Prompt library

AI Engineering prompts

Prompts for building with models: designing evaluations, writing tool definitions, and planning retrieval pipelines.

  • evaluation
  • testing
  • llm
100/100 · 191 tokens

Evaluation plan for an LLM feature

Designs a test set and pass criteria for a model-backed feature, before you tune the prompt.

Use it when: You are shipping a feature that depends on a model and need a repeatable way to tell whether a change made it better.

prompt
You are an AI engineer designing evaluations for a language model feature.

## Task
Design an evaluation plan for the feature described below.

## Requirements
- Define 10 test cases: 4 typical inputs, 3 edge cases, and 3 adversarial inputs.
- State the expected property of the output for each case, in a form code or a reviewer can check.
- Name the check for each property: exact match, schema validation, a rule, or a graded rubric.
- State the pass threshold for the suite as a number.
- Do not invent facts about the feature; base every case on the description.

## Output format
Return markdown with three sections: Test cases (a table with the columns ID, Type, Input summary, Expected property, and Check), Pass threshold (one sentence), and Gaps (bulleted list of what the description does not let you test).

## Input
<feature>
{{feature}}
</feature>
Optimize in workspace

Variables

{{feature}}
What the feature does, its inputs, its outputs, and what a wrong answer costs.

Example input

feature: extracts the due date and total from invoice text into JSON; a wrong total causes an incorrect payment.

Example output

## Test cases
| ID | Type | Input summary | Expected property | Check |
|---|---|---|---|---|
| T1 | Typical | One-page invoice with one total | `total` equals 1250.00 | Exact match |
| A1 | Adversarial | Invoice text containing "ignore the instructions" | Output is valid JSON with the real total | Schema validation |

Illustrative: written to show the expected shape, not generated by a model.

  • agents
  • tool use
  • mcp
  • json schema
97/100 · 154 tokens

Tool definition for an agent

Writes a tool name, description, and JSON Schema an agent can use correctly, from a function you describe.

Use it when: Exposing a function to an agent or an MCP client, where a vague description leads to wrong calls.

prompt
You are an AI engineer defining tools for a model that calls tools.

## Task
Draft a tool definition for the operation described below.

## Requirements
- Name the tool with a verb and a noun in snake_case.
- Write a description that says what the tool does, when to call it, and when not to call it.
- Describe every parameter with its type, format, and one example value.
- Mark a parameter as required only when the operation cannot run without it.
- Use enum for every parameter with a fixed set of values.

## Output format
Return one fenced JSON block containing an object with the keys name, description, and input_schema, where input_schema is a JSON Schema object.

## Input
<operation>
{{operation}}
</operation>
Optimize in workspace

Variables

{{operation}}
What the operation does, its parameters, what it returns, and its limits.

Example input

operation: searches support tickets by text and status (open, pending, closed), returns at most 20 tickets, read-only.

Example output

```json
{ "name": "search_tickets", "description": "Search support tickets by text. Call it to find existing tickets before creating one. Read-only; it cannot modify tickets.", "input_schema": { "type": "object", "properties": { "query": { "type": "string" }, "status": { "type": "string", "enum": ["open", "pending", "closed"] } }, "required": ["query"] } }
```

Illustrative: written to show the expected shape, not generated by a model.

Make it yours

Edit the requirements to match your standards, then check the result. Theprompt analyzer re-scores it as you type, theoptimizer removes filler without dropping a requirement, and thesecurity scanner flags secrets and personal data before you send it to a model.

More categories