Prompt Engineer: Precise Prompts With Clear Success Criteria
Prompts tuned to your model, with rules for what they must never do.
The Prompt Engineer is an AI prompt engineer in the Ai1 platform by MyZone AI: it turns a rough brief into a prompt tuned to the text, image or video model you use, with written success criteria, a never-permit list and test cases, and it writes prompts rather than running them.
A prompt built for your model and your task gets you the result you want sooner, with less trial and error.
Guardrails from the first draft
Prompts that face customers or touch live tools carry clear never-permit rules, written in before anyone relies on them.
Prompts you can manage like an asset
A versioned library keeps track of which prompt does what and how it has changed, so nothing is lost when a person leaves or a model updates.
Meet your agent
Get to know Oscar
Oscar turns a rough idea into a precise, model-tuned prompt with clear success and safety criteria. He is curious, playful and takes fika very seriously.
AI agent. Fictional persona; not a real person.
Oscar, the persona of the Prompt Engineer
Name
Oscar L.
Role
Prompt Engineer
Experience
5 years
Work history
Conversational AI designer at a software startup Content designer at a digital agency
Personality
Curious, precise
Based in
Stockholm, Sweden
Why Oscar has a personality
AI does better work as a specific expert, so the Prompt Engineer works as Oscar (Prompt Engineer, Stockholm, Sweden). You can rename Oscar or change the personality, experience and profile settings at any time.
What you need the AI to do, as roughly or as fully as you like
Models it writes for
Text agents, image generators and video tools
With every prompt
Success criteria, a never-permit list and test cases
Measured scores
Run by the Evaluator against the test cases it writes
Your prompts
Kept in a versioned library with each one's model, settings and history
What it never does
Change your live assistants or tools; a person on your team makes the change
Capabilities
What the Prompt Engineer does for you
Writes prompts for your specific model
Takes your brief, asks targeted questions only when something important is missing, and writes a prompt shaped for the model you use rather than a generic template.
Sets out what success looks like
Every prompt comes with examples of good output, a list of things it must never do and test cases that can be used to check it.
Repairs prompts that underperform
Works out why an existing prompt gives poor results, rewrites it and explains what changed and why.
Builds safety into the wording
For customer-facing prompts or ones linked to live tools, it writes the guardrails and never-permit rules straight into the prompt.
Moves prompts to a new model
Ports your prompts when you switch models, removes what will not carry over and asks the Evaluator for a regression check where quality matters.
Keeps a prompt library
Organises your prompts into a versioned collection, each with its model, settings and change history.
How the Prompt Engineer differs from a prompt template
A template gives you wording and leaves you to find out whether it works. The Prompt Engineer asks targeted questions when a brief is unclear, recommends a model and settings, and writes a prompt shaped for that model. Every prompt comes with success criteria, a never-permit list and test cases, so the Evaluator can measure it. It writes prompts only, and a person on your team makes any live change.
How this differs from the Evaluator: the Evaluator runs the measured tests and scores, while the Prompt Engineer writes the prompt, its success criteria and the test cases the Evaluator runs.
How it works
From your request to a finished result
It runs inside your Ai1 system and works in the tools you already use. You ask, it works, it reports, and it stops for your OK where it matters.
Tap the diagram to enlarge it
Step 1: Share your brief
Tell it what you need the AI to do, as roughly or as fully as you like.
You approve
Step 2: Clarify if needed
If something material is unclear, it asks up to five targeted questions and you confirm the answers before it writes anything.
Step 3: Choose the right model
It recommends the model and settings that suit the task, and explains why.
Step 4: Write the prompt
It drafts the prompt tuned to that model, with the right structure and examples.
Step 5: Define success and safety
It writes down what good output looks like, what the prompt must never do and the test cases to check it.
Step 6: Deliver, test if needed
You receive the prompt and its criteria. When you want a measured score, the Evaluator runs the tests.
When to use it
Hand these situations to the Prompt Engineer
Illustrative photo. Ask why the chat assistant keeps promising refunds.
If this is you…
…here's what it does
Your chat assistant says things it should not
It rewrites the prompt so the assistant stays on brand and never offers something like a refund without a person's approval.
An image prompt keeps producing the wrong style
It diagnoses the problem, rewrites the prompt and notes what changed so you can see the difference.
You are moving to a different AI model
It ports your main prompts, versions them and asks for a regression check where the output matters.
Your prompts are scattered across documents and chats
It gathers them into one versioned library you can browse and reuse.
You are not sure which model suits a task
It recommends a model and settings and explains the trade-offs in plain terms.
What you get
A finished prompt tuned to your chosen model, ready to copy and use
Written success criteria and a never-permit list for each prompt
Test cases ready for the Evaluator to run
A note on what changed and why when a prompt is rewritten
A versioned prompt library with each prompt's model, settings and history
What it won't do
✕Run measured prompt tests and scoresHandled by: The Evaluator
✕Generate the images, video or text itselfHandled by: The generation tool or agent you use
✕Build reusable skills and tool packagesHandled by: The Skill Manager
✕Carry out the task a prompt is written forHandled by: The agent or person who runs the prompt
Example prompt rewrite
Example: support assistant prompt rewrite
Example with a fictional company. Names, people and figures are invented to show the agent's output. Any resemblance to a real company or person is unintended. Industry facts are real and cited with their sources.
What it was asked: Our chat assistant keeps promising refunds and guessing delivery dates: fix the prompt, keep it sounding like us, and make sure it never offers a refund without a person's approval.
Example report
The brief, and why the old prompt went wrongThe rewritten prompt, version 2.0What good looks like, and what it must never doTest pack for the evaluation agent, and who does what next
What it found: 3 findings, with the numbers
A "do whatever it takes to keep the customer happy" line caused the refunds: 6 of the 20 shared chats offered one. Refunds now always go to a person.
Delivery dates were guesses because nothing told the assistant to use the order lookup. The new prompt quotes dates only from the lookup and says plainly when it has none.
Fourteen scattered tone rules, two contradicting, became five rules and three example replies. Twelve test cases are written for the evaluation agent, which runs the measured score before launch.
The Prompt Engineer read the shop's current prompt and 20 example chats the shop shared (names and contact details removed first), asked two questions, then rewrote the prompt for Claude with success criteria, a never-permit list and 12 test cases, citing the model provider's own guidance. It did not run the prompt or score it: the measured test run belongs to the evaluation agent, and the support lead approves and a person on the shop's team makes the change to the live assistant. Run date: .
Builds the reusable skills and tool packages that sit outside prompt writing.
Common questions
Frequently asked questions about the Prompt Engineer
What are prompt success criteria?
The written test of a good prompt: examples of the output you want, a list of what the prompt must never do and test cases to check it against. The Prompt Engineer in Ai1 by MyZone AI writes them with every prompt.
The Evaluator then runs the prompt against those test cases and reports a measured result, so you know a new prompt actually performs.
Can prompt engineering fix an image prompt that keeps missing the style?
Yes. The Prompt Engineer works out why the prompt gives poor results, rewrites it for the image model you use and notes what changed and why. It covers text agents, image generators and video tools, using the right approach for each medium.
It writes the prompt only and hands it to you or to the tool you use; your image tool creates the picture.
How does prompt engineering stop a chat assistant from overpromising?
By writing guardrails and never-permit rules into the prompt itself, such as never offering a refund without a person's approval. The Prompt Engineer adds them to customer-facing prompts, and a person on your team approves the new prompt and makes the change to the live assistant.
What does an AI prompt engineer give me that a template does not?
A prompt shaped for the exact model and task you have, plus written success criteria, a never-permit list and test cases. A template gives you wording; good prompt engineering gives you a prompt you can check.
When an AI provider updates its models, it can check the provider's latest guidance, flag what has changed and update your prompts.
About Ai1
Do I get just the Prompt Engineer, or the whole platform?
The whole platform. The Prompt Engineer is included on every Ai1 level, including Developer Core, with no per-agent charge. It works alongside the other Ai1 agents on your account. Compare plans →
Two paths, one platform. Build it yourself on a developer plan, or let our team run your AI operations for you. Every plan runs on its own private server, and every price is shown in full. See Ai1 pricing →
Product & Engineering
Product & Engineering
Product & Engineering
Product & Engineering
Product & Engineering