Möchtest du dein Wissen auch so organisieren?

Kostenlos starten

Wiki-Seite

Amazon Bedrock

Amazon Bedrock provides managed foundation-model and agent capabilities, including retrieval over operational policy documents in FleetGPT.

4 Quellen✦ KI-generiert von Pith

Overview

Amazon Bedrock is the agent-orchestration service in the AWS architecture described by the source, handling user requests and routing them to Lambda action groups.1 The example pairs a Bedrock agent with a DynamoDB table that serves as both the operational store and vector store, allowing the same system to answer conversational questions and perform direct document operations.1

Agent Actions

The architecture assigns separate actions to Lambda functions: one performs semantic retrieval and another carries out create, read, update, and delete operations against DynamoDB.1 For semantic retrieval, the Lambda function obtains a query embedding using Amazon Titan Text Embeddings V2 and calls DynamoDB’s SearchVectors API.1 This divides responsibility between the agent’s request routing and the functions that perform database work.1

Data Synchronization

The design uses DynamoDB Streams to trigger an embedding pipeline when stored content changes, helping keep vectors aligned with their source records without manual updates.1 Keeping document data and embeddings in the same database is presented as a way to reduce the synchronization burden and the chance of inconsistent retrieval results.1

Use Case

The pattern is presented for knowledge-management systems where users need natural-language conversational search as well as direct access to documents.1 Its broader architectural motivation is to simplify an agent stack by reducing the need to operate and synchronize a separate vector database.1

Security considerations

A reported Bedrock AgentCore issue showed how prompt-driven access to the Instance Metadata Service could expose temporary cloud credentials: the service initially used IMDSv1, and weak network isolation in its Firecracker microVM setup enabled an SSRF-style request to the credential endpoint.2 The credentials reportedly enabled cross-agent discovery, access to ECR images, agent memories and conversations, and retrieval of Secrets Manager secrets; Zenity also identified permissions scoped broadly across regional AgentCore resources.2 AWS later moved AgentCore to IMDSv2 and addressed the permission issue, while disputing the researchers’ characterization of the incident as a vulnerability.2

Timeline
Berichtete Sicherheitsprüfung von AgentCore
  • Dec 2025
  • Jan 2026
  • 22 Jun 2026
  • 29 Sept 2026
Retrieved 12 Oct 2026 · Sources: theregister.com
Berichtete Sicherheitsprüfung von AgentCore
LabelValueSourceEvidence
Dec 2025Zenity meldete die Erkenntnisse an AWStheregister.comResearchers at Zenity Labs disclosed their findings to AWS in December 2025.
Jan 2026Zenity übermittelte Details zu übermäßigen Berechtigungentheregister.comThe Zenity researchers told Bob's tale, or something like it, to AWS last December, then followed up in January 2026 with details about AgentCore being overprivileged.
22 Jun 2026Die übermäßigen Berechtigungen waren weiterhin nicht behobentheregister.comAgentCore's excessive permissions remained in place at least until June 22, 2026, when Zenity checked in and found the issue hadn't been remediated.
29 Sept 2026Zenity stellte fest, dass AWS die bestehenden Probleme behoben hattetheregister.comA final review by Zenity occurred on September 29, 2026, at which point the biz observed that AWS had addressed the extant problems, clearing the way for Bob's hypothetical adventure to finally be told.

Usage

In an AWS reference architecture for antimicrobial-resistance surveillance, Bedrock Guardrails are used in the conversational query layer, while an AgentCore-hosted Strands agent calls Athena-backed tools to answer users' natural-language questions.23

FleetGPT example

In Novus Hi-Tech’s FleetGPT, Amazon Bedrock Knowledge Bases indexes unstructured standard operating procedures, policies, and documentation so the system can retrieve them during natural-language fleet-data investigations.24

  • Amazon Bedrock AgentCore — AgentCore extends AWS agent capabilities with runtime isolation and permission safeguards alongside Amazon Bedrock’s managed foundation-model and agent services.
  • FleetGPT — FleetGPT uses Amazon Bedrock’s managed foundation models and agent capabilities to investigate fleet events and retrieve operational policy documents.
  • Amazon DynamoDB — DynamoDB complements Amazon Bedrock in FleetGPT by providing operational records and vector search for fleet-event access and retrieval.
Themen-Puls
Amazon Bedrock
8
Artikel in 8 Wochen
1
diese Woche
KW 40: 11KW 41: 11KW 42: 11KW 43: 11KW 44: 11KW 45: 11KW 46: 11KW 47: 11KW 40diese Woche
8 Artikel in den Quellen und Feeds hinter diesem Wiki nennen „Amazon Bedrock“ oder „Bedrock“ in Titel oder Anriss (2 davon gespeichert) · Stand: 21. Nov. 2026
Amazon Bedrock
BezeichnungWertQuelle
KW 40 (28. Sept. 2026)1
KW 41 (5. Okt. 2026)1
KW 42 (12. Okt. 2026)1
KW 43 (19. Okt. 2026)1
KW 44 (26. Okt. 2026)1
KW 45 (2. Nov. 2026)1
KW 46 (9. Nov. 2026)1
KW 47 (16. Nov. 2026)1
Chronologie
BezeichnungWertQuelle
25. Sept. 2026 (gespeichert)Build a unified AI agent architecture with DynamoDB and Bedrockaws.amazon.com
9. Okt. 2026 (veröffentlicht)AWS AgentCore security undone by prompt requesting credentialstheregister.com
12. Okt. 2026 (im Feed)Agentic antimicrobial resistance surveillance with AWS HealthOmics and Amazon Bedrock AgentCoreaws.amazon.com
9. Nov. 2026 (im Feed)Transforming fleet analytics for Novus Hi-Tech through agentic AIaws.amazon.com

Quellen

  1. 1

    Build a unified AI agent architecture with DynamoDB and Bedrock

    aws.amazon.com
  2. 2

    AWS AgentCore security undone by prompt requesting credentials

    theregister.com
  3. 3

    Agentic antimicrobial resistance surveillance with AWS HealthOmics and Amazon Bedrock AgentCore

    aws.amazon.com
  4. 4

    Transforming fleet analytics for Novus Hi-Tech through agentic AI

    aws.amazon.com

Möchtest du dein Wissen auch so organisieren?

Speichere, was du liest — Pith schreibt dir jeden Morgen einen Report mit Belegen und baut daraus dein Wiki. Speichern ist kostenlos, KI kostet Cent pro Aktion.