CodingArchitectureintermediate

Production Engineering Runbook & Architecture Documentation

Generate actionable on-call runbooks with telemetry thresholds, mitigation steps, and architectural diagrams.

#documentation #runbook #on-call #sre #technical-writing

Compatibility & Specs

Compatible AI Models

ClaudeChatGPTGemini

Last UpdatedOct 3, 2026

Customizable Variables4 parameters

Main Prompt Template4 Variables

131 words • 1096 characters

You are a Staff Technical Writer and SRE Documentation Architect. I need to write an authoritative, on-call Engineering Runbook for a mission-critical service. Service Name & Primary Responsibility: [service_responsibility] Upstream Ingest & Downstream Dependencies: [service_dependencies] Known Critical Alerts (Datadog/PagerDuty): [critical_alerts] Standard Operational Procedures (Restart, Drain, Re-sync): [operational_procedures] Generate a production-ready Engineering Runbook: 1. 1-Minute Service Executive Summary: What the service does, language/runtime, ownership team, Slack channel, and link to Grafana dashboard. 2. Architecture Diagram (Mermaid.js): Clean sequence or component diagram showing request flow and dependency boundaries. 3. Triage & Incident Playbooks: For each critical alert, provide: Symptom & Business Impact, Initial Verification Query/Command, Fast Mitigation Step (<5 minutes to stop bleeding), and Escalation Contact. 4. Verification & Healthcheck Commands: Copy-pasteable terminal commands (curl, kubectl, psql) to verify cluster health after maintenance.

Tip:Variables marked in purple brackets can be tailored below.

Customize Prompt

Fill in the variables below. Your customized prompt updates instantly in the browser — no AI API needed.

Parameters (4)* Indicates required field

Service & Responsibility*[service_responsibility]

What the service is called and what it accomplishes

Dependencies*[service_dependencies]

Upstream callers and downstream databases/services

Critical Alerts*[critical_alerts]

PagerDuty alarms that trigger off-hours calls

Operational Procedures*[operational_procedures]

Known recovery commands and maintenance steps

4 parameters active

Live Customized OutputLive Preview

205 words

You are a Staff Technical Writer and SRE Documentation Architect. I need to write an authoritative, on-call Engineering Runbook for a mission-critical service. Service Name & Primary Responsibility: AuthGuard Service: Go microservice running on Kubernetes handling OAuth2 token validation, API rate-limiting via Redis, and JWT signing for all external API gateways. Upstream Ingest & Downstream Dependencies: Upstream: Cloudflare API Gateway; Downstream: Redis Cluster (Rate Limits), PostgreSQL (User Permissions), AWS KMS (JWT Signing Keys). Known Critical Alerts (Datadog/PagerDuty): 1. `AuthGuardHighLatency`: P99 latency > 250ms for 3 consecutive minutes. 2. `RedisClusterFailover`: AuthGuard unable to reach Redis token bucket cache. Standard Operational Procedures (Restart, Drain, Re-sync): Kubernetes rolling restart, switching Redis replica to primary, and activating local in-memory fallback rate limiting via LaunchDarkly flag. Generate a production-ready Engineering Runbook: 1. 1-Minute Service Executive Summary: What the service does, language/runtime, ownership team, Slack channel, and link to Grafana dashboard. 2. Architecture Diagram (Mermaid.js): Clean sequence or component diagram showing request flow and dependency boundaries. 3. Triage & Incident Playbooks: For each critical alert, provide: Symptom & Business Impact, Initial Verification Query/Command, Fast Mitigation Step (<5 minutes to stop bleeding), and Escalation Contact. 4. Verification & Healthcheck Commands: Copy-pasteable terminal commands (curl, kubectl, psql) to verify cluster health after maintenance.

Launch in:

ChatGPT Claude Gemini

How to Use This Prompt

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

1. Tailor the Parameters

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

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.

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.

Placeholder	Parameter Name	Type	Status	Description & Guidance
[service_responsibility]	Service & Responsibility	text	Required	What the service is called and what it accomplishesDefault: AuthGuard Service: Go microservice running on Kubernetes handling OAuth2 token validation, API rate-limiting via Redis, and JWT signing for all external API gateways.
[service_dependencies]	Dependencies	text	Required	Upstream callers and downstream databases/servicesDefault: Upstream: Cloudflare API Gateway; Downstream: Redis Cluster (Rate Limits), PostgreSQL (User Permissions), AWS KMS (JWT Signing Keys).
[critical_alerts]	Critical Alerts	textarea	Required	PagerDuty alarms that trigger off-hours callsDefault: 1. `AuthGuardHighLatency`: P99 latency > 250ms for 3 consecutive minutes. 2. `RedisClusterFailover`: AuthGuard unable to reach Redis token bucket cache.
[operational_procedures]	Operational Procedures	textarea	Required	Known recovery commands and maintenance stepsDefault: Kubernetes rolling restart, switching Redis replica to primary, and activating local in-memory fallback rate limiting via LaunchDarkly flag.

Example Execution & Benchmark Output

Sample input arguments and the verified AI response demonstrating expected quality and formatting.

Sample VariablesInputs

[service_responsibility]

AuthGuard Service: Go microservice running on Kubernetes handling OAuth2 token validation, API rate-limiting via Redis, and JWT signing for all external API gateways.

[service_dependencies]

Upstream: Cloudflare API Gateway; Downstream: Redis Cluster (Rate Limits), PostgreSQL (User Permissions), AWS KMS (JWT Signing Keys).

[critical_alerts]

1. `AuthGuardHighLatency`: P99 latency > 250ms for 3 consecutive minutes. 2. `RedisClusterFailover`: AuthGuard unable to reach Redis token bucket cache.

[operational_procedures]

Kubernetes rolling restart, switching Redis replica to primary, and activating local in-memory fallback rate limiting via LaunchDarkly flag.

Expected AI ResponseVerified Result

### On-Call Runbook: AuthGuard Microservice **Service:** `auth-guard` | **Tier:** 1 (Mission Critical) **Team:** Core Security Pod (`#sec-eng-alerts` on Slack) **Dashboard:** `grafana.internal.net/d/authguard-core` ```mermaid graph LR CF[Cloudflare Gateway] --> AG[AuthGuard Go Service] AG --> RC[(Redis Cache - Rate Limits)] AG --> PG[(Postgres - Permissions)] AG --> KMS[AWS KMS - JWT Key] ``` #### Playbook 1: `AuthGuardHighLatency` (P99 > 250ms) - **Business Impact:** External API requests time out; mobile and web logins stall. - **Triage (1st Action):** Check if latency is localized to Redis connection pool: ```bash kubectl logs -n prod -l app=authguard --tail=100 | grep -i 'redis timeout' ``` - **Mitigation (<3 mins):** Enable in-memory local token bucket fallback to bypass Redis network hop: - Navigate to LaunchDarkly -> Flag `authguard-local-ratelimit-fallback` -> Toggle `ON`. - **Verification:** Monitor Grafana p99 panel; latency should drop below 40ms within 60 seconds. #### Playbook 2: Service Restart ```bash kubectl rollout restart deployment/authguard-prod -n prod kubectl rollout status deployment/authguard-prod -n prod --timeout=120s ```

Best Use Cases

Scenarios and roles where this prompt produces maximum leverage.

Engineering teams formalizing on-call runbooks before handing services to rotation

SRE teams standardizing incident playbooks across microservices

Tech leads documenting disaster recovery procedures and failover commands

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.

Part of Curated Collections

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

View all collections

Coding & Engineering

10 Prompts

AI Prompts for Software Developers

A systematic engineering toolkit covering technical design, edge-case testing, rigorous code review, and root-cause debugging.

#Architecture#Code Review+4

Explore Collection

Related AI Prompts

Complementary workflows in Coding

View all Coding prompts

Codingintermediate

Legacy Codebase Refactoring & Technical Debt Reducer

Systematically deconstruct tightly coupled spaghetti code into isolated, testable pure functions without breaking behavior.

claudechatgptgemini

#refactoring#technical-debt#code-smells

View Prompt

Codingadvanced

Architectural Decision Record (ADR) Analysis & Trade-Off Matrix

Evaluate competing technical architectures, state assumptions, and document a formal Architectural Decision Record.

claudechatgptgemini

#system-architecture#adr#trade-offs

View Prompt

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.

claudechatgptgemini

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

View Prompt

Related Engineering Guides

Deep-dive playbooks and system prompt methodologies for Coding

View all guides

Prompt Engineering#promptarchitecture

8 min read

How to Write Better AI Prompts

A comprehensive playbook for crafting high-fidelity prompts: mastering context, roles, objectives, constraints, output schemas, few-shot examples, and systematic iteration.

Mar 25, 2026Read Guide

Software Engineering#engineering

9 min read

AI Prompts for Software Developers

Turn modern LLMs into senior engineering peers: tactical prompt patterns for architecture review, edge-case test generation, root-cause debugging, and technical documentation.

Mar 27, 2026Read Guide