Prompt Simulator
Practice prompt engineering the honest way: write a prompt for a real scenario, get a deterministic 0–10 score with per-dimension feedback, and see side-by-side what vague vs. precise prompts earn. Companion to the Prompt Engineering video course.
Before you start
Teaching simulation — no AI runs here. Outputs are hand-crafted examples showing what vague vs. precise prompts earn, so every student sees the same lesson. Nothing you type leaves your browser. For real-model practice, see Level 2 (coming soon).
Choose a practice scenario
Scenarios unlock in order — score 4+ to open the next one. Your best scores are saved on this device.
Scenario
Tip: give the AI a role, add context, set limits, name the format, and show what “good” looks like.
Your score
New personal best — saved on this device.
Feedback per dimension
See the contrast
Both outputs below are hand-written teaching examples — the same ones every student sees. No AI generated them.
What a vague prompt usually earns
Typical output
What a precise prompt earns
Typical output
Exemplar prompt
Study the highlighted cues — each highlight is a scoring keyword. Then try again and beat your score.
How to practice prompt engineering here
- Pick a scenario — start with “The Vague Email” from Episode 1. Later scenarios unlock as you score 4+.
- Read the task, then write your prompt like you would to a real AI assistant. Aim for a role, context, limits, a format, and an example of good.
- Hit “Test my prompt” for a deterministic 0–10 score plus one line of feedback per dimension — the same prompt always earns the same score.
- See the contrast to compare hand-written examples of what vague vs. precise prompts typically earn.
- Reveal the exemplar, study the highlighted scoring cues, and retry to beat your best — best scores are saved on your device.
Teaching simulation — no AI runs here. Outputs are hand-crafted examples showing what vague vs. precise prompts earn, so every student sees the same lesson. Nothing you type leaves your browser. For real-model practice, see Level 2 (coming soon).
Frequently asked questions
Is the Prompt Simulator a real AI?
No. It is a teaching simulation — no AI runs here. The example outputs are hand-crafted to show what vague vs. precise prompts typically earn, so every student sees the same lesson. Scoring uses simple deterministic keyword checks, not a model.
Is what I type private?
Yes. Nothing you type leaves your browser — there are no network requests, no accounts, and no servers. Only your best score per scenario is saved, in your own browser's local storage.
How is my prompt scored?
Each scenario checks five dimensions — role/persona, context, constraints, output format, and examples — for scenario-specific keywords, awarding 0–2 points each for a total out of 10. The same prompt always earns the same score.
How do I unlock new scenarios?
Scenarios unlock in order: score 4 or more out of 10 on the current scenario to unlock the next one. Your best score per scenario is remembered between visits.
Will there be more scenarios?
Yes — the picker already lists 15 upcoming scenarios across Episodes 1–10 of the course, marked “coming soon”. Three scenarios are fully playable today.
More from the codex
Prompt Simulator
Practice prompt engineering with deterministic scoring.
Word Counter
Count words and estimate reading time instantly.
Open tool → LiveFlashcard Maker
Spaced-repetition flashcards for any subject.
Open tool → LiveText-to-Speech Reader
Hear your essay read aloud for proofreading.
Open tool →Support the codex
This tool is free, with no account and no ads. If it saved you some time, consider supporting the indie dev behind it.
Questions or a bug to report? Email [email protected].