Interactive Prompt Engineering Lab

Test and score your prompts against real-world enterprise scenarios. Get immediate 4-axis quality telemetry, negative guardrail verification, and golden reference prompts.

Read Syllabus

1. Authoritative Persona

Expert role + zero fluff

25 pts

2. Deterministic Schema

XML tags + JSON / keys

25 pts

3. Negative Guardrails

NEVER / fallback rules

25 pts

4. Token Efficiency

150–1,800 chars concise

25 pts

Data Engineering & RAGIntermediate

SQL Query Generation from Ambiguous Natural Language

Convert an ambiguous business question ("Who are our top customers this quarter?") into a safe, deterministic PostgreSQL query with explicit date filters, aggregations, and limit clauses.

Target Input Context / Untrusted Data:

Database Schema:
- customers (id, name, created_at, plan_tier)
- orders (id, customer_id, total_amount_cents, status, created_at)
Ambiguous Prompt: "Who are our top customers this quarter?"

Quality Requirements & Guardrails:

Define a Lead Analytics Engineer persona.

Resolve "top" unambiguously as total completed order spend in cents.

Resolve "this quarter" using date_trunc('quarter', CURRENT_DATE).

Filter out cancelled, refunded, or failed order statuses.

Include a LIMIT 10 clause and performance index comment.

Your System Prompt Draft

49 chars~12 tokens

Golden Reference Architecture (100% Quality Benchmark)

<system_instructions>
You are a Principal Analytics & SQL Engineer.
Translate the business request "Who are our top customers this quarter?" into an efficient PostgreSQL query.

AMBIGUITY RESOLUTION & SAFETY:
1. BUSINESS METRIC: Define "top" strictly as total settled revenue (`SUM(total_amount_cents) / 100.0`).
2. STATUS FILTERING: Filter strictly for completed orders (`orders.status = 'completed'`), explicitly excluding pending or refunded records.
3. TEMPORAL ANCHORING: Use dynamic PostgreSQL date functions (`orders.created_at >= date_trunc('quarter', CURRENT_DATE)`) rather than hardcoded dates.
4. PROTECTION: Enforce `LIMIT 20` to prevent unconstrained result sets.
5. Output query inside <sql_query> tags with a brief technical commentary on required indexes.
</system_instructions>