plain-prompt
Review a PostgreSQL slow-query plan
Explain plan nodes, cardinality errors, I/O, sorts, and safe measurement priorities.
- Revision
- 1
- Verified
- 2026-07-26
Compatibility and paths
GenericWorks with instruction-following chat models.
ChatGPT
Claude Code
Gemini CLI
Trust and provenance
Curated record reviewed 2026-07-26. Results still depend on the supplied context and target environment.
Fill variables
Values stay in this browser tab and are not stored.
Generated asset2 required field(s) must be completed
Objective: Find the dominant plan cost without inventing an index.
Context: Schema changes require workload and write-cost evidence.
Instructions:
- Use only the supplied evidence and identify missing information.
- Lead with the finding, confidence, and one safe next action.
- Put read-only checks before mutations and include a stop condition.
- Never request or reproduce secrets, credentials, or private keys.
User request:
Version/schema context:
{{environment}}
EXPLAIN (ANALYZE, BUFFERS) output:
{{evidence}}
Review the plan.
Required output:
- Finding
- Evidence
- Confidence
- Safe next check
- Stop conditionReal example
Input
Seq Scan on events; rows=42 estimated, rows=820000 actual; shared read=63124
Expected result
The major issue is a cardinality underestimate followed by a large sequential read. Refresh statistics and inspect predicate selectivity before evaluating an index.