# Awesome Checklists

> A living reference library of practical review checklists for software and AI products. Use the checklists to identify gaps, verify work, and support evidence-based decisions.

Website: https://awesome-checklists.pages.dev/
Source: https://github.com/Pro-GenAI/awesome-checklists

## Important limitations

This collection is a reference, not the definitive or exhaustive source of truth. It does not confer certification or guarantee security, reliability, compliance, accessibility, AI safety, or launch readiness. Select applicable checks based on project context, risk, and jurisdiction; verify important facts against current primary sources. Suggestions, corrections, and contributions are encouraged.

## Start here

- [Overview and how to use](https://awesome-checklists.pages.dev/): Purpose, workflow, important warnings, and contribution guidance.
- [Contributor and AI-agent guide](https://awesome-checklists.pages.dev/AGENTS.html): Scope ownership, stable checklist IDs, and repository maintenance conventions.

## Shared checklists

- [01 — Requirements and Planning Checklist](https://awesome-checklists.pages.dev/01_Requirements_and_Planning.html): Verify that the project solves a validated problem, has measurable goals, clear scope, testable requirements, realistic delivery plans, and defined API/frontend requirements.
- [02 — Legal Issues Checklist](https://awesome-checklists.pages.dev/02_LegalIssues.html): Identify legal, licensing, contractual, privacy, and regulatory questions early. This is an issue-spotting tool, not legal advice or a certification of compliance.
- [03 — Architecture and Code Quality Checklist](https://awesome-checklists.pages.dev/03_Architecture_and_CodeQuality.html): Review design trade-offs, system boundaries, maintainable code, engineering reviews, decision records, and API/frontend architecture. This checklist evaluates structure and evolvability; it 
- [04 — Internationalization and Localization Checklist](https://awesome-checklists.pages.dev/04_Internationalization_and_Localization.html): Verify that supported languages, writing systems, locales, and markets have functional and comprehensible end-to-end experiences. Internationalization makes a system adaptable; localization 
- [05 — Security Checklist](https://awesome-checklists.pages.dev/05_Security.html): Assess confidentiality, integrity, availability, abuse resistance, and operational security proportionate to project risk.
- [06 — Cost and FinOps Checklist](https://awesome-checklists.pages.dev/06_Cost_and_FinOps.html): Verify that technology spending is attributable, visible, forecastable, and optimized for business value without compromising required quality, reliability, security, or user outcomes. FinOp
- [07 — Documentation and Developer Experience Checklist](https://awesome-checklists.pages.dev/07_Documentation_and_DeveloperExperience.html): Verify that developers and operators can find accurate information, reproduce their local environment, understand API and system behavior, make changes safely, and maintain the product witho
- [08 — Testing Checklist](https://awesome-checklists.pages.dev/08_Testing.html): Verify expected functionality, quality, reliability, and release readiness using reproducible evidence.
- [09 — Performance and Scalability Checklist](https://awesome-checklists.pages.dev/09_Performance_and_Scalability.html): Verify that priority user experiences and services meet documented latency, throughput, capacity, and efficiency objectives at realistic demand. Separate browser metrics from backend metrics
- [10 — Reliability and Disaster Recovery Checklist](https://awesome-checklists.pages.dev/10_Reliability_and_DisasterRecovery.html): Verify that critical user journeys remain usable under expected failures and can recover within agreed downtime and data-loss targets. Reliability, backup/restore, disaster recovery, and bus
- [11 — DevOps and CI/CD Checklist](https://awesome-checklists.pages.dev/11_DevOps_and_CI_CD.html): Verify repeatable builds, trusted deployment artifacts, controlled infrastructure changes, safe rollout and rollback, and accountable software delivery. This checklist focuses on delivery sy
- [12 — Monitoring and Observability Checklist](https://awesome-checklists.pages.dev/12_Monitoring_and_Observability.html): Verify that critical services and user journeys can be understood through trustworthy telemetry, actionable alerts, service-level measurements, and effective incident investigation. Monitori
- [13 — Analytics and Product Metrics Checklist](https://awesome-checklists.pages.dev/13_Analytics_and_ProductMetrics.html): Verify that product metrics answer meaningful decisions and are built on well-defined events, trustworthy data, privacy-aware collection, and sound experimentation. This template does not ce
- [14 — GEO and AEO Checklist](https://awesome-checklists.pages.dev/14_GEO_and_AEO.html): Improve how clearly and reliably a project can be understood, sourced, and answered by search answer systems and generative AI. GEO = Generative Engine Optimization; AEO = Answer Engine Opti
- [15 — Release and Launch Readiness Checklist](https://awesome-checklists.pages.dev/15_Release_and_LaunchReadiness.html): Verify that a new product, service, or significant change is ready for controlled customer exposure, has an explicit go/no-go decision, and can be operated and supported safely after launch.

## Frontend checklists

- [01 — Requirements and Planning Checklist](https://awesome-checklists.pages.dev/frontend/01_Requirements_and_Planning.html): Verify that the project solves a validated problem, has measurable goals, clear scope, testable requirements, realistic delivery plans, and defined API/frontend requirements.
- [02 — Legal Issues Checklist](https://awesome-checklists.pages.dev/frontend/02_LegalIssues.html): Identify legal, licensing, contractual, privacy, and regulatory questions early. This is an issue-spotting tool, not legal advice or a certification of compliance.
- [03 — Architecture and Code Quality Checklist](https://awesome-checklists.pages.dev/frontend/03_Architecture_and_CodeQuality.html): Review design trade-offs, system boundaries, maintainable code, engineering reviews, decision records, and API/frontend architecture. This checklist evaluates structure and evolvability; it 
- [04 — UI, UX, and Usability Checklist](https://awesome-checklists.pages.dev/frontend/04_UI_UX_and_Usability.html): Review whether the product helps people complete meaningful tasks with understandable navigation, predictable interactions, inclusive experiences, and evidence-based improvements. This focus
- [05 — Accessibility Checklist](https://awesome-checklists.pages.dev/frontend/05_Accessibility.html): Verify that essential product experiences are perceivable, operable, understandable, and robust for people using a range of input methods and assistive technologies. The intended standard an
- [06 — Internationalization and Localization Checklist](https://awesome-checklists.pages.dev/frontend/06_Internationalization_and_Localization.html): Verify that supported languages, writing systems, locales, and markets have functional and comprehensible end-to-end experiences. Internationalization makes a system adaptable; localization 
- [07 — API Design and Integrations Checklist](https://awesome-checklists.pages.dev/frontend/07_API_Design_and_Integrations.html): Verify that service interfaces have understandable contracts, predictable behavior, secure integration boundaries, maintained consumer compatibility, and workable fallback procedures. This c
- [08 — Data and Database Management Checklist](https://awesome-checklists.pages.dev/frontend/08_Data_and_DatabaseManagement.html): Review data ownership, schema design, migration safety, transactional correctness, data quality, and lifecycle management. This checklist covers the integrity and governance of information t
- [09 — Security Checklist](https://awesome-checklists.pages.dev/frontend/09_Security.html): Assess confidentiality, integrity, availability, abuse resistance, and operational security proportionate to project risk.
- [10 — AI Evaluation and Governance Checklist](https://awesome-checklists.pages.dev/frontend/10_AI_Evaluation_and_Governance.html): Review whether a proposed AI use is appropriate, its risks are understood, the system has credible evaluation evidence, human oversight is operational, and organizational accountability is m
- [11 — AI Model Selection and Benchmarking Checklist](https://awesome-checklists.pages.dev/frontend/11_AI_Model_Selection_and_Benchmarking.html): Choose AI models against the actual application workload, operating constraints, safety requirements, and measurable outcomes. Public leaderboards help identify candidates but do not prove s
- [12 — AI Data Curation and Labeling Checklist](https://awesome-checklists.pages.dev/frontend/12_AI_Data_Curation_and_Labeling.html): Verify that datasets used for AI training, tuning, evaluation, or retrieval are lawfully and responsibly sourced, technically consistent, properly labeled, traceable to origin, and separated
- [13 — AI Model and Dataset Cards Checklist](https://awesome-checklists.pages.dev/frontend/13_AI_Model_and_Dataset_Cards.html): Verify that model and dataset documentation accurately communicates intended use, capabilities, limitations, provenance, evaluation evidence, risks, and change history. A card is a living di
- [14 — AI Fine-tuning and Training Checklist](https://awesome-checklists.pages.dev/frontend/14_AI_FineTuning_and_Training.html): Verify that training or fine-tuning a model is justified, reproducible, permissioned, numerically stable, evaluated for unintended behavioral changes, and released under explicit control. Lo
- [15 — Prompt Engineering and Versioning Checklist](https://awesome-checklists.pages.dev/frontend/15_Prompt_Engineering_and_Versioning.html): Review instructions, templates, prompt revisions, and evaluation gates used in model-integrated software. Treat prompt wording as a behavioral control and engineering artifact, not a guarant
- [16 — RAG and Knowledge Bases Checklist](https://awesome-checklists.pages.dev/frontend/16_RAG_and_Knowledge_Bases.html): Verify that retrieval-augmented generation (RAG) uses authorized, attributable, sufficiently fresh evidence; retrieves relevant passages; and produces answers whose factual claims can be che
- [17 — AI Agents and Tool Orchestration Checklist](https://awesome-checklists.pages.dev/frontend/17_AI_Agents_and_Tool_Orchestration.html): Verify that AI agents achieve bounded tasks through permitted tools, safe handoffs, controlled state, and meaningful human supervision. The model may propose plans and actions, but independe
- [18 — AI Inference and Serving Checklist](https://awesome-checklists.pages.dev/frontend/18_AI_Inference_and_Serving.html): Verify that production AI inference is deployable, secure, performant, cost-bounded, and recoverable under realistic workloads. Serving improvements must be measured against user-visible qua
- [19 — Multimodal AI Quality Checklist](https://awesome-checklists.pages.dev/frontend/19_Multimodal_AI_Quality.html): Verify that AI features using images, audio, speech, video, documents, or combinations of modalities produce fit-for-purpose, safe, accessible, and properly grounded results. An AI model's c
- [20 — AI Human Review and Escalation Checklist](https://awesome-checklists.pages.dev/frontend/20_AI_Human_Review_and_Escalation.html): Ensure human involvement in AI-assisted decisions is meaningful, authorized, timely, and auditable. A review button, nominal human sign-off, or the ability to view model output does not esta
- [21 — AI Evaluation and Regression Checklist](https://awesome-checklists.pages.dev/frontend/21_AI_Evaluation_and_Regression.html): Verify that AI-enabled applications have representative, measurable, repeatable evaluation of task quality and safety, and that changes are held to defined regression and release standards. 
- [22 — AI Red Teaming and Guardrails Checklist](https://awesome-checklists.pages.dev/frontend/22_AI_Red_Teaming_and_Guardrails.html): Verify that AI-enabled products have risk-based adversarial coverage and enforceable defenses against harmful outputs, unauthorized actions, data disclosure, and abuse. Red teaming seeks to 
- [23 — MLOps and Model Lifecycle Checklist](https://awesome-checklists.pages.dev/frontend/23_MLOps_and_Model_Lifecycle.html): Verify that AI/ML experiments, data, models, approvals, deployment configurations, and retirement decisions are traceable and managed across the system lifecycle. Registry entries and passin
- [24 — AI Monitoring and Drift Checklist](https://awesome-checklists.pages.dev/frontend/24_AI_Monitoring_and_Drift.html): Verify that production AI systems are observable, that distribution changes are separated from demonstrated model-quality regressions, and that emerging user harm or operational failures tri
- [25 — Documentation and Developer Experience Checklist](https://awesome-checklists.pages.dev/frontend/25_Documentation_and_DeveloperExperience.html): Verify that developers and operators can find accurate information, reproduce their local environment, understand API and system behavior, make changes safely, and maintain the product witho
- [26 — Testing Checklist](https://awesome-checklists.pages.dev/frontend/26_Testing.html): Verify expected functionality, quality, reliability, and release readiness using reproducible evidence.
- [27 — Performance and Scalability Checklist](https://awesome-checklists.pages.dev/frontend/27_Performance_and_Scalability.html): Verify that priority user experiences and services meet documented latency, throughput, capacity, and efficiency objectives at realistic demand. Separate browser metrics from backend metrics
- [28 — SEO Checklist](https://awesome-checklists.pages.dev/frontend/28_SEO.html): Check discoverability, crawl/index controls, content quality, usability, and measurement for sites meant to appear in search results.
- [29 — GEO and AEO Checklist](https://awesome-checklists.pages.dev/frontend/29_GEO_and_AEO.html): Improve how clearly and reliably a project can be understood, sourced, and answered by search answer systems and generative AI. GEO = Generative Engine Optimization; AEO = Answer Engine Opti
- [30 — DevOps and CI/CD Checklist](https://awesome-checklists.pages.dev/frontend/30_DevOps_and_CI_CD.html): Verify repeatable builds, trusted deployment artifacts, controlled infrastructure changes, safe rollout and rollback, and accountable software delivery. This checklist focuses on delivery sy
- [31 — Reliability and Disaster Recovery Checklist](https://awesome-checklists.pages.dev/frontend/31_Reliability_and_DisasterRecovery.html): Verify that critical user journeys remain usable under expected failures and can recover within agreed downtime and data-loss targets. Reliability, backup/restore, disaster recovery, and bus
- [32 — Monitoring and Observability Checklist](https://awesome-checklists.pages.dev/frontend/32_Monitoring_and_Observability.html): Verify that critical services and user journeys can be understood through trustworthy telemetry, actionable alerts, service-level measurements, and effective incident investigation. Monitori
- [33 — Analytics and Product Metrics Checklist](https://awesome-checklists.pages.dev/frontend/33_Analytics_and_ProductMetrics.html): Verify that product metrics answer meaningful decisions and are built on well-defined events, trustworthy data, privacy-aware collection, and sound experimentation. This template does not ce
- [34 — Cost and FinOps Checklist](https://awesome-checklists.pages.dev/frontend/34_Cost_and_FinOps.html): Verify that technology spending is attributable, visible, forecastable, and optimized for business value without compromising required quality, reliability, security, or user outcomes. FinOp
- [35 — Release and Launch Readiness Checklist](https://awesome-checklists.pages.dev/frontend/35_Release_and_LaunchReadiness.html): Verify that a new product, service, or significant change is ready for controlled customer exposure, has an explicit go/no-go decision, and can be operated and supported safely after launch.

## Backend checklists

- [01 — Requirements and Planning Checklist](https://awesome-checklists.pages.dev/backend/01_Requirements_and_Planning.html): Verify that the project solves a validated problem, has measurable goals, clear scope, testable requirements, realistic delivery plans, and defined API/frontend requirements.
- [02 — Legal Issues Checklist](https://awesome-checklists.pages.dev/backend/02_LegalIssues.html): Identify legal, licensing, contractual, privacy, and regulatory questions early. This is an issue-spotting tool, not legal advice or a certification of compliance.
- [03 — Architecture and Code Quality Checklist](https://awesome-checklists.pages.dev/backend/03_Architecture_and_CodeQuality.html): Review design trade-offs, system boundaries, maintainable code, engineering reviews, decision records, and API/frontend architecture. This checklist evaluates structure and evolvability; it 
- [04 — UI, UX, and Usability Checklist](https://awesome-checklists.pages.dev/backend/04_UI_UX_and_Usability.html): Review whether the product helps people complete meaningful tasks with understandable navigation, predictable interactions, inclusive experiences, and evidence-based improvements. This focus
- [05 — Accessibility Checklist](https://awesome-checklists.pages.dev/backend/05_Accessibility.html): Verify that essential product experiences are perceivable, operable, understandable, and robust for people using a range of input methods and assistive technologies. The intended standard an
- [06 — Internationalization and Localization Checklist](https://awesome-checklists.pages.dev/backend/06_Internationalization_and_Localization.html): Verify that supported languages, writing systems, locales, and markets have functional and comprehensible end-to-end experiences. Internationalization makes a system adaptable; localization 
- [07 — API Design and Integrations Checklist](https://awesome-checklists.pages.dev/backend/07_API_Design_and_Integrations.html): Verify that service interfaces have understandable contracts, predictable behavior, secure integration boundaries, maintained consumer compatibility, and workable fallback procedures. This c
- [08 — Data and Database Management Checklist](https://awesome-checklists.pages.dev/backend/08_Data_and_DatabaseManagement.html): Review data ownership, schema design, migration safety, transactional correctness, data quality, and lifecycle management. This checklist covers the integrity and governance of information t
- [09 — Security Checklist](https://awesome-checklists.pages.dev/backend/09_Security.html): Assess confidentiality, integrity, availability, abuse resistance, and operational security proportionate to project risk.
- [10 — AI Evaluation and Governance Checklist](https://awesome-checklists.pages.dev/backend/10_AI_Evaluation_and_Governance.html): Review whether a proposed AI use is appropriate, its risks are understood, the system has credible evaluation evidence, human oversight is operational, and organizational accountability is m
- [11 — AI Model Selection and Benchmarking Checklist](https://awesome-checklists.pages.dev/backend/11_AI_Model_Selection_and_Benchmarking.html): Choose AI models against the actual application workload, operating constraints, safety requirements, and measurable outcomes. Public leaderboards help identify candidates but do not prove s
- [12 — AI Data Curation and Labeling Checklist](https://awesome-checklists.pages.dev/backend/12_AI_Data_Curation_and_Labeling.html): Verify that datasets used for AI training, tuning, evaluation, or retrieval are lawfully and responsibly sourced, technically consistent, properly labeled, traceable to origin, and separated
- [13 — AI Model and Dataset Cards Checklist](https://awesome-checklists.pages.dev/backend/13_AI_Model_and_Dataset_Cards.html): Verify that model and dataset documentation accurately communicates intended use, capabilities, limitations, provenance, evaluation evidence, risks, and change history. A card is a living di
- [14 — AI Fine-tuning and Training Checklist](https://awesome-checklists.pages.dev/backend/14_AI_FineTuning_and_Training.html): Verify that training or fine-tuning a model is justified, reproducible, permissioned, numerically stable, evaluated for unintended behavioral changes, and released under explicit control. Lo
- [15 — Prompt Engineering and Versioning Checklist](https://awesome-checklists.pages.dev/backend/15_Prompt_Engineering_and_Versioning.html): Review instructions, templates, prompt revisions, and evaluation gates used in model-integrated software. Treat prompt wording as a behavioral control and engineering artifact, not a guarant
- [16 — RAG and Knowledge Bases Checklist](https://awesome-checklists.pages.dev/backend/16_RAG_and_Knowledge_Bases.html): Verify that retrieval-augmented generation (RAG) uses authorized, attributable, sufficiently fresh evidence; retrieves relevant passages; and produces answers whose factual claims can be che
- [17 — AI Agents and Tool Orchestration Checklist](https://awesome-checklists.pages.dev/backend/17_AI_Agents_and_Tool_Orchestration.html): Verify that AI agents achieve bounded tasks through permitted tools, safe handoffs, controlled state, and meaningful human supervision. The model may propose plans and actions, but independe
- [18 — AI Inference and Serving Checklist](https://awesome-checklists.pages.dev/backend/18_AI_Inference_and_Serving.html): Verify that production AI inference is deployable, secure, performant, cost-bounded, and recoverable under realistic workloads. Serving improvements must be measured against user-visible qua
- [19 — Multimodal AI Quality Checklist](https://awesome-checklists.pages.dev/backend/19_Multimodal_AI_Quality.html): Verify that AI features using images, audio, speech, video, documents, or combinations of modalities produce fit-for-purpose, safe, accessible, and properly grounded results. An AI model's c
- [20 — AI Human Review and Escalation Checklist](https://awesome-checklists.pages.dev/backend/20_AI_Human_Review_and_Escalation.html): Ensure human involvement in AI-assisted decisions is meaningful, authorized, timely, and auditable. A review button, nominal human sign-off, or the ability to view model output does not esta
- [21 — AI Evaluation and Regression Checklist](https://awesome-checklists.pages.dev/backend/21_AI_Evaluation_and_Regression.html): Verify that AI-enabled applications have representative, measurable, repeatable evaluation of task quality and safety, and that changes are held to defined regression and release standards. 
- [22 — AI Red Teaming and Guardrails Checklist](https://awesome-checklists.pages.dev/backend/22_AI_Red_Teaming_and_Guardrails.html): Verify that AI-enabled products have risk-based adversarial coverage and enforceable defenses against harmful outputs, unauthorized actions, data disclosure, and abuse. Red teaming seeks to 
- [23 — MLOps and Model Lifecycle Checklist](https://awesome-checklists.pages.dev/backend/23_MLOps_and_Model_Lifecycle.html): Verify that AI/ML experiments, data, models, approvals, deployment configurations, and retirement decisions are traceable and managed across the system lifecycle. Registry entries and passin
- [24 — AI Monitoring and Drift Checklist](https://awesome-checklists.pages.dev/backend/24_AI_Monitoring_and_Drift.html): Verify that production AI systems are observable, that distribution changes are separated from demonstrated model-quality regressions, and that emerging user harm or operational failures tri
- [25 — Documentation and Developer Experience Checklist](https://awesome-checklists.pages.dev/backend/25_Documentation_and_DeveloperExperience.html): Verify that developers and operators can find accurate information, reproduce their local environment, understand API and system behavior, make changes safely, and maintain the product witho
- [26 — Testing Checklist](https://awesome-checklists.pages.dev/backend/26_Testing.html): Verify expected functionality, quality, reliability, and release readiness using reproducible evidence.
- [27 — Performance and Scalability Checklist](https://awesome-checklists.pages.dev/backend/27_Performance_and_Scalability.html): Verify that priority user experiences and services meet documented latency, throughput, capacity, and efficiency objectives at realistic demand. Separate browser metrics from backend metrics
- [28 — SEO Checklist](https://awesome-checklists.pages.dev/backend/28_SEO.html): Check discoverability, crawl/index controls, content quality, usability, and measurement for sites meant to appear in search results.
- [29 — GEO and AEO Checklist](https://awesome-checklists.pages.dev/backend/29_GEO_and_AEO.html): Improve how clearly and reliably a project can be understood, sourced, and answered by search answer systems and generative AI. GEO = Generative Engine Optimization; AEO = Answer Engine Opti
- [30 — DevOps and CI/CD Checklist](https://awesome-checklists.pages.dev/backend/30_DevOps_and_CI_CD.html): Verify repeatable builds, trusted deployment artifacts, controlled infrastructure changes, safe rollout and rollback, and accountable software delivery. This checklist focuses on delivery sy
- [31 — Reliability and Disaster Recovery Checklist](https://awesome-checklists.pages.dev/backend/31_Reliability_and_DisasterRecovery.html): Verify that critical user journeys remain usable under expected failures and can recover within agreed downtime and data-loss targets. Reliability, backup/restore, disaster recovery, and bus
- [32 — Monitoring and Observability Checklist](https://awesome-checklists.pages.dev/backend/32_Monitoring_and_Observability.html): Verify that critical services and user journeys can be understood through trustworthy telemetry, actionable alerts, service-level measurements, and effective incident investigation. Monitori
- [33 — Analytics and Product Metrics Checklist](https://awesome-checklists.pages.dev/backend/33_Analytics_and_ProductMetrics.html): Verify that product metrics answer meaningful decisions and are built on well-defined events, trustworthy data, privacy-aware collection, and sound experimentation. This template does not ce
- [34 — Cost and FinOps Checklist](https://awesome-checklists.pages.dev/backend/34_Cost_and_FinOps.html): Verify that technology spending is attributable, visible, forecastable, and optimized for business value without compromising required quality, reliability, security, or user outcomes. FinOp
- [35 — Release and Launch Readiness Checklist](https://awesome-checklists.pages.dev/backend/35_Release_and_LaunchReadiness.html): Verify that a new product, service, or significant change is ready for controlled customer exposure, has an explicit go/no-go decision, and can be operated and supported safely after launch.

## AI checklists

- [01 — Requirements and Planning Checklist](https://awesome-checklists.pages.dev/AI/01_Requirements_and_Planning.html): Verify that the project solves a validated problem, has measurable goals, clear scope, testable requirements, realistic delivery plans, and defined API/frontend requirements.
- [02 — Legal Issues Checklist](https://awesome-checklists.pages.dev/AI/02_LegalIssues.html): Identify legal, licensing, contractual, privacy, and regulatory questions early. This is an issue-spotting tool, not legal advice or a certification of compliance.
- [03 — AI Evaluation and Governance Checklist](https://awesome-checklists.pages.dev/AI/03_AI_Evaluation_and_Governance.html): Review whether a proposed AI use is appropriate, its risks are understood, the system has credible evaluation evidence, human oversight is operational, and organizational accountability is m
- [04 — Security Checklist](https://awesome-checklists.pages.dev/AI/04_Security.html): Assess confidentiality, integrity, availability, abuse resistance, and operational security proportionate to project risk.
- [05 — AI Model Selection and Benchmarking Checklist](https://awesome-checklists.pages.dev/AI/05_AI_Model_Selection_and_Benchmarking.html): Choose AI models against the actual application workload, operating constraints, safety requirements, and measurable outcomes. Public leaderboards help identify candidates but do not prove s
- [06 — AI Data Curation and Labeling Checklist](https://awesome-checklists.pages.dev/AI/06_AI_Data_Curation_and_Labeling.html): Verify that datasets used for AI training, tuning, evaluation, or retrieval are lawfully and responsibly sourced, technically consistent, properly labeled, traceable to origin, and separated
- [07 — AI Model and Dataset Cards Checklist](https://awesome-checklists.pages.dev/AI/07_AI_Model_and_Dataset_Cards.html): Verify that model and dataset documentation accurately communicates intended use, capabilities, limitations, provenance, evaluation evidence, risks, and change history. A card is a living di
- [08 — AI Fine-tuning and Training Checklist](https://awesome-checklists.pages.dev/AI/08_AI_FineTuning_and_Training.html): Verify that training or fine-tuning a model is justified, reproducible, permissioned, numerically stable, evaluated for unintended behavioral changes, and released under explicit control. Lo
- [09 — Prompt Engineering and Versioning Checklist](https://awesome-checklists.pages.dev/AI/09_Prompt_Engineering_and_Versioning.html): Review instructions, templates, prompt revisions, and evaluation gates used in model-integrated software. Treat prompt wording as a behavioral control and engineering artifact, not a guarant
- [10 — RAG and Knowledge Bases Checklist](https://awesome-checklists.pages.dev/AI/10_RAG_and_Knowledge_Bases.html): Verify that retrieval-augmented generation (RAG) uses authorized, attributable, sufficiently fresh evidence; retrieves relevant passages; and produces answers whose factual claims can be che
- [11 — AI Agents and Tool Orchestration Checklist](https://awesome-checklists.pages.dev/AI/11_AI_Agents_and_Tool_Orchestration.html): Verify that AI agents achieve bounded tasks through permitted tools, safe handoffs, controlled state, and meaningful human supervision. The model may propose plans and actions, but independe
- [12 — AI Inference and Serving Checklist](https://awesome-checklists.pages.dev/AI/12_AI_Inference_and_Serving.html): Verify that production AI inference is deployable, secure, performant, cost-bounded, and recoverable under realistic workloads. Serving improvements must be measured against user-visible qua
- [13 — Multimodal AI Quality Checklist](https://awesome-checklists.pages.dev/AI/13_Multimodal_AI_Quality.html): Verify that AI features using images, audio, speech, video, documents, or combinations of modalities produce fit-for-purpose, safe, accessible, and properly grounded results. An AI model's c
- [14 — AI Human Review and Escalation Checklist](https://awesome-checklists.pages.dev/AI/14_AI_Human_Review_and_Escalation.html): Ensure human involvement in AI-assisted decisions is meaningful, authorized, timely, and auditable. A review button, nominal human sign-off, or the ability to view model output does not esta
- [15 — AI Evaluation and Regression Checklist](https://awesome-checklists.pages.dev/AI/15_AI_Evaluation_and_Regression.html): Verify that AI-enabled applications have representative, measurable, repeatable evaluation of task quality and safety, and that changes are held to defined regression and release standards. 
- [16 — AI Red Teaming and Guardrails Checklist](https://awesome-checklists.pages.dev/AI/16_AI_Red_Teaming_and_Guardrails.html): Verify that AI-enabled products have risk-based adversarial coverage and enforceable defenses against harmful outputs, unauthorized actions, data disclosure, and abuse. Red teaming seeks to 
- [17 — MLOps and Model Lifecycle Checklist](https://awesome-checklists.pages.dev/AI/17_MLOps_and_Model_Lifecycle.html): Verify that AI/ML experiments, data, models, approvals, deployment configurations, and retirement decisions are traceable and managed across the system lifecycle. Registry entries and passin
- [18 — AI Monitoring and Drift Checklist](https://awesome-checklists.pages.dev/AI/18_AI_Monitoring_and_Drift.html): Verify that production AI systems are observable, that distribution changes are separated from demonstrated model-quality regressions, and that emerging user harm or operational failures tri
- [19 — Cost and FinOps Checklist](https://awesome-checklists.pages.dev/AI/19_Cost_and_FinOps.html): Verify that technology spending is attributable, visible, forecastable, and optimized for business value without compromising required quality, reliability, security, or user outcomes. FinOp
- [20 — Analytics and Product Metrics Checklist](https://awesome-checklists.pages.dev/AI/20_Analytics_and_ProductMetrics.html): Verify that product metrics answer meaningful decisions and are built on well-defined events, trustworthy data, privacy-aware collection, and sound experimentation. This template does not ce
- [21 — GEO and AEO Checklist](https://awesome-checklists.pages.dev/AI/21_GEO_and_AEO.html): Improve how clearly and reliably a project can be understood, sourced, and answered by search answer systems and generative AI. GEO = Generative Engine Optimization; AEO = Answer Engine Opti
- [22 — Release and Launch Readiness Checklist](https://awesome-checklists.pages.dev/AI/22_Release_and_LaunchReadiness.html): Verify that a new product, service, or significant change is ready for controlled customer exposure, has an explicit go/no-go decision, and can be operated and supported safely after launch.