# Amazon Bedrock Knowledge Bases

Amazon Bedrock Knowledge Bases is an AWS service for integrating proprietary data into generative-AI applications through retrieval-augmented generation, with managed or customer-managed ingestion, indexing, storage, and retrieval infrastructure.

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

## OVHcloud AI Summit 2026: 55 launches to take AI into production

DevFeed: [OVHcloud AI Summit 2026: 55 launches to take AI into production](<https://devfeed.tech/articles/ovhcloud-ai-summit-2026-55-launches-to-take-ai-into-production-144298.md>)

Original publisher: [Read original article](<https://blog.ovhcloud.com/en/posts/ai-summit-2026-announcements/>)

Author: OVHcloud Team

Published: 2026-11-19T06:30:00Z

Content type: article

Language: en

Sources: [OVHcloud Blog](<https://devfeed.tech/sources/ovhcloud-blog.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [The Three Main Cloud Service Models](<https://devfeed.tech/topics/the-three-main-cloud-service-models.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Internationalization (i18n)](<https://devfeed.tech/topics/i18n.md>), [OpenAPI Specification](<https://devfeed.tech/topics/openapi.md>)

Tags: [17](<https://devfeed.tech/tags/17.md>), [2026](<https://devfeed.tech/tags/2026.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [act](<https://devfeed.tech/tags/act.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-platform](<https://devfeed.tech/tags/agentic-platform.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-act](<https://devfeed.tech/tags/ai-act.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [launches](<https://devfeed.tech/tags/launches.md>), [ovhcloud](<https://devfeed.tech/tags/ovhcloud.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [production](<https://devfeed.tech/tags/production.md>), [summit](<https://devfeed.tech/tags/summit.md>), [workspace](<https://devfeed.tech/tags/workspace.md>)

### AI overview

OVHcloud announced 55 launches at its 19 November 2026 AI Summit: 38 across cloud foundations and 17 spanning the AI stack. The excerpt emphasizes private networking and security features intended to support production workloads, alongside GPUs, orchestration, inference routing, agents, search, and applications. Olala 1.0 mini 7A1B is an open model with 7 billion parameters and 1 billion active per request; OVHcloud says it can run on an 8 GB GPU or a standard CPU and plans to release it under Apache 2.0. OVHai Workspace combines productivity, website creation, and company-data search; its free alpha launched in France with 5 GB per user, European data hosting, and a commitment not to use customer data for model training. These details describe the supplied excerpt, not necessarily all 55 launches.

### Source excerpt

Olala, OVHai Workspace, GPUs, and AI agents: discover the 55 launches from the OVHcloud AI Summit 2026, and the ones you can try right now.

## Design responsible AI controls for Amazon Aurora PostgreSQL

DevFeed: [Design responsible AI controls for Amazon Aurora PostgreSQL](<https://devfeed.tech/articles/design-responsible-ai-controls-for-amazon-aurora-postgresql-141279.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/design-responsible-ai-controls-for-amazon-aurora-postgresql/>)

Author: InduTeja Aligeti

Published: 2026-11-18T21:38:22Z

Content type: article

Language: en

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

Topics: [Amazon Aurora](<https://devfeed.tech/topics/amazon-aurora.md>), [responsible-ai](<https://devfeed.tech/topics/responsible-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [audit](<https://devfeed.tech/topics/audit.md>), [API Logging](<https://devfeed.tech/topics/api-logging.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-aurora](<https://devfeed.tech/tags/amazon-aurora.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-guardrails](<https://devfeed.tech/tags/amazon-bedrock-guardrails.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [controls](<https://devfeed.tech/tags/controls.md>), [design](<https://devfeed.tech/tags/design.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [logging](<https://devfeed.tech/tags/logging.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [rag](<https://devfeed.tech/tags/rag.md>), [responsible-ai](<https://devfeed.tech/tags/responsible-ai.md>), [sources](<https://devfeed.tech/tags/sources.md>), [sql](<https://devfeed.tech/tags/sql.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

The article details an Explainability design for a customer-support RAG chatbot using Aurora PostgreSQL, pgvector, Aurora ML, and Amazon Bedrock. It embeds documents and queries with the same Titan Text Embeddings V2 model, retrieves tenant-scoped chunks by cosine similarity, applies Bedrock Guardrails for privacy and contextual grounding, and logs retrieved chunk IDs, scores, actually cited sources, guardrail traces, and model ID in SQL. It stresses protecting interaction logs with PII redaction or encryption and row-level security, and archiving records to S3 before purging. Amazon Bedrock Knowledge Bases is presented as a simpler option when its default retrieval and citations suffice; custom logging suits cases needing provenance in a user-managed schema. Limitations include guardrail latency and charges, approximate HNSW search that may return fewer results after filtering, grounding that does not verify source-document accuracy, and synchronous embedding generation for large ingestions.

### Source excerpt

Learn how to make RAG chatbot answers traceable with Amazon Aurora PostgreSQL, pgvector, and Amazon Bedrock Guardrails, logging sources, scores, and guardrail traces in SQL.

## Add your organization's runbooks and policies using Retrieval Augmented Generation (RAG) on Amazon Aurora PostgreSQL

DevFeed: [Add your organization's runbooks and policies using Retrieval Augmented Generation (RAG) on Amazon Aurora PostgreSQL](<https://devfeed.tech/articles/add-your-organization-s-runbooks-and-policies-using-retrieval-augmented-generation-rag-on-amazon-aurora-postgresql-138650.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/database/add-your-organizations-runbooks-and-policies-using-retrieval-augmented-generation-rag-on-amazon-aurora-postgresql/>)

Author: Narendra Tawar

Published: 2026-11-17T19:43:40Z

Content type: tutorial

Language: en

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

Topics: [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Amazon Aurora](<https://devfeed.tech/topics/amazon-aurora.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [amazon-aurora](<https://devfeed.tech/tags/amazon-aurora.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [kiro](<https://devfeed.tech/tags/kiro.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [policies](<https://devfeed.tech/tags/policies.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation-rag](<https://devfeed.tech/tags/retrieval-augmented-generation-rag.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

The walkthrough connects a Kiro DBA assistant to team runbooks and policies using Amazon Bedrock Knowledge Bases, Amazon S3, and Aurora PostgreSQL with pgvector. Bedrock chunks documents, creates Titan Text Embeddings V2 vectors, and stores them with text in Aurora; at query time, the Retrieval MCP server returns relevant chunks for the assistant to ground its recommendations. Setup requires Aurora PostgreSQL 15.4 or later, pgvector, the RDS Data API, and appropriate Bedrock, S3, and Secrets Manager access. The Knowledge Base needs the `mcp-multirag-kb=true` tag for automatic MCP discovery. For structured policies, section-based custom chunking may improve retrieval precision over default chunking. In the example, retrieval surfaces required peer review, CAB approval, and a manual snapshot before schema changes, while suggesting reader-endpoint traffic redirection as an immediate mitigation. The article also stresses that steering files are soft guardrails; read-only database permissions and IAM deny policies provide additional write protection. Re-sync documents as they change, and restrict `bedrock:Retrieve` access to protect sensitive runbooks.

### Source excerpt

In Part 2 of this series, you connect your Kiro DBA assistant to your team's runbooks and policies. Store runbooks in Amazon S3, index them with Amazon Bedrock Knowledge Bases on Amazon Aurora PostgreSQL using pgvector, and wire up retrieval so the assistant grounds its recommendations in your own documentation.

## Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base

DevFeed: [Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base](<https://devfeed.tech/articles/build-memory-aware-ai-agents-with-agentic-retrieve-on-amazon-bedrock-managed-knowledge-base-136362.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/build-memory-aware-ai-agents-with-agentic-retrieve-on-amazon-bedrock-managed-knowledge-base/>)

Author: Peng Yang

Published: 2026-11-16T22:43:30Z

Content type: tutorial

Language: en

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

Topics: [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [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-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [base](<https://devfeed.tech/tags/base.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [build](<https://devfeed.tech/tags/build.md>), [call](<https://devfeed.tech/tags/call.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [managed](<https://devfeed.tech/tags/managed.md>), [memory](<https://devfeed.tech/tags/memory.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Adding `memoryConfiguration` to `AgenticRetrieveStream` lets Amazon Bedrock Managed Knowledge Base restore a conversation, retrieve relevant AgentCore memory, use it to shape knowledge-base searches, and persist the question and answer in the same call. The example uses Cognito's verified email for ACL filtering and stable `sub` for per-user memory identity; IAM session tags and condition keys add defense against cross-user access. Memory summaries capture conversation facts, while preference strategies capture stated response preferences. Memory retrieval is planner-selected, and long-term extraction is asynchronous, so new facts may not be available immediately. Memory failures are best-effort: the trace reports the failure and the answer can continue from the knowledge base. The walkthrough also notes added session-restore latency and the need to manage deletion of both raw events and extracted records.

### Source excerpt

Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore memory now store conversations, extract facts, and bring long-term memory into a single AgenticRetrieveStream call. This post shows how to build a memory-aware, multi-user assistant where each user sees only the documents they may read and each user's memory stays private.

## Get answers from tables with tabular search in Amazon Bedrock Managed Knowledge Base

DevFeed: [Get answers from tables with tabular search in Amazon Bedrock Managed Knowledge Base](<https://devfeed.tech/articles/get-answers-from-tables-with-tabular-search-in-amazon-bedrock-managed-knowledge-base-136121.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/get-answers-from-tables-with-tabular-search-in-amazon-bedrock-managed-knowledge-base/>)

Author: Josh DeMuth

Published: 2026-11-16T16:12:16Z

Content type: tutorial

Language: en

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

Topics: [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [CSV](<https://devfeed.tech/topics/csv.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>)

Tags: [agentic-retrieval](<https://devfeed.tech/tags/agentic-retrieval.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [atlassian-confluence](<https://devfeed.tech/tags/atlassian-confluence.md>), [aws-cdk](<https://devfeed.tech/tags/aws-cdk.md>), [aws-cli](<https://devfeed.tech/tags/aws-cli.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-sdk](<https://devfeed.tech/tags/aws-sdk.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [bi](<https://devfeed.tech/tags/bi.md>), [bi-tools](<https://devfeed.tech/tags/bi-tools.md>), [csv](<https://devfeed.tech/tags/csv.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [tables](<https://devfeed.tech/tags/tables.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

Amazon Bedrock Managed Knowledge Base tabular search lets agentic retrieval calculate over full CSV and Excel tables and combine those results with retrieved documents in one AgenticRetrieveStream request. It stages original files in an isolated, network-free sandbox, runs model-written code, and returns printed results for the agent's cited answer. In the finance example, it applies policy rules and memo revisions to workbook data to identify departments requiring variance commentary. Plain Retrieve returns passages without running code; tabular search adds an agent turn and latency. It is intended for table lookups and calculations, while governed metrics, recurring dashboards, warehouse-scale joins, and reporting controls remain suited to BI tools. File types, size limits, caller permissions, and retrieval's choice of workbook affect whether it can operate; traces identify files read, but do not expose generated code.

### Source excerpt

Amazon Bedrock Managed Knowledge Base now supports tabular search, so agentic retrieval can answer questions over CSV, XLSX, and XLS files. It looks up values and runs calculations across every relevant row, then combines the results with facts from related documents to answer multi-step analytical questions.

## Customize answers per tenant in Amazon Bedrock Managed Knowledge Base

DevFeed: [Customize answers per tenant in Amazon Bedrock Managed Knowledge Base](<https://devfeed.tech/articles/customize-answers-per-tenant-in-amazon-bedrock-managed-knowledge-base-136120.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/customize-answers-per-tenant-in-amazon-bedrock-managed-knowledge-base/>)

Author: Josh DeMuth

Published: 2026-11-16T15:46:28Z

Content type: tutorial

Language: en

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

Topics: [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [tenant data protection](<https://devfeed.tech/topics/tenant-data-protection.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentic-retrieval](<https://devfeed.tech/tags/agentic-retrieval.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [api](<https://devfeed.tech/tags/api.md>), [audit](<https://devfeed.tech/tags/audit.md>), [aws-cdk](<https://devfeed.tech/tags/aws-cdk.md>), [aws-cloudtrail](<https://devfeed.tech/tags/aws-cloudtrail.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [brand-voice](<https://devfeed.tech/tags/brand-voice.md>), [iam](<https://devfeed.tech/tags/iam.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [managed](<https://devfeed.tech/tags/managed.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

Amazon Bedrock Managed Knowledge Base retrieval instructions let each request apply tenant-specific voice, answer format, retrieval guidance, and answer policy through a managed, versioned resource. A backend can select an instruction version and metadata filter from the authenticated tenant, add a tenant-identifying line, and call AgenticRetrieveStream; one instruction can apply across as many as five knowledge bases. Instructions do not enforce data isolation or authorization, so use server-built metadata filters or separate knowledge bases, and scope IAM permissions when tenants use separate credentials. Filters require accurate document metadata; separate knowledge bases add resources to maintain and pay for. Policies are best effort, and output formats should be validated when code depends on them. Pin versions per tenant to canary, promote, or roll back changes; traces report the applied instruction ID and version, while CloudTrail can record calls when data events are enabled.

### Source excerpt

Retrieval instructions in Amazon Bedrock Managed Knowledge Base set the voice, format, retrieval guidance, and answer policy for each tenant on shared knowledge bases. This post shows how to give each tenant its own answers, keep tenant data apart with metadata filters, scope access with IAM tags, and roll out changes one tenant at a time.

## Article: Governed Autonomous Intelligence for Mission-Critical Utility

DevFeed: [Article: Governed Autonomous Intelligence for Mission-Critical Utility](<https://devfeed.tech/articles/article-governed-autonomous-intelligence-for-mission-critical-utility-135325.md>)

Original publisher: [Read original article](<https://www.infoq.com/articles/utility-governed-autonomous-intelligence-ai/>)

Author: Purnang Borah

Published: 2026-11-16T11:00:00Z

Content type: article

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [human-in-the-loop UX](<https://devfeed.tech/topics/human-in-the-loop-ux.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [audit](<https://devfeed.tech/topics/audit.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-architecture](<https://devfeed.tech/tags/agentic-ai-architecture.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-architecture](<https://devfeed.tech/tags/ai-architecture.md>), [application-performance-management](<https://devfeed.tech/tags/application-performance-management.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [article](<https://devfeed.tech/tags/article.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [audit](<https://devfeed.tech/tags/audit.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [aws](<https://devfeed.tech/tags/aws.md>), [but](<https://devfeed.tech/tags/but.md>), [control](<https://devfeed.tech/tags/control.md>), [covers](<https://devfeed.tech/tags/covers.md>), [critical](<https://devfeed.tech/tags/critical.md>), [enterprise-architecture](<https://devfeed.tech/tags/enterprise-architecture.md>), [execution](<https://devfeed.tech/tags/execution.md>), [gate](<https://devfeed.tech/tags/gate.md>), [governance](<https://devfeed.tech/tags/governance.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [mission](<https://devfeed.tech/tags/mission.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [observability](<https://devfeed.tech/tags/observability.md>), [operating-systems](<https://devfeed.tech/tags/operating-systems.md>), [operational-intelligence](<https://devfeed.tech/tags/operational-intelligence.md>), [operations-management](<https://devfeed.tech/tags/operations-management.md>), [performance](<https://devfeed.tech/tags/performance.md>), [utility](<https://devfeed.tech/tags/utility.md>), [utility-governed-autonomous-intelligence-ai](<https://devfeed.tech/tags/utility-governed-autonomous-intelligence-ai.md>)

### AI overview

The architecture keeps AI reasoning separate from production authority: agents correlate signals, retrieve runbooks, assess business impact, and propose remediation, while a deterministic, versioned action catalog sets risk and approval requirements. A governed tool gateway is the sole execution path, enforcing least privilege, checking authorization and approvals, validating arguments, recording evidence, and supporting post-action health checks. Prediction carries evidence and confidence but grants no authority. The AWS reference uses Bedrock AgentCore, Bedrock Knowledge Bases, and MCP; Azure and Google Cloud equivalents are also described, with some Azure governance features noted as preview. The platform can support compliance evidence but does not itself establish compliance. Autonomy starts read-only and expands by action class based on operational and governance evidence, with revocation available.

### Source excerpt

The article describes an architecture for agentic AI in regulated utility operations. Agents reason and propose actions, but a deterministic policy gate and a governed tool gateway control execution, with human approval where required. It covers an AWS reference implementation, grounding in runbooks, governed prediction, outcome validation, audit evidence, and phased autonomy. By Purnang Borah

## Tabular Population Priors as Structured Retrieval for EHR Medication Set Prediction

DevFeed: [Tabular Population Priors as Structured Retrieval for EHR Medication Set Prediction](<https://devfeed.tech/articles/tabular-population-priors-as-structured-retrieval-for-ehr-medication-set-prediction-135057.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17341>)

Author: Animesh Agarwal, Meysam Ghaffari, Nina Fatehi, Carlos Morato

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

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

Topics: [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [Structured-data](<https://devfeed.tech/topics/structured-data.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [aggregate](<https://devfeed.tech/tags/aggregate.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [set](<https://devfeed.tech/tags/set.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

For fixed-vocabulary EHR medication prediction, a population prior built from sparse condition-medication co-occurrences may provide more task-aligned retrieval than retrieving similar patient records. In a PACERAG pipeline, replacing only the patient retriever with ranked medication-class candidates raised F1 from 0.303 to 0.338 and Jaccard from 0.218 to 0.237 across 1,004 held-out MIMIC-IV admissions. The swap required no additional LLM calls or inference-time patient index. A non-LLM top-k baseline reached F1 0.248. These results are limited to the reported evaluation.

### Source excerpt

arXiv:2611.17341v1 Announce Type: new Abstract: Medication prediction from electronic health records is a fixed vocabulary structured prediction problem, yet recent clinical RAG systems often treat it like open ended case based reasoning: retrieve similar patient admissions and ask an LLM to infer a medication set. This retrieval object is indirect the model receives retrieved patient records while the target is a discrete set of medication class labels. We propose a more task aligned retrieval object: a tabular population prior ranked medication class candidates from a sparse condition medication co occurrence table estimated from training admissions. Using PACERAG as a fixed downstream pipeline and replacing only its patient retriever, this drop in swap improves F1 from 0.303 to 0.338 (+11.5% relative) and Jaccard from 0.218 to 0.237 on 1,004 heldout MIMIC IV admissions, with no additional LLM calls and no inference time patient index. A non LLM top k baseline reaches F1=0.248, confirming the prior is predictive before LLM integration. Aggregate population statistics can provide a more task aligned, efficient, and auditable retrieval source than patient level nearest neighbors for fixed vocabulary EHR set prediction.

## Build a self-healing ETL pipeline with Amazon Bedrock AgentCore

DevFeed: [Build a self-healing ETL pipeline with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/build-a-self-healing-etl-pipeline-with-amazon-bedrock-agentcore-133386.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/build-a-self-healing-etl-pipeline-with-amazon-bedrock-agentcore/>)

Author: Kevin Tinn

Published: 2026-11-13T19:08:10Z

Content type: tutorial

Language: en

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

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [etl](<https://devfeed.tech/topics/etl.md>), [AWS Glue](<https://devfeed.tech/topics/aws-glue.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [data lake](<https://devfeed.tech/topics/data-lake.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [aws-sns](<https://devfeed.tech/topics/aws-sns.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-glue](<https://devfeed.tech/tags/aws-glue.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [build](<https://devfeed.tech/tags/build.md>), [can](<https://devfeed.tech/tags/can.md>), [data](<https://devfeed.tech/tags/data.md>), [data-lake](<https://devfeed.tech/tags/data-lake.md>), [domain](<https://devfeed.tech/tags/domain.md>), [errors](<https://devfeed.tech/tags/errors.md>), [etl](<https://devfeed.tech/tags/etl.md>), [etl-pipeline](<https://devfeed.tech/tags/etl-pipeline.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [self-healing](<https://devfeed.tech/tags/self-healing.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The described AWS Glue pipeline routes records that fail schema validation to a four-agent system on Amazon Bedrock AgentCore. A correction agent queries a Bedrock Knowledge Base for domain guidance and looks up precomputed strategies in S3 Vectors in parallel, selecting the higher-confidence result. At the default 0.7 threshold, it applies qualifying corrections; otherwise, the orchestrator sends an SNS alert for human review. A persistence agent writes corrected records to both corrected and transformed data lake zones. The sample annotates records with the chosen strategy rather than changing field values; direct transformations require extending its correction function. With repository credentials configured, a remediation agent can analyze the source error and open a GitHub pull request; without them, that step is skipped. The post outlines AWS CDK deployment and sample-data workflow, and notes required AWS services, model access, Python 3.10+, and a container runtime for local testing.

### Source excerpt

Build a self-healing ETL pipeline on AWS Glue and Amazon Bedrock AgentCore that automatically corrects bad records using domain knowledge, writes the fixes back to the data lake, and can open pull requests to prevent the same errors from recurring.

## How Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore

DevFeed: [How Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/how-natera-designed-an-agentic-ai-system-for-lab-ops-with-amazon-bedrock-agentcore-130935.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-natera-designed-an-agentic-ai-system-for-lab-ops-with-amazon-bedrock-agentcore/>)

Author: Ariel Jirau

Published: 2026-11-12T21:47:07Z

Content type: tutorial

Language: en

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

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automated](<https://devfeed.tech/tags/automated.md>), [base](<https://devfeed.tech/tags/base.md>), [construction](<https://devfeed.tech/tags/construction.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [faster](<https://devfeed.tech/tags/faster.md>), [first](<https://devfeed.tech/tags/first.md>), [full](<https://devfeed.tech/tags/full.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [lab](<https://devfeed.tech/tags/lab.md>), [ops](<https://devfeed.tech/tags/ops.md>)

### AI overview

Natera's SWARM system uses Amazon Bedrock AgentCore to turn lab operations knowledge into ticket diagnostics, cutting average first response from 17.4 hours to about 8 minutes and generating reports for 96.2% of incoming tickets before engineer review. It separates autonomous ticket analysis from interactive engineer sessions, with both runtimes sharing a versioned library of 33 independently testable skills. Jira tickets flow through EventBridge, SQS, and Lambda; diagnostics retrieve from a knowledge base built from vendor manuals, historical tickets, and operational data. Natera emphasizes data quality, reporting that adding missing manuals raised one instrument family's accuracy from 71% to 75% without model changes. Its controls include short-lived OIDC/STS deployment credentials, least-privilege IAM, private networking, audit logging, and excluding patient-identifiable information from the index and model. A continuous engineer-verified evaluation loop grades responses by instrument family. The reported results are based on a 90-day production evaluation; only 269 of 524 evaluated tickets had confidence labels and verified resolutions for accuracy comparisons.

### Source excerpt

Natera built SWARM, an agentic AI system on Amazon Bedrock AgentCore that captures institutional lab-operations knowledge and deploys it at scale. This post walks through the full architecture, from knowledge base construction to deployment and evaluation, delivering about 130x faster first response and 96.2% automated coverage across support tickets.

## Inside an enterprise AI agent: A governed, observable loop architecture

DevFeed: [Inside an enterprise AI agent: A governed, observable loop architecture](<https://devfeed.tech/articles/inside-an-enterprise-ai-agent-a-governed-observable-loop-architecture-132421.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/inside-an-enterprise-ai-agent-a-governed-observable-loop-architecture/>)

Author: Rushabh Lokhande

Published: 2026-11-12T19:31:28Z

Content type: article

Language: en

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

Topics: [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [set up event-driven architecture AWS](<https://devfeed.tech/topics/set-up-event-driven-architecture-aws.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-runtime](<https://devfeed.tech/tags/agent-runtime.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [api](<https://devfeed.tech/tags/api.md>), [api-gateway](<https://devfeed.tech/tags/api-gateway.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [avoid](<https://devfeed.tech/tags/avoid.md>), [aws](<https://devfeed.tech/tags/aws.md>), [control](<https://devfeed.tech/tags/control.md>), [cross](<https://devfeed.tech/tags/cross.md>), [design](<https://devfeed.tech/tags/design.md>), [design-patterns](<https://devfeed.tech/tags/design-patterns.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [enterprise-ai-agents](<https://devfeed.tech/tags/enterprise-ai-agents.md>), [inside](<https://devfeed.tech/tags/inside.md>), [observable](<https://devfeed.tech/tags/observable.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

The article presents a five-layer AWS reference architecture for enterprise agents: an API gateway enforces identity and policy; a five-phase runtime understands, plans, retrieves, reasons, then acts and observes; knowledge and state provide RAG, memory, and session data; platform services supply models, tools, secrets, and events; and trust controls and governance span the system. Every tool call passes permission, input, policy, rate, and budget checks, while destructive actions can require approval. Step-level traces capture execution paths, tool status, latency, and token use; output gates check safety, groundedness, confidence, and human approval for high-risk actions. Recommended safeguards include least privilege, read-only starts with graduated autonomy, explicit tool schemas, model routing by task, and hard limits on iterations, time, and tokens with escalation paths. AWS service mappings are starting points to tune for workload, residency, latency, and cost; the article notes compliance remains the customer's responsibility under AWS's shared responsibility model.

### Source excerpt

This post lays out a five-layer reference architecture for governed, observable enterprise AI agents on AWS: an API gateway, a five-phase agent runtime, a knowledge and state tier, platform services, and a cross-cutting trust and control framework. Each layer maps to managed AWS services, with the design patterns worth copying and the mistakes to avoid.

## Migrate to Amazon Bedrock Managed Knowledge Base with your coding agent

DevFeed: [Migrate to Amazon Bedrock Managed Knowledge Base with your coding agent](<https://devfeed.tech/articles/migrate-to-amazon-bedrock-managed-knowledge-base-with-your-coding-agent-130564.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/migrate-to-amazon-bedrock-managed-knowledge-base-with-your-coding-agent/>)

Author: Josh DeMuth

Published: 2026-11-12T16:16:45Z

Content type: article

Language: en

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

Topics: [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [base](<https://devfeed.tech/tags/base.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [customer](<https://devfeed.tech/tags/customer.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [guide](<https://devfeed.tech/tags/guide.md>), [helps](<https://devfeed.tech/tags/helps.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [infrastructure-as-code](<https://devfeed.tech/tags/infrastructure-as-code.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [managed](<https://devfeed.tech/tags/managed.md>), [migrate](<https://devfeed.tech/tags/migrate.md>), [migration](<https://devfeed.tech/tags/migration.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The migration guide helps move a customer-managed Amazon Bedrock knowledge base to a Managed Knowledge Base while keeping the original available for rollback. A coding agent first performs read-only discovery and produces a reviewable configuration map and plan; with explicit approval it can create the replacement and data sources alongside the original, or write a migrated IaC template. Ingestion, application updates, and cutover remain the team's responsibility. Managed Knowledge Base runs storage, indexing, and retrieval, with automatic scaling and hybrid search; it also offers connectors, ACL-aware retrieval, and agentic retrieval. This trades direct control of the vector store for managed operations and usage-based storage and retrieval charges. Applications must target the new ID and use `managedSearchConfiguration`; managed retrieval has no search-type override and does not support the `startsWith` or `stringContains` metadata filters. Before cutover, sync data, grant runtime access, compare representative queries while accounting for differing score scales and result formats, and retain the original through the rollback period.

### Source excerpt

The migration guide in the amazon-bedrock skill helps you migrate a customer-managed Amazon Bedrock knowledge base to a Managed Knowledge Base. Your coding agent plans the move with read-only discovery, creates the new knowledge base or an infrastructure-as-code template alongside the original, and validates retrieval before you cut over.

## Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools

DevFeed: [Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools](<https://devfeed.tech/articles/fine-grained-access-control-for-amazon-bedrock-managed-knowledge-base-tools-130562.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/fine-grained-access-control-for-amazon-bedrock-managed-knowledge-base-tools/>)

Author: Renya Kujirada

Published: 2026-11-12T15:40:24Z

Content type: article

Language: en

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

Topics: [Access Control](<https://devfeed.tech/topics/access-control.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [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-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [base](<https://devfeed.tech/tags/base.md>), [based](<https://devfeed.tech/tags/based.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [control](<https://devfeed.tech/tags/control.md>), [fine](<https://devfeed.tech/tags/fine.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [identity](<https://devfeed.tech/tags/identity.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [managed](<https://devfeed.tech/tags/managed.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The design keeps a shared agent from choosing whose documents it searches: a gateway interceptor overwrites the MCP tool's `userContext` with the email from a JWT validated by the gateway, and Managed Knowledge Base ACL awareness filters results to that user's permitted documents. ACL awareness trusts the supplied identity, so it is not authorization by itself. Policy in AgentCore can independently deny calls when the injected user ID does not match the JWT email; a knowledge base resource policy can also restrict `Retrieve` and `GetDocumentContent` to the gateway execution role, blocking direct calls and other principals. These defenses have limits: the resource policy cannot distinguish another gateway using the same role, and explicit denial can affect other consumers. The sample requires a verified email claim; Cognito token customization needs the Essentials or Plus plan. S3 ACL updates apply after sync, and ACL mistakes silently omit documents.

### Source excerpt

Learn how to expose an Amazon Bedrock Managed Knowledge Base to AI agents as MCP tools through Amazon Bedrock AgentCore Gateway while keeping per-user access control. A request interceptor injects verified identity, Policy in AgentCore validates it independently, and a resource-based policy restricts direct access to the knowledge base.

## Build a data foundation for agentic AI on AWS: From lakehouse to MCP

DevFeed: [Build a data foundation for agentic AI on AWS: From lakehouse to MCP](<https://devfeed.tech/articles/build-a-data-foundation-for-agentic-ai-on-aws-from-lakehouse-to-mcp-129558.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/build-a-data-foundation-for-agentic-ai-on-aws-from-lakehouse-to-mcp/>)

Author: Adrien Lebret

Published: 2026-11-11T21:03:43Z

Content type: article

Language: en

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

Topics: [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [AWS Glue](<https://devfeed.tech/topics/aws-glue.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [databricks](<https://devfeed.tech/topics/databricks.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-data](<https://devfeed.tech/tags/ai-data.md>), [aws](<https://devfeed.tech/tags/aws.md>), [build](<https://devfeed.tech/tags/build.md>), [building](<https://devfeed.tech/tags/building.md>), [context](<https://devfeed.tech/tags/context.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [data](<https://devfeed.tech/tags/data.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [governance](<https://devfeed.tech/tags/governance.md>), [interoperability](<https://devfeed.tech/tags/interoperability.md>), [lakehouse](<https://devfeed.tech/tags/lakehouse.md>), [like](<https://devfeed.tech/tags/like.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [model](<https://devfeed.tech/tags/model.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>)

### AI overview

The article presents a four-pillar AWS data foundation for agentic AI: a unified lakehouse, context engineering, interoperability, and governance. Amazon SageMaker Lakehouse and S3 Tables bring operational, analytical, and AI data into a governed foundation with Apache Iceberg, zero-ETL ingestion, and federated queries. Context engineering combines knowledge bases, short- and long-term memory, and tools that fetch selected data, addressing stateless models' limited context windows. For collaboration, A2A supports agent-to-agent communication over HTTP and JSON, while MCP standardizes agent access to resources, tools, and prompts; Amazon Bedrock AgentCore Gateway centralizes connections, authentication, audit logging, and permission-scoped semantic tool discovery. Amazon SageMaker Data Catalog adds dataset discovery, lineage, quality indicators, and publish-and-subscribe access controls. The article recommends establishing the lakehouse and ingestion first, developing context capabilities before scaling orchestration, and treating governance as an ongoing effort from the start.

### Source excerpt

Building a data foundation ready for agentic AI relies on a unified lakehouse and interoperability protocols like Model Context Protocol (MCP). This post walks through four pillars for building an agentic AI data foundation on AWS: a unified lakehouse, context engineering, multi-agent interoperability, and data governance.

## How DXC Technology built a multi-model AI substrate on Amazon Bedrock

DevFeed: [How DXC Technology built a multi-model AI substrate on Amazon Bedrock](<https://devfeed.tech/articles/how-dxc-technology-built-a-multi-model-ai-substrate-on-amazon-bedrock-129623.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-dxc-technology-built-a-multi-model-ai-substrate-on-amazon-bedrock/>)

Author: Asif Fouzi

Published: 2026-11-11T20:45:45Z

Content type: article

Language: en

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

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Amazon Bedrock Guardrails](<https://devfeed.tech/topics/amazon-bedrock-guardrails.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon EventBridge](<https://devfeed.tech/topics/amazon-eventbridge.md>), [VPC Flow Logs](<https://devfeed.tech/topics/vpc-flow-logs.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>), [Managed Services](<https://devfeed.tech/topics/managed-services.md>), [amazon](<https://devfeed.tech/topics/amazon.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>), [audits](<https://devfeed.tech/tags/audits.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [critical](<https://devfeed.tech/tags/critical.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [harness](<https://devfeed.tech/tags/harness.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [it](<https://devfeed.tech/tags/it.md>), [it-services](<https://devfeed.tech/tags/it-services.md>), [learn](<https://devfeed.tech/tags/learn.md>), [managed](<https://devfeed.tech/tags/managed.md>), [mission](<https://devfeed.tech/tags/mission.md>), [model](<https://devfeed.tech/tags/model.md>), [oasis](<https://devfeed.tech/tags/oasis.md>), [organizations](<https://devfeed.tech/tags/organizations.md>), [scale](<https://devfeed.tech/tags/scale.md>), [substrate](<https://devfeed.tech/tags/substrate.md>), [technology](<https://devfeed.tech/tags/technology.md>)

### AI overview

DXC separates DXC OASIS into a governed model substrate on Amazon Bedrock and a DXC-built harness for orchestration, operational context, policy checks, human approval, and audit trails. Bedrock gives the system one API for Claude, Nova, Llama, and open-weight models, with Guardrails for content and PII controls, PrivateLink for private inference traffic, and regional controls for data residency. The shared API enables workload-based model routing, but the harness evaluates models against task suites before production use because models differ in behavior. Agents start read-only; production changes require recorded approval in the described workflow. DXC reports a 95% average reduction in resolution time across 56 measured use cases and diagnostic accuracy of at least 92%, validated against senior engineers.

### Source excerpt

DXC Technology runs mission-critical managed IT services for regulated organizations across 70 countries. Learn how DXC built DCX OASIS, its Human+AI operating model, on a governed multi-model substrate in Amazon Bedrock, separating a resilient model substrate from a trusted harness that orchestrates, governs, and audits AI agents at scale.

## Accelerating generative AI delivery with reusable assets

DevFeed: [Accelerating generative AI delivery with reusable assets](<https://devfeed.tech/articles/accelerating-generative-ai-delivery-with-reusable-assets-129620.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/accelerating-generative-ai-delivery-with-reusable-assets/>)

Author: Sabine Khan

Published: 2026-11-11T19:19:21Z

Content type: article

Language: en

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

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [assets](<https://devfeed.tech/tags/assets.md>), [aws](<https://devfeed.tech/tags/aws.md>), [catalog](<https://devfeed.tech/tags/catalog.md>), [components](<https://devfeed.tech/tags/components.md>), [delivery](<https://devfeed.tech/tags/delivery.md>), [doordash](<https://devfeed.tech/tags/doordash.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [lyft](<https://devfeed.tech/tags/lyft.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [post](<https://devfeed.tech/tags/post.md>), [processors](<https://devfeed.tech/tags/processors.md>), [production](<https://devfeed.tech/tags/production.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The AWS Generative AI Innovation Center offers 23 open source, maintained, security-reviewed building blocks for capabilities such as RAG, document processing, and agent applications. The post attributes delivery gains to starting from these validated assets: DoorDash's contact center agent handled over 100,000 calls daily with 2.5-second response latency and a reported 50-fold increase in testing capacity; Ricoh's document processing solution increased throughput sevenfold and cut engineering hours per deployment by over 90%. A Contact Center GenAI Agent walkthrough covers prerequisites, deploying two CloudFormation stacks, connecting Amazon Connect, and validating with Jupyter notebooks; it estimates the process takes under an hour. Newer templates include FAST, which deploys in under 30 minutes and allows major components to be swapped, and an Agentic Chatbot Accelerator built with AWS CDK, Strands Agents, and Amazon Bedrock AgentCore. Results and timing are reported by the post and its cited case studies.

### Source excerpt

Every generative AI team keeps rebuilding the same components: RAG pipelines, document processors, and agent scaffolding. This post shows how to access a curated catalog of 23 production-ready, open source reusable assets from the AWS Generative AI Innovation Center, with real delivery results from DoorDash, Lyft, and Ricoh.

## How TCS built an agentic test orchestrator with Amazon Bedrock AgentCore

DevFeed: [How TCS built an agentic test orchestrator with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/how-tcs-built-an-agentic-test-orchestrator-with-amazon-bedrock-agentcore-127428.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-tcs-built-an-agentic-test-orchestrator-with-amazon-bedrock-agentcore/>)

Author: Varun Valsan

Published: 2026-11-10T16:59:43Z

Content type: article

Language: en

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

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Selenium](<https://devfeed.tech/topics/selenium.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>), [Amazon EventBridge](<https://devfeed.tech/topics/amazon-eventbridge.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [banking](<https://devfeed.tech/tags/banking.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [effort](<https://devfeed.tech/tags/effort.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [insurance](<https://devfeed.tech/tags/insurance.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [tenant-isolation](<https://devfeed.tech/tags/tenant-isolation.md>), [test](<https://devfeed.tech/tags/test.md>), [testing](<https://devfeed.tech/tags/testing.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

TCS built a production test orchestrator for BFSI clients that turns requirements into governed, executable tests. Specialized agents handle scenario design, Gherkin and Java or Python generation, refinement, and execution; project context is retrieved with tenant, project, and session filters. A deterministic supervisor and LangGraph workflow control steps, bounded retries, error classification, correction checks, and reporting. API tests run on ECS with Fargate, while Selenium UI tests use ECS backed by EC2; tenant-specific identity, storage, keys, and knowledge bases support isolation. In an internal benchmark of about 100 scenarios, effort fell from roughly 200 hours manually to about 24 hours with the system, an 88% reduction. TCS cautions that results vary by workload, application complexity, and team.

### Source excerpt

Tata Consultancy Services (TCS) built an agentic test orchestrator on Amazon Bedrock AgentCore that turns requirements into executable, governed tests for its Banking, Financial Services, and Insurance (BFSI) clients. Learn how specialized agents, per-tenant isolation, and workload-aware execution cut testing effort by 88% in an internal benchmark.

## Transforming fleet analytics for Novus Hi-Tech through agentic AI

DevFeed: [Transforming fleet analytics for Novus Hi-Tech through agentic AI](<https://devfeed.tech/articles/transforming-fleet-analytics-for-novus-hi-tech-through-agentic-ai-124814.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/transforming-fleet-analytics-for-novus-hi-tech-through-agentic-ai/>)

Author: Sameer Shrivastava

Published: 2026-11-09T20:34:35Z

Content type: article

Language: en

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

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [AI for SQL query generation](<https://devfeed.tech/topics/ai-for-sql-query-generation.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Data visualization](<https://devfeed.tech/topics/data-visualization.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-aurora](<https://devfeed.tech/tags/amazon-aurora.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [automated](<https://devfeed.tech/tags/automated.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [data](<https://devfeed.tech/tags/data.md>), [driver](<https://devfeed.tech/tags/driver.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [fleet](<https://devfeed.tech/tags/fleet.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [novus](<https://devfeed.tech/tags/novus.md>), [tech](<https://devfeed.tech/tags/tech.md>)

### AI overview

Novus Hi-Tech reports FleetGPT reduced road-behavior violations by 46%, drowsiness alerts per 1,000 km by 55%, and increased fuel efficiency by 3-6%. Built with AWS PACE using Strands Agents and Amazon Bedrock, FleetGPT combines natural-language fleet and policy queries with automated safety response. A Supervisor routes requests to specialized agents: Claude Sonnet 4.6 handles intent and Text-to-SQL, while Claude Haiku 3.0 generates Python for analyses beyond SQL. Aurora PostgreSQL stores analytical data, DynamoDB handles warning events and streams, and Bedrock Knowledge Bases retrieves policies. For critical events, interventions await user approval; approved calls use a driver's language and support two-way voice interaction. The article says stream-based alerts reach operators within seconds and conversational queries bring video, history, and fleet context together. The reported outcomes are presented without detailed measurement methods in the supplied text.

### Source excerpt

Learn how Novus Hi-Tech, with the AWS Prototyping and AI Customer Engineering (PACE) team, built FleetGPT, an agentic AI solution on Amazon Bedrock that turns fleet IoT data into real-time safety interventions through natural language querying, automated investigation, and AI-powered driver voice calls, cutting road-behavior violations by 46% and drowsiness alerts by 55%.

## Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base

DevFeed: [Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base](<https://devfeed.tech/articles/single-shot-and-agentic-retrieval-with-amazon-bedrock-managed-knowledge-base-125100.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/single-shot-and-agentic-retrieval-with-amazon-bedrock-managed-knowledge-base/>)

Author: Siddhant Sahu

Published: 2026-11-09T20:13:18Z

Content type: article

Language: en

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

Topics: [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agentic-retrieval](<https://devfeed.tech/tags/agentic-retrieval.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [banking](<https://devfeed.tech/tags/banking.md>), [expert-400](<https://devfeed.tech/tags/expert-400.md>), [policy](<https://devfeed.tech/tags/policy.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

Amazon Bedrock Managed Knowledge Base now uses `AgenticRetrieveStream` for three retrieval modes, selected per request by the application. Set `maxAgentIteration=0` and `generateResponse=false` to return passages without foundation model calls; setting generation to true at zero is invalid. Set it to 1 with generation enabled for one retrieval and one grounded answer, without planning. Values 2-5 retain agentic retrieval, allowing up to n−1 planning rounds before answer generation; this can help with multi-part questions but may add latency. The service can search multiple knowledge bases in all three modes. The article recommends evaluating representative questions, latency, cost, and answer support to choose an iteration limit; mode selection is application logic.

### Source excerpt

Amazon Bedrock Managed Knowledge Base now supports single-shot RAG and retrieval-only requests through AgenticRetrieveStream, alongside agentic retrieval. This post explains how the maxAgentIteration parameter matches retrieval effort to each request, using an illustrative internal banking policy assistant.

## Pluggable Agentic AI Framework: A seven-layer composable enterprise agentic AI reference architecture on Amazon Bedrock AgentCore

DevFeed: [Pluggable Agentic AI Framework: A seven-layer composable enterprise agentic AI reference architecture on Amazon Bedrock AgentCore](<https://devfeed.tech/articles/pluggable-agentic-ai-framework-a-seven-layer-composable-enterprise-agentic-ai-reference-architecture-on-amazon-bedrock-agentcore-125098.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/pluggable-agentic-ai-framework-a-seven-layer-composable-enterprise-agentic-ai-reference-architecture-on-amazon-bedrock-agentcore/>)

Author: Sindhura Palakodety

Published: 2026-11-09T19:05:54Z

Content type: article

Language: en

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

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>), [Amazon DynamoDB](<https://devfeed.tech/topics/amazon-dynamodb.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>)

Tags: [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-framework](<https://devfeed.tech/tags/agentic-ai-framework.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-framework](<https://devfeed.tech/tags/ai-framework.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [can](<https://devfeed.tech/tags/can.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-agentic-ai](<https://devfeed.tech/tags/enterprise-agentic-ai.md>), [expert-400](<https://devfeed.tech/tags/expert-400.md>), [framework](<https://devfeed.tech/tags/framework.md>), [layer](<https://devfeed.tech/tags/layer.md>), [production](<https://devfeed.tech/tags/production.md>), [reference](<https://devfeed.tech/tags/reference.md>), [reference-architecture](<https://devfeed.tech/tags/reference-architecture.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>)

### AI overview

The framework proposes seven composable layers for moving multi-agent applications from prototype to production: data and knowledge, model and inference, orchestration, security and guardrails, application, observability, and agentic operations. Each layer has a stable contract, allowing its technology to be replaced without redesigning the stack; listed AWS services and other tools are examples, not requirements. The guidance includes routing models through a common interface after realistic evaluation; using scoped specialist agents and a registry for complex workflows; authenticating requests, limiting tool access, masking sensitive data, auditing decisions, and gating high-impact actions; and tracking traces, cost, latency, safety, and quality with continuous evaluation and regression checks. A retail refund example combines a supervisor with scoped order and refund agents, DynamoDB lookups, knowledge-base policy retrieval, gateway access control, and end-to-end tracing. The implementation is a starting point, not a substitute for production security hardening, testing, and review.

### Source excerpt

A seven-layer composable reference architecture for taking enterprise agentic AI from prototype to production on Amazon Bedrock AgentCore. Each layer has a stable contract, so you can swap technologies at any layer without redesigning the rest of the stack.

## How CrossnoKaye grounds physical AI with Amazon Bedrock AgentCore

DevFeed: [How CrossnoKaye grounds physical AI with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/how-crossnokaye-grounds-physical-ai-with-amazon-bedrock-agentcore-125094.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-crossnokaye-grounds-physical-ai-with-amazon-bedrock-agentcore/>)

Author: Raphael Simon

Published: 2026-11-09T18:55:43Z

Content type: article

Language: en

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

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>), [execution](<https://devfeed.tech/topics/execution.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [advanced-process-control](<https://devfeed.tech/tags/advanced-process-control.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [aggregates](<https://devfeed.tech/tags/aggregates.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-reasoning](<https://devfeed.tech/tags/ai-reasoning.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [atlas](<https://devfeed.tech/tags/atlas.md>), [aura](<https://devfeed.tech/tags/aura.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [heavy-industry](<https://devfeed.tech/tags/heavy-industry.md>), [industry](<https://devfeed.tech/tags/industry.md>), [live](<https://devfeed.tech/tags/live.md>), [math](<https://devfeed.tech/tags/math.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [python](<https://devfeed.tech/tags/python.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>)

### AI overview

CrossnoKaye grounds industrial AI in a unified plant model: its ATLAS platform gives AURA access to live telemetry, equipment topology, control narratives, interlocks, histories, and optimization state within one security boundary. For quantitative work, AURA runs model-authored Python in isolated Amazon Bedrock AgentCore microVMs. It keeps warm sessions for interactive Chats, while repeatable Tasks and automated Routines use fresh single-run sandboxes. A verification harness checks DataFrame schemas and writes Parquet outputs; failures trigger a structured retry before results are published. Routines can send cited Briefs by email, but do not change controls automatically. Guardrails, read-only sandboxes, human approval for proposed setting changes, deterministic edge controls, and physical protections constrain plant impact. CrossnoKaye reports investigations completing in under four minutes and operational improvements across its facilities.

### Source excerpt

CrossnoKaye brought physical AI to heavy industry with Amazon Bedrock AgentCore. Its ATLAS platform and AURA agentic system ground AI reasoning in live plant data and run verifiable Python in isolated AgentCore sandboxes, giving plant engineers checkable, math-backed answers instead of model guesses.

## Serverless MCP server for AI agent data lake access on Amazon ECS Fargate

DevFeed: [Serverless MCP server for AI agent data lake access on Amazon ECS Fargate](<https://devfeed.tech/articles/serverless-mcp-server-for-ai-agent-data-lake-access-on-amazon-ecs-fargate-121745.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/serverless-mcp-server-for-ai-agent-data-lake-access-on-amazon-ecs-fargate/>)

Author: Aishwarya Pawar

Published: 2026-11-06T17:13:13Z

Content type: article

Language: en

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

Topics: [Serverless](<https://devfeed.tech/topics/serverless.md>), [AWS Fargate](<https://devfeed.tech/topics/aws-fargate.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [data lake](<https://devfeed.tech/topics/data-lake.md>), [Amazon DynamoDB](<https://devfeed.tech/topics/amazon-dynamodb.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>), [AWS Lambda](<https://devfeed.tech/topics/aws-lambda.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-data](<https://devfeed.tech/tags/ai-agent-data.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-ecs](<https://devfeed.tech/tags/amazon-ecs.md>), [amazon-elastic-container-service](<https://devfeed.tech/tags/amazon-elastic-container-service.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-fargate](<https://devfeed.tech/tags/aws-fargate.md>), [code](<https://devfeed.tech/tags/code.md>), [context](<https://devfeed.tech/tags/context.md>), [data](<https://devfeed.tech/tags/data.md>), [data-lake](<https://devfeed.tech/tags/data-lake.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [ecs](<https://devfeed.tech/tags/ecs.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [server](<https://devfeed.tech/tags/server.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

The article describes a centralized MCP gateway on Amazon ECS Fargate that lets MCP-compatible agents query an enterprise data lake through shared tools and access controls. Dataset onboarding uses a metadata JSON file describing schema, business context, and column meanings; a pipeline embeds and indexes it in Amazon Bedrock Knowledge Bases, making the dataset discoverable after a sync without per-dataset integration code. Optional context mappings narrow metadata search. The agent uses catalog information to generate SQL, validates and auto-corrects it for Athena, and executes it; document search can also be combined with SQL in one response. Cognito handles user authentication, the server runs in private subnets, Athena tools reject non-SELECT queries, and tool calls are logged to CloudWatch. The authors report 15-20 seconds for end-to-end interactions in testing. They identify finer-grained column restrictions and query-failure feedback as planned extensions.

### Source excerpt

Learn how to build a serverless Model Context Protocol (MCP) server on Amazon ECS with AWS Fargate that gives AI agents secure, metadata-driven access to an enterprise data lake. Exposing a new dataset requires only a JSON file, with no per-dataset integration code.

## Taxbit Assist: A grounded, role-aware AI agent on Amazon Bedrock AgentCore

DevFeed: [Taxbit Assist: A grounded, role-aware AI agent on Amazon Bedrock AgentCore](<https://devfeed.tech/articles/taxbit-assist-a-grounded-role-aware-ai-agent-on-amazon-bedrock-agentcore-121746.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/taxbit-assist-a-grounded-role-aware-ai-agent-on-amazon-bedrock-agentcore/>)

Author: Karan Nayak

Published: 2026-11-06T16:49:42Z

Content type: article

Language: en

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

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [rbac](<https://devfeed.tech/topics/rbac.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [Amazon EventBridge](<https://devfeed.tech/topics/amazon-eventbridge.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-guardrails](<https://devfeed.tech/tags/amazon-bedrock-guardrails.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-eventbridge](<https://devfeed.tech/tags/amazon-eventbridge.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>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [permission](<https://devfeed.tech/tags/permission.md>), [production](<https://devfeed.tech/tags/production.md>), [quality](<https://devfeed.tech/tags/quality.md>), [region](<https://devfeed.tech/tags/region.md>), [safety](<https://devfeed.tech/tags/safety.md>)

### AI overview

Taxbit built a cited, permission-aware assistant inside its dashboard using Strands Agents SDK on Amazon Bedrock AgentCore. It grounds answers in a curated knowledge base combining published help and API content, product documentation generated from source code, and approved corrections. Semantic chunking adds each document's title and scope to passages; retrieval over-fetches and reranks candidates, while code enforces which sources can be cited. The model checks feature and role access before suggesting workflows, but identity comes from the authenticated service and is bound to tools; AgentCore isolates sessions. Guardrails screen each incoming turn, masking formatted tax identifiers and blocking secrets. EU and US deployments use geography-aware inference. Production traces feed automated evaluations and expert review, with approved corrections incrementally ingested. Taxbit reports over 55% of users who ask a question return within 24 hours, and average model cost below 20 cents per conversation. The assistant currently uses product knowledge and cannot read customer tax data.

### Source excerpt

Taxbit built Taxbit Assist, a cited, permission-aware AI assistant embedded in its enterprise dashboard, on Amazon Bedrock AgentCore. This post shows how they grounded answers in a curated knowledge base, enforced role-aware and region-compliant safety, and continuously measured answer quality on live production traffic.

## How Indegene is modernizing and scaling enterprise data quality in life sciences

DevFeed: [How Indegene is modernizing and scaling enterprise data quality in life sciences](<https://devfeed.tech/articles/how-indegene-is-modernizing-and-scaling-enterprise-data-quality-in-life-sciences-117738.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-indegene-is-modernizing-and-scaling-enterprise-data-quality-in-life-sciences/>)

Author: Bhagyashree Chandak

Published: 2026-11-04T16:25:57Z

Content type: article

Language: en

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

Topics: [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [data-governance](<https://devfeed.tech/topics/data-governance.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AWS Glue](<https://devfeed.tech/topics/aws-glue.md>), [sensitive data](<https://devfeed.tech/topics/sensitive-data.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-communication](<https://devfeed.tech/tags/agent-communication.md>), [aws](<https://devfeed.tech/tags/aws.md>), [context](<https://devfeed.tech/tags/context.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [data](<https://devfeed.tech/tags/data.md>), [data-platform](<https://devfeed.tech/tags/data-platform.md>), [data-quality](<https://devfeed.tech/tags/data-quality.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-data](<https://devfeed.tech/tags/enterprise-data.md>), [governance](<https://devfeed.tech/tags/governance.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [life-sciences](<https://devfeed.tech/tags/life-sciences.md>), [llm](<https://devfeed.tech/tags/llm.md>), [modernizing](<https://devfeed.tech/tags/modernizing.md>), [platform](<https://devfeed.tech/tags/platform.md>), [production](<https://devfeed.tech/tags/production.md>), [python](<https://devfeed.tech/tags/python.md>), [rules](<https://devfeed.tech/tags/rules.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [sql](<https://devfeed.tech/tags/sql.md>)

### AI overview

Indegene's Data Quality Agent in its NEXT Unified Data Platform uses LLMs and two knowledge bases--internal enterprise materials and approved external references--to recommend technical and life sciences business rules from table metadata, profiles, anomalies, existing rules, and domain context. Users select a source such as Amazon Redshift or Snowflake, review and refine suggestions, and approve rules before the agent generates SQL, Python, or PySpark. Generated code receives syntax and schema checks and, where supported, a sample-data test. High-confidence, low-risk rules may be approved automatically; critical and business rules require SME review, with decisions recorded centrally. The system is built around Amazon Bedrock, Strands Agents, and Bedrock AgentCore, with Guardrails for input/output safeguards. Indegene reports reducing rule implementation effort from about 30 to 4 hours per dataset and table onboarding from 2-5 working days to 2-4 hours in its production deployments; these figures are estimated. The text describes current rule generation and governance, while remediation recommendations and root cause analysis are future enhancements.

### Source excerpt

This post explores how Indegene built a production-grade, LLM-powered Data Quality Agent in its NEXT Unified Data Platform on AWS. The agent generates context-aware data quality rules, validates them, and produces ready-to-run SQL and Python under human-in-the-loop governance, helping life sciences organizations scale enterprise data quality.

[Next page](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md?cursor=WyIyMDI2LTExLTA0VDE2OjI1OjU3KzAwOjAwIiwgIjZmZTUwMjE1LTgzMDUtNDkzNC1hZTVmLTM5N2JhOTY0YzM1MyJd>)