Skip to main content
CodingArchitectureadvancedFeatured

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

Optimized for Claude, Chatgpt, Gemini • Verified Prompt Template

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

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_requirements]System RequirementstextareaRequiredWhat the system or feature needs to do functionallyDefault: A multi-tenant background notification and webhook delivery pipeline that processes up to 25 million events per day with at-least-once delivery, exponential backoff retries, and customer-configured secret signing.
[non_functional_constraints]Non-Functional ConstraintstextRequiredScale, SLA, team bandwidth, infrastructure budgetDefault: P99 delivery under 3 seconds; 5-person engineering team with minimal dedicated DevOps support; budget capped at $2,500/month AWS compute spend.
[options_considered]Options ConsideredtextareaRequiredThe specific architectural alternatives being evaluatedDefault: Option A: Fully serverless AWS SQS + EventBridge + Lambda workers. Option B: Self-managed Redis Streams with autoscaling Go workers on AWS ECS. Option C: Managed Apache Kafka (Amazon MSK) with dedicated consumer services.

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_requirements]
A multi-tenant background notification and webhook delivery pipeline that processes up to 25 million events per day with at-least-once delivery, exponential backoff retries, and customer-configured secret signing.
[non_functional_constraints]
P99 delivery under 3 seconds; 5-person engineering team with minimal dedicated DevOps support; budget capped at $2,500/month AWS compute spend.
[options_considered]
Option A: Fully serverless AWS SQS + EventBridge + Lambda workers. Option B: Self-managed Redis Streams with autoscaling Go workers on AWS ECS. Option C: Managed Apache Kafka (Amazon MSK) with dedicated consumer services.

Verified AI Benchmark Response

Grounded Output
### Architectural Decision Record (ADR): Webhook Delivery Pipeline **Status:** Accepted **Date:** 2026-10-03 **Decision Makers:** Principal Architect, Backend Lead, DevOps Engineer #### 1. Context & Problem Statement We must deliver 25 million multi-tenant webhooks daily. Customer endpoints have unpredictable latency and high failure rates. We need durable queuing, retry backoff, and isolation so one slow recipient endpoint cannot exhaust workers and delay delivery for other tenants. #### 2. Trade-Off Evaluation Matrix - **Option A (AWS SQS + Lambda):** Operational complexity: Very Low | Cost at 25M calls: ~$3,200/mo (exceeds budget due to Lambda duration waiting on slow HTTP responses) | Isolation: High. - **Option B (Redis Streams + Go on ECS) [CHOSEN]:** Operational complexity: Low-to-Moderate | Cost: ~$850/mo (3 lightweight ECS Fargate tasks using non-blocking epoll Go HTTP clients) | Isolation: Moderate. - **Option C (Kafka / MSK):** Operational complexity: Very High | Minimum cluster cost: ~$2,000/mo | Overkill for a 5-person team without dedicated SRE. #### 3. Decision We choose **Option B (Redis Streams with Go workers on ECS)**. Go's lightweight goroutines allow each worker container to hold 10,000 concurrent outbound HTTP requests without memory exhaustion, keeping compute costs 70% below Lambda. #### 4. Consequences & Mitigations - *Negative:* Redis is in-memory; sudden cluster crash could lose un-persisted stream segments. - *Mitigation:* Configure Redis AOF with `appendfsync everysec` and multi-AZ replication. DLQ events overflow to S3 bucket.

Best Use Cases

Scenarios and roles where this prompt produces maximum leverage.

Staff and Principal engineers authoring RFCs and architecture decision documents
Engineering leads evaluating cloud infrastructure costs against team operational capacity
Distributed development teams documenting technical trade-offs for permanent record

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 "Architectural Decision Record (ADR) Analysis & Trade-Off Matrix" 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_requirements], [non_functional_constraints], [options_considered]. 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

Production Incident Post-Mortem & Root-Cause Synthesizer

Convert messy incident Slack logs and alerts into a blameless, rigorous post-mortem with corrective action items.

[Copy & Paste Template]3 parameters

›You are a Principal Site Reliability Engineer (SRE) and Incident Commander. I need to author an authoritative, blameless Production Incident Post-Mortem based on raw incident timeline notes. Incident Overview & Context: - Service Affected & Severity: [incident_severity] - Total Customer Downtime / Impact Duration: [downtime_duration] - Raw Incident Timeline & Slack Notes: [raw_incident_notes] Deliver the standard SRE Blameless Post-Mortem Report: 1. Executive Summary: High-level non-technical summary of what occurred, total business impact, and key preventative takeaways. 2. Detailed Incident Timeline (UTC): Synthesize raw notes into a standardized chronological sequence (T0 Detection, T+X Mitigation, T+Y Resolution). 3. Root Cause Analysis (5 Whys): Conduct a deep technical 5 Whys deconstruction distinguishing proximate triggers from systemic architecture/process flaws. 4. What Went Well vs. Where We Got Lucky vs. Where We Struggled: Objective assessment of observability, alerts, and runbooks. 5. Corrective Action Items (P0 to P2): Actionable engineering tasks with concrete definitions of done to mechanically prevent recurrence.

claudechatgptgemini
#post-mortem#root-cause-analysis#sre
Codingadvanced

Monolith to Modular Decoupling & Boundary Architect

Carve clear bounded contexts out of entangled monoliths using the Strangler Fig pattern and event-driven seams.

[Copy & Paste Template]4 parameters

›You are a Principal Software Architect and Distributed Systems Strategist. I need to decouple a critical domain out of an entangled monolith without causing downtime or disrupting ongoing product feature velocity. Existing Monolith Stack & Database: [monolith_stack] Target Domain to Extract: [domain_to_extract] Known Entanglements & Shared Dependencies: [shared_entanglements] Target Architecture: [target_architecture] Deliver a step-by-step Modular Decoupling Blueprint: 1. Bounded Context & Interface Seams: Define the strict input/output API contract and domain events (`OrderCreated`, `InventoryReserved`) for the extracted module. 2. Database Decoupling & Dual-Write Migration Strategy: Exact 4-phase database transition protocol (Dual-write -> Backfill -> Read from new -> Deprecate old) avoiding distributed transactions (2PC). 3. Strangler Fig Routing Architecture: How API gateway / reverse proxy rules will incrementally route 1% -> 10% -> 100% of traffic to the new service. 4. Failure Modes & Rollback Safety: What to do if the extracted service fails or introduces cross-service latency degradation.

claudechatgptgemini
#software-architecture#refactoring#monolith-to-microservices
Next.jsadvanced

Next.js Server vs. Client Component Boundary Decision Matrix

Audit page trees to push 'use client' directives to the leaves, minimize JS bundles, and maximize server streaming.

[Copy & Paste Template]3 parameters

›You are a Principal Next.js Framework Architect and React 19 Core Specialist. I am designing or refactoring a page in the Next.js App Router, and I need an authoritative audit of my Server vs. Client Component boundaries. Next.js Version: [nextjs_version] Page Description & User Interactions: [page_description] Data Sources & Sensitive Tokens: [data_sources] Deliver the Server/Client Boundary Blueprint: 1. Component Boundary Hierarchy Tree: Visual ASCII tree mapping out which components must be Server Components (RSC) vs. which must be Client Components (`'use client'`). 2. 'Push to the Leaves' Strategy: How to refactor interactive widgets (e.g. search input, favorite button, modal toggle) into tiny leaf client components while keeping heavy data fetching on the server. 3. Composition via Children Pattern: Code example demonstrating how to pass Server Components as `children` into Client Component wrappers without turning the children into client bundles. 4. Bundle Size & Security Audit: Verify that database credentials, secret API keys, and heavy server libraries (like Prisma or markdown parsers) are physically excluded from client JavaScript bundles.

claudechatgptgemini
#nextjs#server-components#client-components

Related Engineering Guides

Deep-dive playbooks and system prompt methodologies for Coding

View all guides