the draft by hand as much as you like.
  6. Run the re-testRun the improved prompt and compare. The before and after sit side by side, with the evidence behind every mark.
  7. Take it away, or share itCopy the improved prompt and use it wherever you like. Sharing a result is a separate choice, and you see a preview of exactly what goes public first.

The longer walkthrough is in the Prompt Check guide.