AI Prompt for Optimizing SQL Queries

Speed up slow SQL with this AI prompt: execution-plan analysis, index recommendations, and a rewritten query that returns the same results faster.

The prompt

Role: You are a database performance consultant who makes slow queries fast without changing their results.

Context: Dialect: [DIALECT]. The slow query: [SLOW_QUERY]. It takes [EXECUTION_TIME] on [TABLE_SIZES]. Schema and existing indexes: [SCHEMA_AND_INDEXES]. Execution plan: [EXPLAIN_OUTPUT].

Task: 1) Diagnose from the plan: what is the expensive step (seq scan, nested loop, sort spill, correlated subquery)? 2) Rewrite the query for speed while returning IDENTICAL results — prove equivalence by explaining the transformation. 3) Recommend specific indexes (exact CREATE INDEX statements) with the reasoning for each. 4) Estimate the expected improvement and state what to measure to confirm it.

Format: Diagnosis first, then the rewritten query, then index recommendations, then how to verify.

Ask the AI to predict the new execution plan in words before you apply the changes, then compare with the actual EXPLAIN afterward. Matching prediction to reality is how you build a reliable intuition for query plans.

Constraints: Results must be identical — no changing semantics for speed. Prefer index and rewrite fixes over hardware or config changes. Warn if the rewrite trades write performance for read performance.

Variables to fill in

Replace each [variable] in the prompt with your own details:

[DIALECT] [SLOW_QUERY] [EXECUTION_TIME] [TABLE_SIZES] [SCHEMA_AND_INDEXES] [EXPLAIN_OUTPUT]

Example input

DIALECT=PostgreSQL, SLOW_QUERY=SELECT with 3 JOINs and a correlated subquery taking 8s on 2M rows, SCHEMA=tables + indexes listed, PLAN=EXPLAIN ANALYZE output pasted

How to use this prompt

Paste EXPLAIN/EXPLAIN ANALYZE output — it is the single most valuable input for optimization. Include table sizes and existing indexes.

Tips for the best results

Always test the rewritten query returns identical results on a data sample first.
Ask which index helps which part of the query — understanding beats copy-paste.
Re-run EXPLAIN after applying changes and ask the AI to confirm the plan improved.

Frequently asked questions

Can it optimize without seeing my data?

It finds the classic culprits (correlated subqueries, missing indexes, functions on indexed columns). Paste EXPLAIN output for a precise diagnosis.

Will the rewritten query always be faster?

On your data and indexes, almost always — but verify with EXPLAIN ANALYZE. Data distribution surprises even experts, so the prompt includes a verification step.

Related SlickCalcs tools

Scientific Calculator

More coding prompts

AI Prompt for SQL-to-ORM Conversion

Convert raw SQL to ORM code with this AI prompt: idiomatic queries for your ORM, N+1 risks flagged, and guidance on what should stay raw SQL.

AI Prompt for Storage Decisions

Decide where data lives with this AI prompt: database vs cache vs memory analysis on durability, latency, size, and operational cost trade-offs.

AI Prompt for Structure Trade-offs

Compare data structures head-to-head with this AI prompt: trade-off matrix on your workload, cache and memory analysis, and a conditional winner.

AI Prompt for Sync-to-Async Conversion

Convert sync code to async with this AI prompt: correct async/await conversion, independent calls parallelized, and every semantic change flagged.

AI Prompt for Git Commit Messages

Write perfect git commit messages with this AI prompt: conventional-commit format from your diff, with the why explained and scope chosen correctly.

AI Prompt for REST-to-GraphQL

Convert REST to GraphQL with this AI prompt: client-driven schema design, N+1-safe resolvers with batching, and a reversible strangler migration plan.