Skip to main content
CodingArchitectureadvanced

System Performance Bottleneck & Latency Waterfall Profiler

Optimized for Claude, Chatgpt, Gemini • Verified Prompt Template

Diagnose CPU spikes, memory leaks, event loop delays, and distributed latency waterfalls in production.

Compatibility & Specs

Compatible AI Models
ClaudeChatGPTGemini
Last UpdatedOct 3, 2026
Customizable Variables3 parameters

How to Use This Prompt

Follow this 3-step workflow to extract high-signal responses from any compatible AI model.

01

1. Tailor the Parameters

Use the interactive customizer above to substitute the bracketed placeholders with your exact context, requirements, and constraints.

02

2. Send to AI Model

Copy the prompt and paste it into Claude, ChatGPT, Gemini, or Copilot. These models follow structured multi-step constraints reliably.

03

3. Review and Iterate

Review the output against the verified benchmark below. Follow up in the conversation to stress-test edge cases or refine tone.

Prompt Variables & Parameters

Reference breakdown of every dynamic variable embedded in this prompt template.

PlaceholderParameter NameTypeStatusDescription & Guidance
[system_runtime]Service Architecture & RuntimetextRequiredLanguage, framework, and deployment contextDefault: Node.js 20 API on AWS ECS with PostgreSQL and Redis, handling JSON payload exports.
[observed_symptoms]Observed SymptomstextareaRequiredLatency metrics, CPU graphs, memory leaksDefault: When users request large CSV/JSON report exports, container CPU jumps to 100% and event loop lag exceeds 500ms, causing unrelated lightweight health-check requests to time out and ECS to kill the container.
[apm_data]APM / Profiler DatatextareaRequiredTrace data, Datadog flamegraph, or slow function tracesDefault: Datadog APM flamegraph shows 70% of CPU time spent in `JSON.stringify` and `Array.prototype.map` formatting 80,000 database row objects in memory before sending the HTTP response.

Example Output & Parameters Breakdown

Inspect verified benchmark AI responses and review how parameters, system constraints, and input variables calibrate generation.

Parameters & Variable Breakdown

3 Inputs
[system_runtime]
Node.js 20 API on AWS ECS with PostgreSQL and Redis, handling JSON payload exports.
[observed_symptoms]
When users request large CSV/JSON report exports, container CPU jumps to 100% and event loop lag exceeds 500ms, causing unrelated lightweight health-check requests to time out and ECS to kill the container.
[apm_data]
Datadog APM flamegraph shows 70% of CPU time spent in `JSON.stringify` and `Array.prototype.map` formatting 80,000 database row objects in memory before sending the HTTP response.

Verified AI Benchmark Response

Grounded Output
### Performance Bottleneck Analysis #### 1. Classification: CPU-Bound Main Thread Starvation Node.js is single-threaded. Serializing 80,000 objects via `JSON.stringify` synchronously locks the JavaScript event loop for 450ms. During this window, Node cannot process HTTP I/O or respond to ALB health-checks, triggering false-positive ECS task termination. #### 2. The 3-Step Remediation Plan - **Immediate Code Fix (Transform Stream):** Replace in-memory array accumulation with Node.js stream pipeline: ```typescript import { pipeline } from 'node:stream/promises'; // Stream directly from Postgres cursor -> JSON Transform Stream -> HTTP Response ``` This buffers only 16KB in memory at any moment, dropping event loop lag from 500ms to <2ms. - **Offload Heavy Work to Worker Threads:** If data manipulation requires complex calculations, delegate to a Node.js `worker_threads` pool. - **Background S3 Presigned URL Pattern:** For exports exceeding 10,000 rows, convert the endpoint into an asynchronous job: generate the export in a worker, upload to S3, and email the user a download link.

Best Use Cases

Scenarios and roles where this prompt produces maximum leverage.

Backend developers eliminating CPU spikes and event loop blocks under high concurrency
Engineers optimizing slow API responses using APM flamegraph telemetry
Architects restructuring synchronous blocking endpoints into asynchronous streaming architectures

Tips for Best Results

Techniques to elevate response fidelity

  • •Provide rich background context rather than one-sentence inputs to receive deep, non-generic responses.
  • •Engage in multi-turn conversation: use the initial output as a baseline, then ask the AI to sharpen specific sections.
  • •Prompt the model to highlight any hidden assumptions or missing trade-offs in its recommendations.

Common Mistakes to Avoid

Frequent failure modes and anti-patterns

  • •Giving minimal context and expecting nuanced, expert-level strategic output.
  • •Not validating factual references, citations, or statistical claims with verified primary sources.
  • •Skipping the customization step and pasting raw bracketed template variables into the AI chat.

Frequently Asked Questions About This Prompt

Technical guidance on model compatibility, parameter substitution, iteration techniques, and commercial usage.

Q1.Which AI models work best with the "System Performance Bottleneck & Latency Waterfall Profiler" prompt?

This prompt is thoroughly tested and compatible with Claude, Chatgpt, Gemini. For multi-step reasoning, architectural planning, and code refactoring, Claude 3.7/3.5 Sonnet and ChatGPT-4o provide the highest constraint adherence. For large-document synthesis, Google Gemini 2.5 Pro is also recommended.

Q2.How do I customize the parameters in this prompt template?

This template features 3 customizable parameter(s): [system_runtime], [observed_symptoms], [apm_data]. Replace each bracketed placeholder with your project's specific details, constraints, or code before submitting to your AI model. You can also use our interactive workbench on this page to populate and copy the completed prompt in one click.

Q3.Can I use this prompt and its outputs for commercial projects?

Yes. All prompts published on Beautiful AI Prompt are 100% free for both personal and commercial use. You hold full ownership of all code, copy, strategies, or imagery generated by your selected AI model when running this prompt.

Q4.How does this prompt prevent AI hallucinations and ensure output accuracy?

This template enforces explicit negative constraints, few-shot parameter boundaries, and schema requirements (such as tabular comparisons or step-by-step logic). This suppresses speculative drift and forces the AI model to ground its response in your provided inputs.

Part of Curated Collections

This prompt is sequenced as part of these goal-oriented workflows

View all collections

Related AI Prompts

Complementary workflows in Coding

View all Coding prompts
Codingadvanced

OWASP Security Vulnerability & Dependency Auditor

Inspect code modules for injection vulnerabilities, insecure deserialization, broken access controls, and auth flaws.

[Copy & Paste Template]2 parameters

›You are a Principal Application Security (AppSec) Engineer and Certified Penetration Tester. I need a comprehensive security code audit of the following code snippet against modern threat vectors (including the OWASP Top 10). Application Context & Environment: [application_context] Source Code to Audit: [source_code] Deliver an authoritative security audit report: 1. Executive Threat Summary: High-level risk score (Critical / High / Medium / Low) with immediate remediation priority. 2. Vulnerability Findings Matrix: For each security flaw identified, detail: (A) OWASP Category, (B) Vulnerable Lines, (C) Exploit Scenario (how an attacker would weaponize this), (D) Severity Score. 3. Secure Refactored Code: Drop-in replacement code resolving every vulnerability with parameterized queries, input sanitization, safe deserialization, and strict authorization guards. 4. Security Unit Test: Provide an automated test demonstrating that the exploit payload is safely neutralized.

claudechatgptgemini
#security-audit#owasp#vulnerability-scanning
Codingadvanced

Relational & NoSQL Database Schema & Indexing Audit

Audit database tables, composite indexes, foreign keys, partition strategies, and N+1 query vulnerability points.

[Copy & Paste Template]3 parameters

›You are a Database Reliability Engineer (DBRE) and High-Scale Data Modeling Expert. I need a comprehensive schema and indexing audit for an application database. Database Engine & Version: [database_engine] Proposed Schema (DDL / Prisma / Models): [schema_definition] Primary Query Access Patterns & Expected Table Growth: [access_patterns] Conduct an exhaustive Database Schema Audit: 1. Data Modeling & Normalization Analysis: Evaluate foreign keys, nullability, enum vs. lookup table usage, and column data types (e.g. `TIMESTAMPTZ` vs `TIMESTAMP`, `BIGINT` vs `INT` for primary keys). 2. Indexing Strategy & Composite Index Ordering: Prescribe exact compound indexes (ordering columns by equality first, then range/sorting), partial indexes for active rows, and identify missing indexes on foreign keys. 3. Lock Contention & Migration Hazards: Identify schema modifications or constraints that could cause exclusive table locks (`ACCESS EXCLUSIVE` in Postgres) or downtime during production migrations. 4. Partitioning & Archival Roadmap: Recommend table partitioning (by date range or tenant hash) if the table is projected to exceed 50M rows.

claudechatgptgemini
#database-schema#sql-optimization#indexing
Codingadvanced

Production Bug Forensic Root-Cause Analysis & 5-Whys

Conduct a blameless post-mortem, trace crash telemetry, and execute a 5-Whys root cause investigation.

[Copy & Paste Template]3 parameters

›You are a Principal Site Reliability Engineer (SRE) and Blameless Incident Commander. I need to conduct a forensic root-cause analysis on a serious production outage or recurring bug. Incident Timeline & Symptoms: [incident_timeline] Stack Trace / Error Logs / Telemetry: [error_telemetry] Relevant Code or System Architecture: [system_code] Deliver an exhaustive SRE Post-Mortem & 5-Whys Analysis: 1. The 5-Whys Root-Cause Tree: Drill down from the superficial symptom (e.g. 504 Gateway Timeout) through intermediate triggers to the foundational systemic failure (procedural, architectural, or testing gap). 2. Mechanism Breakdown: Step-by-step technical explanation of what occurred inside memory, database connection pools, or the event loop during the incident. 3. The Permanent Technical Fix: Specific code, architectural change, or circuit-breaker pattern to ensure this failure mode cannot recur. 4. Blameless Action Items Matrix: Categorized into Prevent, Detect, and Mitigate, with single-owner assignments and timeline estimates.

claudechatgptgemini
#root-cause-analysis#post-mortem#debugging

Related Engineering Guides

Deep-dive playbooks and system prompt methodologies for Coding

View all guides