Machine Learning

AWS Kendra

Amazon Kendra is an intelligent enterprise search service powered by ML that finds answers across documents, wikis, and databases.

41 Compliance Frameworks → AWS CLI Library → Machine Learning Security Guide →

What is Kendra? (Simple Explanation)

Kendra is an AWS service in the Machine Learning category. Amazon Kendra is an intelligent enterprise search service powered by ML that finds answers across documents, wikis, and databases.

When Would You Use Kendra?

  • Enterprise knowledge base search
  • Customer support knowledge management
  • Internal document discovery
  • Compliance and policy search

Who Uses Kendra?

From startups to enterprises, Kendra powers:

StartupsMid-size CompaniesLarge EnterprisesGovernmentNonprofits

What Makes Kendra Powerful

Natural language question answering
Deep learning document ranking
40+ native data source connectors
Custom synonyms and relevance tuning
Incremental learning from feedback

Kendra Pricing & Free Tier

SageMaker: from ~$0.045/hour for ml.t3.medium instances. Bedrock: on-demand per-token pricing. Rekognition: $1 per 1,000 images (first 5,000 free).

Check latest pricing on AWS →

Kendra Best Practices

  1. 1Start with pre-trained models (Bedrock, Rekognition) before training custom models
  2. 2Use SageMaker Experiments to track training runs, hyperparameters, and metrics
  3. 3Enable Model Monitor to detect data drift in production endpoints
  4. 4Set up cost allocation tags on training jobs — GPUs are expensive if left running
  5. 5Clean up unused endpoints — they incur hourly charges even with zero traffic

Getting Started with Kendra in 5 Minutes

  1. 1Open the AWS Console and navigate to Kendra
  2. 2Click "Create" or "Get started" to begin configuration
  3. 3Configure the required settings — name, region, and access permissions
  4. 4Review and create — monitor the initial status in CloudWatch

Kendra CLI Quick Reference

2 production-ready commands. Full CLI Library (225+ services) →

aws kendra helpView all Kendra CLI v2 commands and subcommands
aws kendra describe-kendra --helpView options for describing Kendra resources

Pros & Cons of Kendra

Pros

  • Natural language question answering
  • Deep learning document ranking
  • 40+ native data source connectors
  • Custom synonyms and relevance tuning
  • Incremental learning from feedback

Cons

  • ✕Vendor lock-in — migrating away from AWS requires significant effort
  • ✕Costs can be unpredictable without proper monitoring and budgeting
  • ✕Learning curve for beginners — AWS has 200+ services with complex IAM policies

Kendra vs Alternatives

Kendra vs S3
Choose Kendra when

Choose Kendra for Enterprise knowledge base search and Customer support knowledge management. It excels at natural language question answering.

Choose S3 when

Choose S3 as an alternative when your requirements differ. Each service in the Machine Learning category serves different architectural patterns.

Services That Work with Kendra

Kendra is rarely used alone. It is typically combined with:

S3LambdaCognitoLexCloudWatch

Compliance & Security

How AWS Kendra fits into major compliance standards. Browse all 41 frameworks →

CIS AWS v3.0

Kendra configuration is audited by CIS Benchmarks v1.5–v3.0 for secure cloud defaults.

NIST 800-53

Kendra access controls, encryption, and audit logging map to NIST 800-53 AC, SC, and AU control families.

PCI DSS 4.0

Kendra encryption, access control, and logging support PCI DSS for cardholder data environments.

SOC 2

Kendra security, availability, and confidentiality controls evaluated under SOC 2 Trust Services Criteria.

ISO 27001

Kendra configuration and monitoring controls map to ISO 27001 Annex A information security management.

Frequently Asked Questions About Kendra

What is AWS Kendra?

Amazon Kendra is an intelligent enterprise search service powered by ML that finds answers across documents, wikis, and databases.

What is Kendra used for?

Kendra is commonly used for: Enterprise knowledge base search; Customer support knowledge management; Internal document discovery; Compliance and policy search. It's a core service in the machine learning category of AWS.

Is Kendra free?

SageMaker: from ~$0.045/hour for ml.t3.medium instances. Bedrock: on-demand per-token pricing. Rekognition: $1 per 1,000 images (first 5,000 free).

What are the key features of Kendra?

Kendra's most important capabilities include: Natural language question answering. Deep learning document ranking. 40+ native data source connectors. Custom synonyms and relevance tuning. Incremental learning from feedback. Each of these is designed to help teams enterprise knowledge base search.

How does Kendra compare to alternatives?

Kendra competes with both AWS-native alternatives (S3, Lambda, Cognito) and third-party equivalents. The right choice depends on your specific requirements for scalability, cost, and operational overhead. See the comparisons section below for detailed guidance.

Which compliance frameworks apply to Kendra?

CIS AWS v3.0: Kendra configuration is audited by CIS Benchmarks v1.5–v3.0 for secure cloud defaults. NIST 800-53: Kendra access controls, encryption, and audit logging map to NIST 800-53 AC, SC, and AU control families. PCI DSS 4.0: Kendra encryption, access control, and logging support PCI DSS for cardholder data environments. SOC 2: Kendra security, availability, and confidentiality controls evaluated under SOC 2 Trust Services Criteria. ISO 27001: Kendra configuration and monitoring controls map to ISO 27001 Annex A information security management.

People also search for

AWS Kendra tutorialKendra getting startedKendra best practicesKendra pricingKendra free tierwhat is KendraKendra vsKendra documentationKendra cheat sheetKendra tutorial for beginnersKendra use casesKendra vs custom modelKendra API examplesKendra cost calculator

Was this page helpful?

Ready to secure your Kendra configuration?

Pavora continuously monitors your AWS Kendra for misconfigurations, compliance violations, and security risks.

Get StartedBrowse All Services