# Amazon OpenSearch Service

AWS managed service for deploying, operating, and scaling OpenSearch clusters for search and analytics workloads.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Introducing Amazon OpenSearch Memory: Persistent memory for AI agents

DevFeed: [Introducing Amazon OpenSearch Memory: Persistent memory for AI agents](<https://devfeed.tech/articles/introducing-amazon-opensearch-memory-persistent-memory-for-ai-agents-141878.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/introducing-amazon-opensearch-memory-persistent-memory-for-ai-agents/>)

Author: Ganesh Natarajan

Published: 2026-11-18T20:50:32Z

Content type: release

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-opensearch-serverless](<https://devfeed.tech/tags/amazon-opensearch-serverless.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-titan](<https://devfeed.tech/tags/amazon-titan.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [api](<https://devfeed.tech/tags/api.md>), [aws-sdk-for-python](<https://devfeed.tech/tags/aws-sdk-for-python.md>), [context](<https://devfeed.tech/tags/context.md>), [cross-session-memory](<https://devfeed.tech/tags/cross-session-memory.md>), [events](<https://devfeed.tech/tags/events.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [memory](<https://devfeed.tech/tags/memory.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [persistent-memory](<https://devfeed.tech/tags/persistent-memory.md>), [persistent-memory-for-ai](<https://devfeed.tech/tags/persistent-memory-for-ai.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [session](<https://devfeed.tech/tags/session.md>)

### AI overview

Amazon OpenSearch Memory adds persistent, cross-session memory to AI agents through serverless spaces containing verbatim events and memories derived from them. Applications write each turn and retrieve relevant memories or exact events before responding; event reads are immediate and searchability follows within seconds, while memory extraction runs asynchronously and may return no results for a new user at first. The service handles indexing, consolidation, retrieval, isolation, encryption, and retention, with actor and optional session controls; applications still add retrieved context to prompts and should review agent-written memories. In one LongMemEval-S run, the configured workflow used about 13,500 input tokens per question versus 167,000 for full history and scored 93.0% accuracy versus 95.2%; it beat BM25 raw-turn retrieval by 4.4 points. Results depend on the tested models and settings. General availability is in four AWS Regions.

### Source excerpt

Amazon OpenSearch Memory is now generally available. Built on Amazon OpenSearch Serverless, it adds persistent, cross-session memory to AI agents. It stores interactions as searchable events, derives memories, and retrieves relevant context, so you can give agents long-term memory without building your own memory system.

## AWS Weekly Roundup: AWS Nitro Sandboxes, AWS Emulator, and more (November 16, 2026)

DevFeed: [AWS Weekly Roundup: AWS Nitro Sandboxes, AWS Emulator, and more (November 16, 2026)](<https://devfeed.tech/articles/aws-weekly-roundup-aws-nitro-sandboxes-aws-emulator-and-more-november-16-2026-136092.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/aws/aws-weekly-roundup-aws-nitro-sandboxes-aws-emulator-and-more-november-16-2026/>)

Author: Daniel Abib

Published: 2026-11-16T17:55:46Z

Content type: news

Language: en

Sources: [AWS News Blog](<https://devfeed.tech/sources/aws-news-blog.md>)

Topics: [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Nitro System](<https://devfeed.tech/topics/nitro-system.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon CloudWatch Logs](<https://devfeed.tech/topics/amazon-cloudwatch-logs.md>), [AWS Step Functions](<https://devfeed.tech/topics/aws-step-functions.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-cloudwatch-logs](<https://devfeed.tech/tags/amazon-cloudwatch-logs.md>), [amazon-cognito](<https://devfeed.tech/tags/amazon-cognito.md>), [amazon-dynamodb](<https://devfeed.tech/tags/amazon-dynamodb.md>), [amazon-ec2](<https://devfeed.tech/tags/amazon-ec2.md>), [amazon-elastic-container-service](<https://devfeed.tech/tags/amazon-elastic-container-service.md>), [amazon-elastic-kubernetes-service](<https://devfeed.tech/tags/amazon-elastic-kubernetes-service.md>), [amazon-elasticache](<https://devfeed.tech/tags/amazon-elasticache.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [application](<https://devfeed.tech/tags/application.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-emulator](<https://devfeed.tech/tags/aws-emulator.md>), [aws-re-invent](<https://devfeed.tech/tags/aws-re-invent.md>), [aws-step-functions](<https://devfeed.tech/tags/aws-step-functions.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [delivery](<https://devfeed.tech/tags/delivery.md>), [demo](<https://devfeed.tech/tags/demo.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [developers](<https://devfeed.tech/tags/developers.md>), [emulator](<https://devfeed.tech/tags/emulator.md>), [events](<https://devfeed.tech/tags/events.md>), [news](<https://devfeed.tech/tags/news.md>), [nitro](<https://devfeed.tech/tags/nitro.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [tools](<https://devfeed.tech/tags/tools.md>), [week-in-review](<https://devfeed.tech/tags/week-in-review.md>), [weekly](<https://devfeed.tech/tags/weekly.md>), [weekly-roundup](<https://devfeed.tech/tags/weekly-roundup.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

AWS Emulator lets developers and coding agents test AWS API interactions locally through the AWS CLI or SDKs, without an AWS account or per-attempt cloud provisioning. Its coverage varies: unsupported calls return HTTP 501, and it does not emulate IAM or resource-policy enforcement or cross-account and cross-Region behavior, so production testing on AWS remains necessary. Other launches include Nitro Sandboxes, which isolate pods, tasks, or VMs on shared EC2 instances, with confidential mode adding protection from node operators and attestation; Cognito token exchange for narrower downstream tokens; and Valkey 9 search and aggregations in ElastiCache Serverless. OpenSearch Service cross-Region recovery pairs version 3.7+ domains in one account, with stated recovery objectives under one minute for data loss and under 20 minutes for recovery time, though unplanned failover can lose unreplicated data. The roundup also covers CloudWatch Logs retention policies and the next-generation AgentCore runtime.

### Source excerpt

A second delivery of the same message can reveal more about an application than its happy-path demo. I like tools that make those cases easier to investigate while a change is still small. Last week's launch of AWS Emulator brings part of that work onto your own machine: developers and coding agents can exercise AWS [...]

## Understanding span queries in Amazon OpenSearch Service

DevFeed: [Understanding span queries in Amazon OpenSearch Service](<https://devfeed.tech/articles/understanding-span-queries-in-amazon-opensearch-service-133390.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/understanding-span-queries-in-amazon-opensearch-service/>)

Author: Jon Handler

Published: 2026-11-13T22:00:29Z

Content type: article

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [opensearch](<https://devfeed.tech/topics/opensearch.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>)

Tags: [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-cloud](<https://devfeed.tech/tags/aws-cloud.md>), [edit-distance](<https://devfeed.tech/tags/edit-distance.md>), [expert-400](<https://devfeed.tech/tags/expert-400.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [queries](<https://devfeed.tech/tags/queries.md>), [query](<https://devfeed.tech/tags/query.md>), [span](<https://devfeed.tech/tags/span.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

Span queries let Amazon OpenSearch Service users express term-order, position, proximity, and containment constraints that phrase queries cannot reliably capture. Phrase queries match contiguous terms; `match_phrase` slop allows positional swaps, which can produce matches with terms in an unexpected order. Span queries combine span-only clauses such as `span_term`, `span_near`, `span_first`, `span_not`, `span_containing`, and `span_within`; `in_order` controls clause ordering, while containment queries differ in whether they return the larger or smaller span. The examples show anchoring a term near a field's start and requiring an exact phrase to occur inside a broader span. This precision can help legal, regulatory, patent, scientific, and compliance searches where placement matters, and offers a query-time option when text lacks a structured model. Span queries are more verbose and require careful composition.

### Source excerpt

Among OpenSearch query types, span queries give you precise control over where terms appear in a document and how they relate to one another. Learn how span queries work, when to use them instead of phrase queries, and how to compose them to enforce exact term order, position, and containment that phrase queries cannot express.

## How IGNYTE runs candidate search with Amazon S3 Vectors

DevFeed: [How IGNYTE runs candidate search with Amazon S3 Vectors](<https://devfeed.tech/articles/how-ignyte-runs-candidate-search-with-amazon-s3-vectors-133435.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/storage/how-ignyte-runs-candidate-search-with-amazon-s3-vectors/>)

Author: Saurabh Gupta

Published: 2026-11-13T19:52:38Z

Content type: article

Language: en

Sources: [AWS Storage Blog](<https://devfeed.tech/sources/aws-storage-blog.md>)

Topics: [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon SageMaker](<https://devfeed.tech/topics/amazon-sagemaker.md>), [Parquet files in Amazon S3](<https://devfeed.tech/topics/parquet-files-in-amazon-s3.md>)

Tags: [agentcore](<https://devfeed.tech/tags/agentcore.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-sagemaker-ai](<https://devfeed.tech/tags/amazon-sagemaker-ai.md>), [amazon-simple-storage-service-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-s3.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [aws-glue](<https://devfeed.tech/tags/aws-glue.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [layout](<https://devfeed.tech/tags/layout.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

IGNYTE moved embeddings for more than 1 billion contacts from OpenSearch Service to Amazon S3 Vectors; more than 800 million contacts are currently embedded. OpenSearch Service retains full profiles and handles structured filters. A scheduled batch pipeline loads company records first, then enriches contact records, generates embeddings, and writes profiles and vectors to their respective stores. Vectors are partitioned by continent, with minimal metadata for query filters. Searches embed the recruiter's query, retrieve the 100 closest contacts from the matching S3 Vectors index, then apply skills, experience, and other structured filters in OpenSearch Service. The article reports that the full agent matching workflow averages under 30 seconds after migration, compared with 3-4 minutes before; this is an end-to-end result, not a single vector query.

### Source excerpt

Ignyte moved the embeddings for more than 1 billion contacts from Amazon OpenSearch Service to Amazon S3 Vectors, keeping OpenSearch Service for structured filtering. See the per-continent index layout, the minimal-metadata design, and the batch pipeline behind its two-hop semantic candidate search.

## Managed cross-Region disaster recovery for Amazon OpenSearch Service

DevFeed: [Managed cross-Region disaster recovery for Amazon OpenSearch Service](<https://devfeed.tech/articles/managed-cross-region-disaster-recovery-for-amazon-opensearch-service-129794.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/managed-cross-region-disaster-recovery-for-amazon-opensearch-service/>)

Author: Cedric Pelvet

Published: 2026-11-12T00:45:45Z

Content type: article

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Disaster Recovery](<https://devfeed.tech/topics/disaster-recovery.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [read-replica](<https://devfeed.tech/topics/read-replica.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>)

Tags: [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [api](<https://devfeed.tech/tags/api.md>), [aws-command-line-interface-aws-cli](<https://devfeed.tech/tags/aws-command-line-interface-aws-cli.md>), [aws-key-management-service-aws-kms](<https://devfeed.tech/tags/aws-key-management-service-aws-kms.md>), [aws-management-console](<https://devfeed.tech/tags/aws-management-console.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [business-continuity](<https://devfeed.tech/tags/business-continuity.md>), [cross](<https://devfeed.tech/tags/cross.md>), [disaster-recovery](<https://devfeed.tech/tags/disaster-recovery.md>), [failover](<https://devfeed.tech/tags/failover.md>), [foundational-100](<https://devfeed.tech/tags/foundational-100.md>), [region](<https://devfeed.tech/tags/region.md>), [rpo](<https://devfeed.tech/tags/rpo.md>), [rto](<https://devfeed.tech/tags/rto.md>)

### AI overview

Amazon OpenSearch Service now provides managed cross-Region disaster recovery for domains running OpenSearch 3.7 or later. Pair same-account domains in different Regions with matching capacity; the service copies existing data and continuously replicates changes, with both domains readable and only the primary writable. Planned switchover coordinates a role swap with zero data loss; failover promotes the secondary without waiting, and may lose writes still in replication transit, bounded by replication lag. The stated targets are RPO under one minute and RTO under 20 minutes; example tests saw 8-10 seconds of loss on failover and writes resume in about a minute. Applications must redirect writes after promotion. Index templates, settings, roles, and ISM policies are not replicated and must be managed on both domains. UltraWarm, Writable Warm, and the OpenSearch Optimized engine for log analytics are unsupported. There is no additional service charge, though secondary-domain capacity and cross-Region transfer are billed.

### Source excerpt

Amazon OpenSearch Service now offers managed cross-Region disaster recovery for domains on OpenSearch 3.7 or later. It replicates data from a primary domain to a secondary domain in another Region with API-driven switchover and failover, providing an RPO under 1 minute and an RTO under 20 minutes.

## 46% fewer nodes, 2x faster indexing: Confluent on Amazon OpenSearch Service

DevFeed: [46% fewer nodes, 2x faster indexing: Confluent on Amazon OpenSearch Service](<https://devfeed.tech/articles/46-fewer-nodes-2-faster-indexing-confluent-on-amazon-opensearch-service-127631.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/46-fewer-nodes-2x-faster-indexing-confluent-on-amazon-opensearch-service/>)

Author: Sukanth Rajan

Published: 2026-11-10T19:56:57Z

Content type: news

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [amazon-elastic-block-store-amazon-ebs](<https://devfeed.tech/tags/amazon-elastic-block-store-amazon-ebs.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-simple-storage-service-amazon-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-amazon-s3.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [analytics-workloads](<https://devfeed.tech/tags/analytics-workloads.md>), [apache-kafka](<https://devfeed.tech/tags/apache-kafka.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [backpressure](<https://devfeed.tech/tags/backpressure.md>), [confluent](<https://devfeed.tech/tags/confluent.md>), [cost](<https://devfeed.tech/tags/cost.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [fleet](<https://devfeed.tech/tags/fleet.md>), [indexing](<https://devfeed.tech/tags/indexing.md>), [latency](<https://devfeed.tech/tags/latency.md>), [logs](<https://devfeed.tech/tags/logs.md>), [node](<https://devfeed.tech/tags/node.md>), [nodes](<https://devfeed.tech/tags/nodes.md>), [observability](<https://devfeed.tech/tags/observability.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [write](<https://devfeed.tech/tags/write.md>)

### AI overview

Confluent moved its Amazon OpenSearch Service logging hot tier from r6gd to oi2 using a two-phase, measure-first migration. At the same node count and ingest, oi2 used roughly one-third the CPU; iterative rightsizing then reduced nodes by about 46%, with each remaining node carrying about 1.9x the load. Indexing latency roughly halved and write queues fell below about one queued operation across four domains. JVM heap, not CPU, limited further reductions; one heavily downsized domain retained higher CPU and the only queue not near zero, so it needs monitoring through peak traffic. The final state had no write rejections and healthy clusters. Despite a higher per-node price, fewer nodes yielded an estimated 18% lower hot-tier cost at on-demand rates; a 1-year reserved footprint is estimated at 47-51% below the original on-demand baseline. These approximate figures exclude unchanged storage and dedicated-master tiers.

### Source excerpt

How Confluent modernized its Amazon OpenSearch Service observability hot tier, ingesting hundreds of terabytes of logs per day, by migrating from r6gd to the purpose-built oi2 instance family. A measure-first approach cut the fleet 46%, roughly halved indexing latency, and cleared write backpressure, lowering cost even at a higher per-node price.

## Migrating Booking.com's autocomplete workload at scale to OpenSearch

DevFeed: [Migrating Booking.com's autocomplete workload at scale to OpenSearch](<https://devfeed.tech/articles/migrating-booking-com-s-autocomplete-workload-at-scale-to-opensearch-118928.md>)

Original publisher: [Read original article](<https://opensearch.org/case-studies/migrating-booking-coms-autocomplete-workload-at-scale-to-opensearch/>)

Author: OpenSearch

Published: 2026-11-04T16:00:51Z

Content type: news

Language: en

Sources: [OpenSearch](<https://devfeed.tech/sources/opensearch.md>)

Topics: [opensearch](<https://devfeed.tech/topics/opensearch.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [zero downtime deployment](<https://devfeed.tech/topics/zero-downtime-deployment.md>), [Performance Testing](<https://devfeed.tech/topics/performance-testing.md>)

Tags: [apache](<https://devfeed.tech/tags/apache.md>), [autocomplete](<https://devfeed.tech/tags/autocomplete.md>), [booking](<https://devfeed.tech/tags/booking.md>), [case-studies](<https://devfeed.tech/tags/case-studies.md>), [custom](<https://devfeed.tech/tags/custom.md>), [downtime](<https://devfeed.tech/tags/downtime.md>), [engine](<https://devfeed.tech/tags/engine.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [languages](<https://devfeed.tech/tags/languages.md>), [latency](<https://devfeed.tech/tags/latency.md>), [lucene](<https://devfeed.tech/tags/lucene.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>), [migration](<https://devfeed.tech/tags/migration.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [scale](<https://devfeed.tech/tags/scale.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

Booking.com migrated autocomplete from its custom Lucene engine Brick to Amazon OpenSearch Service, preserving relevance across 42+ languages and rolling out without downtime. The team rebuilt active features in OpenSearch DSL using custom analyzers and edge n-grams, scoring functions, result collapsing, fuzzy matching, and parallel subqueries. A Kubernetes ingestion pipeline and daily index builds with Step Functions and OpenSearch ISM enabled automated blue/green alias switches. To meet an 85 ms p95 SLA after staging latency reached 300-500 ms, engineers flattened dynamic maps and enabled doc_values so rescoring could use in-memory columnar data, then tuned cluster storage and topology. They mirrored production traffic and compared Recall@k and Kendall's tau against Brick, with automated gates for incomplete index updates. A phased language and traffic rollout reached 4,000 requests per second within the SLA and removed bare-metal and NFS dependencies. The new platform also enabled experimentation with hybrid search and intent prediction.

### Source excerpt

Booking.com migrated its autocomplete workload from Brick, a custom Apache Lucene engine, to OpenSearch. The team preserved search relevance across 42+ languages while meeting strict latency requirements and completing the transition without downtime. The migration reduced infrastructure maintenance and established a foundation for more advanced search experiences driven by traveler intent. The post Migrating Booking.com's autocomplete workload at scale to OpenSearch appeared first on OpenSearch.

## Five years after the fork, OpenSearch is slowly stepping out of AWS's shadow

DevFeed: [Five years after the fork, OpenSearch is slowly stepping out of AWS's shadow](<https://devfeed.tech/articles/five-years-after-the-fork-opensearch-is-slowly-stepping-out-of-aws-s-shadow-109952.md>)

Original publisher: [Read original article](<https://thenewstack.io/opensearch-foundation-aws-elasticsearch/>)

Author: Paul Sawers

Published: 2026-10-31T16:02:34Z

Content type: news

Language: en

Sources: [OpenSearch](<https://devfeed.tech/sources/opensearch.md>), [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [opensearch](<https://devfeed.tech/topics/opensearch.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>)

Tags: [2021](<https://devfeed.tech/tags/2021.md>), [2022](<https://devfeed.tech/tags/2022.md>), [2025](<https://devfeed.tech/tags/2025.md>), [2026](<https://devfeed.tech/tags/2026.md>), [about](<https://devfeed.tech/tags/about.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-web-services](<https://devfeed.tech/tags/amazon-web-services.md>), [aws](<https://devfeed.tech/tags/aws.md>), [data](<https://devfeed.tech/tags/data.md>), [first](<https://devfeed.tech/tags/first.md>), [fork](<https://devfeed.tech/tags/fork.md>), [news](<https://devfeed.tech/tags/news.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [project](<https://devfeed.tech/tags/project.md>), [services](<https://devfeed.tech/tags/services.md>), [stack](<https://devfeed.tech/tags/stack.md>), [web](<https://devfeed.tech/tags/web.md>), [web-services](<https://devfeed.tech/tags/web-services.md>)

### AI overview

OpenSearch is gaining contributors and self-managed users beyond AWS, though the company remains influential and concerns about its vendor ties persist. The OpenSearch Software Foundation reports AWS's share of repository contribution activity fell from 91% in the project's first year to 72% in 2025-26, and Amazon-affiliated maintainers in the core repository fell from 95% in April 2022 to 71% today. Self-managed cloud deployments rose from 37% in 2024 to 60%, while use of Amazon's managed service rose from 44% to 48%; 24% of surveyed non-adopters cite neutrality concerns. AWS holds four of 15 Technical Steering Committee seats, and an AWS employee was reelected chair. The article describes OpenSearch's divergence from Elasticsearch and its vector and hybrid search capabilities for AI retrieval applications; version 3.9 adds related retrieval improvements alongside performance, monitoring, and alerting updates. Enterprise adoption may take time because organizations remain bound by existing contracts, and some deployments are still experimental.

### Source excerpt

OpenSearch has come a long way since Amazon Web Services first announced the project back in January 2021, in response The post Five years after the fork, OpenSearch is slowly stepping out of AWS's shadow appeared first on The New Stack.

## AI-enriched ingestion pipelines for searchable live and VOD media on AWS

DevFeed: [AI-enriched ingestion pipelines for searchable live and VOD media on AWS](<https://devfeed.tech/articles/ai-enriched-ingestion-pipelines-for-searchable-live-and-vod-media-on-aws-103468.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/media/ai-enriched-ingestion-pipelines-for-searchable-live-and-vod-media-on-aws/>)

Author: Mohan Kumar Guruswamy

Published: 2026-10-27T23:23:57Z

Content type: article

Language: en

Sources: [AWS for M&E Blog](<https://devfeed.tech/sources/aws-for-m-e-blog.md>)

Topics: [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [AWS Step Functions](<https://devfeed.tech/topics/aws-step-functions.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon EventBridge](<https://devfeed.tech/topics/amazon-eventbridge.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [amazon-api-gateway](<https://devfeed.tech/tags/amazon-api-gateway.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-data-automation](<https://devfeed.tech/tags/amazon-bedrock-data-automation.md>), [amazon-eventbridge](<https://devfeed.tech/tags/amazon-eventbridge.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-simple-queue-service-sqs](<https://devfeed.tech/tags/amazon-simple-queue-service-sqs.md>), [amazon-simple-storage-service-amazon-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-amazon-s3.md>), [amazon-simple-storage-service-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-s3.md>), [amazon-sqs](<https://devfeed.tech/tags/amazon-sqs.md>), [amazon-transcribe](<https://devfeed.tech/tags/amazon-transcribe.md>), [amazon-web-services-aws](<https://devfeed.tech/tags/amazon-web-services-aws.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-elemental-mediaconvert](<https://devfeed.tech/tags/aws-elemental-mediaconvert.md>), [aws-elemental-medialive](<https://devfeed.tech/tags/aws-elemental-medialive.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [aws-step-functions](<https://devfeed.tech/tags/aws-step-functions.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-native](<https://devfeed.tech/tags/cloud-native.md>), [industries](<https://devfeed.tech/tags/industries.md>), [live](<https://devfeed.tech/tags/live.md>), [media](<https://devfeed.tech/tags/media.md>), [media-entertainment](<https://devfeed.tech/tags/media-entertainment.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [services](<https://devfeed.tech/tags/services.md>)

### AI overview

The article describes an AWS design that makes live and archived media searchable by its content through parallel AI analysis at ingestion. For live broadcasts, MediaLive writes roughly six-second HLS segments to S3; every 60 seconds, Step Functions processes a batch with Marengo 3.0 embeddings, Bedrock Data Automation scene analysis, and Transcribe, indexing results in OpenSearch within 60-90 seconds. Elemental Inference separately detects live key moments, which can be indexed within 20-30 seconds. The VOD pipeline queues uploads for backpressure, transcodes by media type, then runs similar analysis; dynamic scene segmentation and a 24-hour workflow accommodate longer assets. It uses modality-specific outputs and permits partial indexing if a branch fails. Both pipelines create a shared document structure for unified search. The AI index adds to TAMS while leaving its timeline and existing tools intact. This is Part 1; the unified search architecture is reserved for Part 2.

### Source excerpt

As organizations adopt TAMS and cloud-centered workflows through the Amazon Web Services (AWS) Cloud-Native Agile Production (CNAP) program, the opportunity is clear: Make content discoverable by what it contains rather than how it was tagged. This post, which is Part 1 of a two-part series, describes how AI-powered ingestion pipelines analyze each piece of media at ingest time.

## Introducing the next generation of serverless time series for Amazon OpenSearch Service

DevFeed: [Introducing the next generation of serverless time series for Amazon OpenSearch Service](<https://devfeed.tech/articles/introducing-the-next-generation-of-serverless-time-series-for-amazon-opensearch-service-104240.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/introducing-the-next-generation-of-serverless-time-series-for-amazon-opensearch-service/>)

Author: Kevin Fallis

Published: 2026-10-27T21:40:22Z

Content type: release

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [Temporal data](<https://devfeed.tech/topics/temporal-data.md>)

Tags: [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [collections](<https://devfeed.tech/tags/collections.md>), [cost](<https://devfeed.tech/tags/cost.md>), [data](<https://devfeed.tech/tags/data.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [define](<https://devfeed.tech/tags/define.md>), [events](<https://devfeed.tech/tags/events.md>), [field](<https://devfeed.tech/tags/field.md>), [generation](<https://devfeed.tech/tags/generation.md>), [insights](<https://devfeed.tech/tags/insights.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [next](<https://devfeed.tech/tags/next.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [performance](<https://devfeed.tech/tags/performance.md>), [raw](<https://devfeed.tech/tags/raw.md>), [series](<https://devfeed.tech/tags/series.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [service](<https://devfeed.tech/tags/service.md>), [time](<https://devfeed.tech/tags/time.md>), [time-series](<https://devfeed.tech/tags/time-series.md>)

### AI overview

Amazon OpenSearch Serverless next-generation time-series collections combine autoscaling--including scaling to zero after 10 idle minutes at the default minimum--with S3-backed durability and separate compute and storage. Per-index settings move aging data from a fast hot tier to a lower-cost warm tier; warm data remains queryable but can have higher latency, and tiering changes cost and responsiveness rather than retention. Lifecycle policies on each index control how long data is kept. You can override the default `@timestamp` field, but every document must include a valid value for the chosen field before ingestion; invalid documents are rejected individually and reported as errors within a bulk response. The article also describes the Observability workspace in the next-generation OpenSearch UI, with alerting, anomaly detection, visualizations, and PPL processing for time-series workloads.

### Source excerpt

The next generation of Amazon OpenSearch Service serverless now supports time series collections. Define the boundaries for cost, performance, security, access, and data retention using simple controls for data tiering, time field selection, and data retention, then turn raw events into insights with the next-generation OpenSearch UI.

## From Problem to Fix in Minutes: Automating Search Relevance Tuning with the Amazon OpenSearch Service Relevance Agent

DevFeed: [From Problem to Fix in Minutes: Automating Search Relevance Tuning with the Amazon OpenSearch Service Relevance Agent](<https://devfeed.tech/articles/from-problem-to-fix-in-minutes-automating-search-relevance-tuning-with-the-amazon-opensearch-service-relevance-agent-104239.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/from-problem-to-fix-in-minutes-automating-search-relevance-tuning-with-the-amazon-opensearch-service-relevance-agent/>)

Author: Aruna Govindaraju

Published: 2026-10-27T21:31:20Z

Content type: article

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [all](<https://devfeed.tech/tags/all.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [better](<https://devfeed.tech/tags/better.md>), [chat](<https://devfeed.tech/tags/chat.md>), [data](<https://devfeed.tech/tags/data.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [insights](<https://devfeed.tech/tags/insights.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [leaving](<https://devfeed.tech/tags/leaving.md>), [minutes](<https://devfeed.tech/tags/minutes.md>), [offline](<https://devfeed.tech/tags/offline.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [query](<https://devfeed.tech/tags/query.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [search](<https://devfeed.tech/tags/search.md>), [service](<https://devfeed.tech/tags/service.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The Amazon OpenSearch Service Search Relevance Agent automates an offline tuning loop: it analyzes User Behavior Insights (UBI) data, proposes a revised query DSL configuration, and uses Search Relevance Workbench (SRW) experiments to compare it with the baseline. Its three skills cover behavior analysis, hypothesis generation, and evaluation; deterministic tools calculate metrics, and the proposed changes and experiment artifacts can be inspected before a person decides whether to deploy. In the example, wireless earbuds searches had a 57.14% CTR (8 clicks from 14 searches); evaluation raised NDCG with minor MAP and Precision tradeoffs. The agent tunes configurations for systematic relevance issues; it does not rewrite queries at runtime or intercept requests. The article requires an OpenSearch Service domain running OpenSearch 3.5 or later, the OpenSearch UI application, and instrumented behavioral records. For hybrid search, SRW also has a separate optimizer for testing normalization, combination, and lexical/neural weight settings.

### Source excerpt

The Amazon OpenSearch Service Search Relevance Agent turns a low NDCG score into a better search query in minutes. Describe the problem through the Ask AI chat, and the agent analyzes your User Behavior Insights data, generates an improved query, and validates it with an offline Search Relevance Workbench experiment, all without leaving the UI.

## Build RAG-ready indexes from Amazon S3 with Amazon OpenSearch intelligent ingestion

DevFeed: [Build RAG-ready indexes from Amazon S3 with Amazon OpenSearch intelligent ingestion](<https://devfeed.tech/articles/build-rag-ready-indexes-from-amazon-s3-with-amazon-opensearch-intelligent-ingestion-98493.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/build-rag-ready-indexes-from-amazon-s3-with-amazon-opensearch-intelligent-ingestion/>)

Author: Hang Zuo

Published: 2026-10-23T21:50:38Z

Content type: release

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [etl](<https://devfeed.tech/topics/etl.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-opensearch-serverless](<https://devfeed.tech/tags/amazon-opensearch-serverless.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-simple-storage-service-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-s3.md>), [amazon-sqs](<https://devfeed.tech/tags/amazon-sqs.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-management-console](<https://devfeed.tech/tags/aws-management-console.md>), [foundational-100](<https://devfeed.tech/tags/foundational-100.md>), [indexes](<https://devfeed.tech/tags/indexes.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [rag](<https://devfeed.tech/tags/rag.md>)

### AI overview

Amazon OpenSearch intelligent ingestion turns data in Amazon S3 into searchable indexes in OpenSearch Serverless (NextGen): it discovers objects, parses PDF and Word documents while retaining structure and tables, describes embedded images, chunks content, generates embeddings, and indexes the results. It also ingests JSON, NDJSON, and CSV, with optional semantic enrichment and transformations. Choose a one-time batch for a static load, continuous streaming for new objects, or batch then stream to backfill existing data and continue monitoring S3 notifications. Setup requires a source bucket and prefix, destination index, and IAM permissions; streams use SQS notifications. Capacity scales within configured OCU limits, and billing covers active processing. Unstructured parsing and image descriptions add costs; the article gives illustrative estimates based on internal testing and notes availability in six AWS Regions.

### Source excerpt

Amazon OpenSearch intelligent ingestion is a fully managed, serverless capability that turns documents and structured data in Amazon S3 into RAG-ready, searchable indexes with no pipelines to manage. Learn how it works and when to use Ingestion Jobs or Ingestion Streams.

## From problem to fix in minutes: Automating search relevance tuning with the Amazon OpenSearch Search Relevance Agent

DevFeed: [From problem to fix in minutes: Automating search relevance tuning with the Amazon OpenSearch Search Relevance Agent](<https://devfeed.tech/articles/from-problem-to-fix-in-minutes-automating-search-relevance-tuning-with-the-amazon-opensearch-search-relevance-agent-96232.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/from-problem-to-fix-in-minutes-automating-search-relevance-tuning-with-the-amazon-opensearch-search-relevance-agent/>)

Author: Aruna Govindaraju

Published: 2026-10-22T17:43:30Z

Content type: article

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [agent](<https://devfeed.tech/tags/agent.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [complete](<https://devfeed.tech/tags/complete.md>), [data](<https://devfeed.tech/tags/data.md>), [example](<https://devfeed.tech/tags/example.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [language](<https://devfeed.tech/tags/language.md>), [minutes](<https://devfeed.tech/tags/minutes.md>), [offline](<https://devfeed.tech/tags/offline.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [post](<https://devfeed.tech/tags/post.md>), [query](<https://devfeed.tech/tags/query.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [search](<https://devfeed.tech/tags/search.md>), [service](<https://devfeed.tech/tags/service.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [this](<https://devfeed.tech/tags/this.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The Amazon OpenSearch Service Search Relevance Agent automates a human-reviewed tuning loop: it analyzes User Behavior Insights (UBI) data, proposes query DSL changes, and validates them with offline Search Relevance Workbench (SRW) experiments before deployment. Its three skills handle behavior analysis, hypothesis generation, and evaluation; deterministic tools calculate metrics, and proposals expose their reasoning for review. In the example, the agent identified low overall clicks, investigated the "wireless earbuds" query (261 searches, 65 clicks, 24% CTR), proposed fixes for keyword field dilution, missing popularity signals, and `best_fields` vulnerability, then reported improved NDCG with minor MAP and Precision tradeoffs. The article says the agent does not alter queries at runtime; it tunes configurations for future searches. It requires an OpenSearch Service domain running OpenSearch 3.5 or later, the OpenSearch UI application, and behavioral data. A separate Hybrid Search Optimizer is described for tuning hybrid-search parameters.

### Source excerpt

The Amazon OpenSearch Service Search Relevance Agent automates search relevance tuning. You describe a problem in plain language, and the agent investigates your behavioral data, proposes an improved query, and validates it with an offline experiment. This post walks through the agent's architecture and a complete example investigation.

## Beyond Top-K: Building search-confidence guardrails for agentic AI with OpenSearch

DevFeed: [Beyond Top-K: Building search-confidence guardrails for agentic AI with OpenSearch](<https://devfeed.tech/articles/beyond-top-k-building-search-confidence-guardrails-for-agentic-ai-with-opensearch-88029.md>)

Original publisher: [Read original article](<https://opensearch.org/blog/beyond-top-k-building-search-confidence-guardrails-for-agentic-ai-with-opensearch/>)

Author: Chanpreet Singh

Published: 2026-10-15T19:11:24Z

Content type: tutorial

Language: en

Sources: [OpenSearch](<https://devfeed.tech/sources/opensearch.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [blog](<https://devfeed.tech/tags/blog.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [technical](<https://devfeed.tech/tags/technical.md>)

### AI overview

The article explains how to add a confidence layer between retrieval and action in agentic AI systems. It proposes combining retrieval score magnitude and gaps with result coherence, freshness, and source authority, then using thresholds adapted to query type and action intent. A graduated response lets an agent act, add a caveat, ask for clarification, escalate, or abstain when retrieved results are not reliable enough. OpenSearch features such as hybrid search, normalization processors, min_score, script_score, and ML Commons reranking provide implementation building blocks.

### Source excerpt

Top-K retrieval always returns results-even when nothing relevant exists. This post introduces a confidence layer framework that gives agents the ability to say 'I'm not confident enough to act,' using OpenSearch primitives like normalization processors, min_score, script_score, and reranking via ML Commons. The post Beyond Top-K: Building search-confidence guardrails for agentic AI with OpenSearch appeared first on OpenSearch.

## How UTS established a modern curriculum data services foundation on AWS

DevFeed: [How UTS established a modern curriculum data services foundation on AWS](<https://devfeed.tech/articles/how-uts-established-a-modern-curriculum-data-services-foundation-on-aws-87252.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/how-uts-established-a-modern-curriculum-data-services-foundation-on-aws/>)

Author: Oleg Polianski

Published: 2026-10-14T14:29:10Z

Content type: article

Language: en

Sources: [AWS Architecture Blog](<https://devfeed.tech/sources/aws-architecture-blog.md>)

Topics: [Snowflake streaming data architecture](<https://devfeed.tech/topics/snowflake-streaming-data-architecture.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Amazon MSK](<https://devfeed.tech/topics/amazon-msk.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [AWS Amplify](<https://devfeed.tech/topics/aws-amplify.md>), [Amazon EventBridge](<https://devfeed.tech/topics/amazon-eventbridge.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Redis](<https://devfeed.tech/topics/redis.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [amazon-api-gateway](<https://devfeed.tech/tags/amazon-api-gateway.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-eventbridge](<https://devfeed.tech/tags/amazon-eventbridge.md>), [amazon-msk](<https://devfeed.tech/tags/amazon-msk.md>), [amazon-neptune](<https://devfeed.tech/tags/amazon-neptune.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-route-53](<https://devfeed.tech/tags/amazon-route-53.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-appsync](<https://devfeed.tech/tags/aws-appsync.md>), [aws-certificate-manager](<https://devfeed.tech/tags/aws-certificate-manager.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-key-management-service](<https://devfeed.tech/tags/aws-key-management-service.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [aws-secrets-manager](<https://devfeed.tech/tags/aws-secrets-manager.md>), [aws-waf](<https://devfeed.tech/tags/aws-waf.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [data](<https://devfeed.tech/tags/data.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantic-search](<https://devfeed.tech/tags/semantic-search.md>)

### AI overview

The University of Technology Sydney built an AWS-based curriculum data service that keeps its Curriculum Management System as the system of record while exposing governed APIs, graph traversal, semantic search, and event delivery. Since production launch, the service has recorded zero incidents, averages 1.6-second delivery of changes, and is operated by one engineer.

### Source excerpt

The University of Technology Sydney built a modern curriculum data services foundation on AWS that treats curriculum data as a governed, reusable product, available through APIs, graph traversal, semantic search, and event delivery, while leaving the source Curriculum Management System authoritative. One engineer now operates the domain.

## Finding the perfect moment: How Formula 1® uses AWS AI to search archives in seconds

DevFeed: [Finding the perfect moment: How Formula 1® uses AWS AI to search archives in seconds](<https://devfeed.tech/articles/finding-the-perfect-moment-how-formula-1-uses-aws-ai-to-search-archives-in-seconds-85260.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/media/finding-the-perfect-moment-how-formula-1-uses-aws-ai-to-search-archives-in-seconds/>)

Author: Paula Marenco

Published: 2026-10-12T15:17:56Z

Content type: article

Language: en

Sources: [AWS for M&E Blog](<https://devfeed.tech/sources/aws-for-m-e-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AWS CloudTrail](<https://devfeed.tech/topics/aws-cloudtrail.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-guardrails](<https://devfeed.tech/tags/ai-guardrails.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-guardrails](<https://devfeed.tech/tags/amazon-bedrock-guardrails.md>), [amazon-dynamodb](<https://devfeed.tech/tags/amazon-dynamodb.md>), [amazon-nova](<https://devfeed.tech/tags/amazon-nova.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-rds](<https://devfeed.tech/tags/amazon-rds.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-simple-storage-service-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-s3.md>), [amazon-web-services-aws](<https://devfeed.tech/tags/amazon-web-services-aws.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-appsync](<https://devfeed.tech/tags/aws-appsync.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [caching](<https://devfeed.tech/tags/caching.md>), [industries](<https://devfeed.tech/tags/industries.md>), [sports](<https://devfeed.tech/tags/sports.md>)

### AI overview

Formula 1 and AWS added a natural-language search layer to the F1 Video Archive, using Amazon Bedrock to interpret requests, resolve facts, and create precise queries for Amazon OpenSearch Service. The article describes catalog-grounded entity extraction, guarded database lookups, layered caching, and fallback to text search when AI-dependent steps fail. AWS says the system lets editors find footage in minutes where research previously took hours.

### Source excerpt

F1 worked with AWS to migrate petabytes of footage from ageing tape robots, in multiple formats and proxy files, into Amazon Simple Storage Service (Amazon S3) alongside the live footage from every new race. That gave the sport one durable home for its heritage: the F1 Video Archive. In April 2026, F1 upgraded the archive with a new Media Archive Discovery system. Working with Amazon Web Services (AWS), the team added Amazon Bedrock in a deliberately narrow role: a layer that reads a request in plain language, works out what it means, looks up any facts it depends on, and turns it into a precise search the archive can retrieve.

## Monitoring MWAA-orchestrated ETL pipelines with Amazon OpenSearch Service

DevFeed: [Monitoring MWAA-orchestrated ETL pipelines with Amazon OpenSearch Service](<https://devfeed.tech/articles/monitoring-mwaa-orchestrated-etl-pipelines-with-amazon-opensearch-service-65455.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/monitoring-mwaa-orchestrated-etl-pipelines-with-amazon-opensearch-service/>)

Author: Anupa Bhattacharyya

Published: 2026-10-06T16:17:46Z

Content type: tutorial

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [amazon-cloudwatch-logs](<https://devfeed.tech/tags/amazon-cloudwatch-logs.md>), [amazon-managed-workflows-for-apache-airflow-amazon-mwaa](<https://devfeed.tech/tags/amazon-managed-workflows-for-apache-airflow-amazon-mwaa.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-sagemaker-ai](<https://devfeed.tech/tags/amazon-sagemaker-ai.md>), [amazon-sns](<https://devfeed.tech/tags/amazon-sns.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [etl-pipelines](<https://devfeed.tech/tags/etl-pipelines.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

This tutorial demonstrates an AWS architecture for monitoring ETL pipelines orchestrated by Amazon MWAA. It streams CloudWatch logs into Amazon OpenSearch Service, where an MCP server on Amazon Bedrock AgentCore lets engineers query logs in natural language and receive root-cause analysis and remediation guidance.

### Source excerpt

Troubleshooting a multi-service, MWAA-orchestrated ETL pipeline often means hunting across scattered Amazon CloudWatch log groups. This post shows how to centralize your ETL logs in Amazon OpenSearch Service and query them in plain language through an MCP server on Amazon Bedrock AgentCore, so you find root causes faster.

## Amagi's intelligent media operations with Amazon Neptune

DevFeed: [Amagi's intelligent media operations with Amazon Neptune](<https://devfeed.tech/articles/amagi-s-intelligent-media-operations-with-amazon-neptune-65160.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/database/amagis-intelligent-media-operations-with-amazon-neptune/>)

Author: Ajith N N

Published: 2026-10-05T15:24:12Z

Content type: article

Language: en

Sources: [AWS Database Blog](<https://devfeed.tech/sources/aws-database-blog.md>)

Topics: [RDF (Resource Description Framework)](<https://devfeed.tech/topics/rdf.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [cephfs](<https://devfeed.tech/topics/cephfs.md>)

Tags: [amazon-neptune](<https://devfeed.tech/tags/amazon-neptune.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [rdf](<https://devfeed.tech/tags/rdf.md>), [synchronization](<https://devfeed.tech/tags/synchronization.md>)

### AI overview

Amagi built a Global Metadata Store on Amazon Neptune to manage deeply connected media metadata across its operations. The article explains how it synchronizes anonymous RDF blank nodes with Amazon OpenSearch Service, routing deep graph queries to Neptune and high-volume reads to the search index. It reports sub-500 ms transactional reads and describes the eventual consistency trade-off for indexed data.

### Source excerpt

Amagi built a Global Metadata Store on Amazon Neptune to model billions of interconnected media metadata relationships. Learn how their RDF knowledge graph, paired with Amazon OpenSearch Service and a custom blank-node synchronization layer, delivers deep semantic queries and sub-500ms transactional reads across 2,500+ channels and 150+ countries.

## Get to know OpenSearch 3.9

DevFeed: [Get to know OpenSearch 3.9](<https://devfeed.tech/articles/get-to-know-opensearch-3-9-62308.md>)

Original publisher: [Read original article](<https://opensearch.org/blog/get-to-know-opensearch-3-9/>)

Author: James McIntyre

Published: 2026-09-29T23:26:03Z

Content type: release

Language: en

Sources: [OpenSearch](<https://devfeed.tech/sources/opensearch.md>)

Topics: [opensearch](<https://devfeed.tech/topics/opensearch.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>)

Tags: [alert](<https://devfeed.tech/tags/alert.md>), [blog](<https://devfeed.tech/tags/blog.md>), [compression](<https://devfeed.tech/tags/compression.md>), [concurrency](<https://devfeed.tech/tags/concurrency.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [observability](<https://devfeed.tech/tags/observability.md>), [releases](<https://devfeed.tech/tags/releases.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

OpenSearch 3.9 introduces a native engine for neural sparse approximate nearest neighbor search, additional vector storage and compression options, and dynamic mapping for vector fields. The release also adds observability features, including unified alert and anomaly triage, PromQL dashboards, no-code alert rules, and adaptive cluster concurrency limits.

### Source excerpt

OpenSearch 3.9 accelerates vector search with a native neural sparse engine and new compression options, brings alerts, anomalies, and forecasts into one unified view, and protects clusters with adaptive concurrency limits and index-level search pruning. The release also advances the OpenSearch Observability Stack with redesigned trace details, reusable PromQL dashboards, and no-code alert rules. The post Get to know OpenSearch 3.9 appeared first on OpenSearch.

## How Condé Nast built multimodal video discovery with Amazon Bedrock

DevFeed: [How Condé Nast built multimodal video discovery with Amazon Bedrock](<https://devfeed.tech/articles/how-conde-nast-built-multimodal-video-discovery-with-amazon-bedrock-62127.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-conde-nast-built-multimodal-video-discovery-with-amazon-bedrock/>)

Author: Mariah Miller

Published: 2026-09-29T15:55:17Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>)

### AI overview

Condé Nast's editorial teams spent an average of 250 minutes per task searching a library of more than 140,000 videos through titles and descriptions. The company built a multimodal discovery solution using Amazon Bedrock and Amazon OpenSearch Service, reducing search time to under two minutes per task.

### Source excerpt

Condé Nast's editorial teams spent an average of 250 minutes per task searching a library of more than 140,000 videos using only titles and descriptions. Working with the AWS Generative AI Innovation Center, they built a multimodal video discovery solution on Amazon Bedrock and Amazon OpenSearch Service that cut discovery time to under 2 minutes.

## Selecting a vector store for Amazon Bedrock Knowledge Bases

DevFeed: [Selecting a vector store for Amazon Bedrock Knowledge Bases](<https://devfeed.tech/articles/selecting-a-vector-store-for-amazon-bedrock-knowledge-bases-42134.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/selecting-a-vector-store-for-amazon-bedrock-knowledge-bases/>)

Author: Deepak Dalakoti

Published: 2026-09-17T15:53:13Z

Content type: comparison

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [PostgreSQL](<https://devfeed.tech/topics/postgresql.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [cost](<https://devfeed.tech/tags/cost.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [rag](<https://devfeed.tech/tags/rag.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

This comparison explains how to choose a customer-managed vector store for Amazon Bedrock Knowledge Bases RAG applications. It evaluates Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvector, and Amazon S3 Vectors across three RAG use cases, focusing on performance, cost, benchmarks, and practical selection criteria.

### Source excerpt

Choosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost. This post compares Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvector, and Amazon S3 Vectors across three RAG use cases, with benchmarks and a practical selection framework.

## Unified Knowledge Graph RAG on AWS: GraphRAG and LightRAG on one stack

DevFeed: [Unified Knowledge Graph RAG on AWS: GraphRAG and LightRAG on one stack](<https://devfeed.tech/articles/unified-knowledge-graph-rag-on-aws-graphrag-and-lightrag-on-one-stack-21545.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/opensource/unified-knowledge-graph-rag-on-aws-graphrag-and-lightrag-on-one-stack/>)

Author: Jonas Kim

Published: 2026-09-14T16:55:58Z

Content type: article

Language: en

Sources: [AWS Open Source Blog](<https://devfeed.tech/sources/aws-open-source-blog.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>)

Tags: [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [aws](<https://devfeed.tech/tags/aws.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This article presents a unified knowledge-graph RAG stack that brings Microsoft GraphRAG and HKUDS LightRAG together on Amazon Bedrock, Amazon Neptune, and Amazon OpenSearch Service. The shared stack supports common ingestion, indexing, caching, and multilingual handling while allowing the retrieval methodology to be selected per query.

### Source excerpt

Picture a compliance analyst staring at a few thousand contracts, amendments, and internal memos, trying to answer one question that sounds straightforward: "Which of our obligations are exposed if this one milestone slips?" The answer isn't written in any single document. It's stitched across three -- a master agreement that ties a payment to a [...]

## A visual guide to troubleshooting search performance using Query Insights dashboards

DevFeed: [A visual guide to troubleshooting search performance using Query Insights dashboards](<https://devfeed.tech/articles/a-visual-guide-to-troubleshooting-search-performance-using-query-insights-dashboards-12783.md>)

Original publisher: [Read original article](<https://opensearch.org/blog/a-visual-guide-to-troubleshooting-search-performance-using-query-insights-dashboards/>)

Author: Chenyang Ji

Published: 2026-09-04T20:11:52Z

Content type: tutorial

Language: en

Sources: [OpenSearch](<https://devfeed.tech/sources/opensearch.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [cpu](<https://devfeed.tech/topics/cpu.md>)

Tags: [blog](<https://devfeed.tech/tags/blog.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [index](<https://devfeed.tech/tags/index.md>), [latency](<https://devfeed.tech/tags/latency.md>), [memory](<https://devfeed.tech/tags/memory.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [navigation](<https://devfeed.tech/tags/navigation.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [performance](<https://devfeed.tech/tags/performance.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [technical](<https://devfeed.tech/tags/technical.md>), [troubleshooting](<https://devfeed.tech/tags/troubleshooting.md>), [view](<https://devfeed.tech/tags/view.md>), [visualization](<https://devfeed.tech/tags/visualization.md>)

### AI overview

A visual guide to using OpenSearch Query Insights dashboards to investigate slow searches and unexpected resource usage. It covers the Live Queries and Top N Queries views, interactive visualizations, configuration, and metrics such as latency, CPU, and memory.

### Source excerpt

OpenSearch Query Insights dashboards provide interactive visualizations for monitoring live queries, analyzing top N query performance, and viewing individual query details. This post explores each visualization and shows how to use visualizations to troubleshoot search performance issues. The post A visual guide to troubleshooting search performance using Query Insights dashboards appeared first on OpenSearch.

## Observing and evaluating production agents using OpenSearch Agent Health

DevFeed: [Observing and evaluating production agents using OpenSearch Agent Health](<https://devfeed.tech/articles/observing-and-evaluating-production-agents-using-opensearch-agent-health-49923.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/observing-and-evaluating-production-agents-using-opensearch-agent-health/>)

Author: Ulrich Hinze

Published: 2026-09-01T16:19:02Z

Content type: tutorial

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [observability](<https://devfeed.tech/topics/observability.md>), [tracing](<https://devfeed.tech/topics/tracing.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Strands Agents](<https://devfeed.tech/topics/strands-agents.md>), [Server-sent events (SSE)](<https://devfeed.tech/topics/server-sent-events-sse.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [aws](<https://devfeed.tech/tags/aws.md>), [evals](<https://devfeed.tech/tags/evals.md>), [integration](<https://devfeed.tech/tags/integration.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production-ai](<https://devfeed.tech/tags/production-ai.md>), [run](<https://devfeed.tech/tags/run.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

A tutorial on observing and evaluating production AI agents with OpenSearch Agent Health. It explains how to deploy an AWS-based agent and observability pipeline, inspect OpenTelemetry traces, and run evaluations to measure agent quality over time.

### Source excerpt

Learn how to observe and evaluate production AI agents by combining an agent running on AWS with OpenSearch Agent Health. This post walks through deploying an agent and its observability pipeline to AWS, then using Agent Health to explore traces and run evaluations that measure and improve agent quality over time.

[Next page](<https://devfeed.tech/topics/amazon-opensearch-service.md?cursor=WyIyMDI2LTA5LTAxVDE2OjE5OjAyKzAwOjAwIiwgIjBjZTZlNDc5LTlkNmMtNDJlNS04ZGQ4LWM5MDM1Nzg1MTcyMSJd>)