Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #747

Amazon S3

Related event timeline, sources and context from the news index.

EVENT TIMELINE

30

CODING · 1 SOURCE · AWS Machine Learning

Amazon outlines Crawl4AI workflow to prepare web content for Bedrock Knowledge Bases

AWS published a how‑to showing a sample workflow that uses the open‑source Crawl4AI crawler to generate Markdown plus metadata sidecars uploaded to Amazon S3 for ingestion by Amazon Bedrock Knowledge Bases. The post explains when to use the built‑in Bedrock Web Crawler versus Crawl4AI for targeted extraction, custom metadata, and boilerplate pruning, and links an aws‑samples repo with the implementation using EventBridge, ECS/Fargate, and S3.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Epsilon adopts Amazon Nova Act and Bedrock AgentCore Browser for intent-driven UI testing

Epsilon’s Agentic Platform team integrated Amazon Nova Act with the Amazon Bedrock AgentCore Browser tool to deliver intent-driven, natural-language UI testing as a managed, multi-tenant platform service layered on top of their existing Playwright regression suite. The architecture uses AWS-managed ephemeral browser sessions, IAM-based auth, cross-account STS provisioning, and session recording/audit to reduce per-team operational burden while enabling resilient, readable test steps.

5.0

CODING · 1 SOURCE · AWS Machine Learning

Build agentic retrieval on Managed Amazon Bedrock Knowledge Base with AWS CDK

An AWS post demonstrates a Python AWS CDK application that deploys an agentic retrieval system using Managed Amazon Bedrock Knowledge Bases and AgentCore. The sample routes queries across two knowledge bases, uses the AgenticRetrieveStream API for multi-turn, cited answers, and provisions CloudWatch dashboards and on-demand/continuous evaluation for observability.

7.0

MODELS · 1 SOURCE · AWS Machine Learning

TwelveLabs' Pegasus 1.5 is now available on Amazon Bedrock

TwelveLabs has made Pegasus 1.5 — a video language model that converts long-form video into structured, timestamped JSON metadata — available on Amazon Bedrock. New features include full-video segmentation, multimodal prompting with reference images, on-the-fly processing with no pre-indexing, and extended single-request analysis up to two hours; calls are made via the bedrock-runtime InvokeModel or InvokeModelWithResponseStream APIs and can process video from an S3 URI or a base64 string while keeping data within the AWS boundary.

6.0

COMPANIES · 1 SOURCE · InfoQ AI, ML & Data Engineering

Amazon acquires DuckLabs and integrates DuckDB into Amazon Aurora PostgreSQL

Amazon (AWS) has acquired DuckLabs, the team behind the analytical database DuckDB; co‑founders Hannes Mühleisen and Mark Raasveldt will join AWS and continue to lead the project. AWS says DuckDB and related components will remain MIT‑licensed and overseen by the DuckDB Foundation, and has already integrated DuckDB into Amazon Aurora PostgreSQL so a single query can combine live Aurora data with historical Iceberg/Parquet data in S3 (via AWS Glue) without separate ETL; the feature is available in all commercial regions and AWS GovCloud (US) with customers paying only for incremental Aurora compute and S3 requests.

8.0

CODING · 1 SOURCE · AWS Machine Learning

Build agentic intelligent document processing on Amazon Bedrock AgentCore with Strands Agents

AWS published a how-to for an agentic intelligent document processing (IDP) solution that uses Amazon Bedrock AgentCore and the open-source Strands Agents SDK to classify, extract, validate, and self-learn from business documents. The architecture ties AgentCore runtime and identity capabilities to AWS services (Textract, S3 Vectors, Aurora DSQL, Lambda, EventBridge, DynamoDB, ECS) in multi-agent workflows so new document formats can be processed and reused with minimal manual template configuration.

6.0

CODING · 1 SOURCE · AWS Machine Learning

Deploy llama.cpp decision models on Amazon SageMaker AI with AWS DLC and SemIf

AWS published a how-to showing how to use the AWS Deep Learning Container (DLC) for llama.cpp to serve OpenAI‑compatible chat completions via SageMaker InvokeEndpoint, and how to extend that image with SemIf (formerly OpenJev) to return option probabilities and logits for structured decision tasks. The post includes CPU and GPU deployment options, a child‑image build path using CodeBuild/ECR for SemIf, and a benchmark comparing CPU vs GPU latency for SemIf workloads.

6.0

CODING · 1 SOURCE · AWS Machine Learning

AWS blog: guide to building a context-aware assistant with OpenClaw on AgentCore

A how-to blog post demonstrates building a personal, memory-enabled AI assistant (example: ‘Sprout’ gardener) by combining OpenClaw with Amazon Bedrock AgentCore runtime and AgentCore memory, with deployment packaged as a single CloudFormation template. The guide shows architecture, cost/consumption tradeoffs, required components (including Claude Haiku 4.5 / Claude Sonnet 4.5 access), and a one-command deploy path for personal use.

7.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Manage Amazon SageMaker HyperPod Spaces directly from SageMaker Studio

AWS added UI support in SageMaker Studio to create and manage SageMaker Spaces on HyperPod EKS clusters, enabling data scientists to launch JupyterLab or Code Editor environments and start/stop Spaces without using the CLI. Administrators must install the SageMaker Spaces add-on on HyperPod clusters, attach required IAM policies, and enable per-user identity propagation for Studio domains.

6.0

CODING · 1 SOURCE · AWS Machine Learning

Amazon publishes Quick Resource Migrator — MCP server on Bedrock AgentCore to automate cross-account promotion

Amazon posted a sample Quick Resource Migrator — an idempotent, auditable Model Context Protocol (MCP) server running on Amazon Bedrock AgentCore that automates promotion of Amazon Quick resources (agents, connectors, knowledge bases, flows, spaces) across AWS accounts. The tool reads resources and permissions via the Amazon Quick API, upserts them into a target account, writes versioned backups to S3, and provides a read-only preview; source code is available in the aws-samples repository.

6.0

CODING · 1 SOURCE · AWS Machine Learning

Amazon Bedrock Managed Knowledge Bases supports agentic retrieval; LangChain walkthrough

A technical walkthrough demonstrates using LangChain with Amazon Bedrock Managed Knowledge Bases to compare standard single-shot retrieval (Retrieve API) and multi-step agentic retrieval (AgenticRetrieveStream API). The post explains architecture, IAM permissions, boto3 version requirements (agentic_retrieve_stream requires boto3 >= 1.43.32), and trade-offs including cost and trace event inspection.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon SageMaker AI demonstrates multi-turn reinforcement learning (MTRL) fine-tuning for search agents with Qwen3.6-27B

Amazon’s blog post describes using Amazon SageMaker AI’s multi-turn reinforcement learning (MTRL) capability to fine-tune a Qwen3.6-27B model for an LLM-powered search agent. The write-up details MTRL features—serverless execution, modular agent-environment interfaces, asynchronous rollouts, built-in algorithms (PPO, CISPO, IS), trajectory observability via MLflow, and evaluation jobs—and shows an enterprise search use case combining BM25 and vector search tools.

6.0

CODING · 1 SOURCE · AWS Machine Learning

How to use Amazon S3 Vectors as persistent memory for NVIDIA NeMo Agent Toolkit (NAT v1.6)

A how-to showing how to implement Amazon S3 Vectors as a custom memory provider for the open-source NVIDIA NeMo Agent Toolkit (NAT), including a MemoryEditor plugin, YAML configuration, and deployment on Amazon EKS; the post was tested with NAT v1.6 and uses Amazon Titan Text Embeddings V2 for embeddings. It demonstrates mapping NAT's memory model (MemoryItem/MemoryEditor) to S3 Vectors indexes and metadata, and explains required tooling and configuration for a multi-agent investment research example.

5.0

CODING · 1 SOURCE · AWS Machine Learning

Amazon Bedrock AgentCore guide for ambient agents with event-driven, human-in-the-loop workflows

AWS published a walkthrough and reference implementation showing how to build "ambient" agents on Amazon Bedrock AgentCore that react to event streams (S3, EventBridge, scheduled tasks), pause for human approval via a single ask_human tool, and resume—using AgentCore Runtime plus serverless AWS components (Lambda, DynamoDB, SQS) and Bedrock foundation models. The post includes a sample deployment path requiring AWS CLI, CDK v2, Docker, and an ECR-hosted agent container, and notes session timeouts align with Lambda's 15-minute limit in the reference.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Uniopen fine-tunes Amazon Nova 2 Lite for retail content moderation

Uniopen (part of Taiwan’s Uni‑President Enterprises Group) adapted Amazon Nova 2 Lite for its retail moderation taxonomy by supervised fine-tuning in Amazon SageMaker AI and additional prompt‑level output optimization, using Nova 2 Pro to generate candidate corrections that humans verify before inclusion in training data. The deployment pipeline uses Amazon S3, DynamoDB, Argo Workflows on EKS, Argo CD, SNS, CloudWatch and Bedrock Guardrails with hard/soft gate checks, fixed test sets, and mandatory human review for ambiguous cases.

6.0

CODING · 1 SOURCE · AWS Machine Learning

AWS how-to: build a cited-answers claims assistant with Amazon Bedrock Knowledge Bases

AWS published a technical how‑to showing how to index claim documents from Amazon S3 into Amazon Bedrock Knowledge Bases and use the AgenticRetrieveStream API to answer natural‑language questions with streamed trace events, citations, and grounding checks; the walkthrough uses synthetic claim records and demonstrates scoping via metadata filters and a contextual grounding guardrail. The guide explains ingestion (parsing, chunking, embeddings, vector storage), agentic retrieval that iterates sub-queries, and streaming of answers, traces, and citations to support auditable, source-backed responses.

6.0

CODING · 1 SOURCE · AWS Machine Learning

AWS shows multi-agent music pipeline on Amazon Bedrock AgentCore Runtime Instances

AWS published a walkthrough demonstrating a three-agent music production pipeline deployed on Amazon Bedrock AgentCore Runtime Instances. The example colocates agents on a single EC2-backed instance with persistent volumes and an NVIDIA L4 GPU (running ACE-Step for on-instance music generation), uses shared runtimeSessionId for agent collaboration, and packages agents as ECR containers or S3 artifacts to enable multi-day, stateful workflows.

6.0

CODING · 1 SOURCE · AWS Machine Learning

AWS guide: building a contract-intelligence platform with Bedrock AgentCore

An AWS how-to describes an architecture for a React web app that converts portfolios of contract PDFs into structured, queryable data: AI extraction agents running via Amazon Bedrock (AgentCore) use Claude Sonnet to extract fields and Claude Haiku to verify them, Amazon Textract acts as a deterministic tiebreaker for signatures, results are stored in Amazon Aurora PostgreSQL, and users query via embedded analytics and a natural-language chat interface with real-time pipeline status over WebSocket.

6.0

CODING · 1 SOURCE · AWS Machine Learning

Generate images and image-conditioned video on SageMaker AI using AWS vLLM-Omni DLC (FLUX.2-klein-4B → Wan2.1-VACE-1.3B)

An AWS blog post demonstrates deploying the same AWS vLLM-Omni Deep Learning Container to two SageMaker AI endpoints: a real-time endpoint running FLUX.2-klein-4B for image generation and an asynchronous endpoint running Wan2.1-VACE-1.3B for image-conditioned video generation. The sample workflow generates a PNG from text, passes it (via S3) to the video endpoint, retrieves the MP4 from S3, and includes CLI and optional Streamlit examples.

5.0

MODELS · 1 SOURCE · AWS Machine Learning

Automating Amazon Textract Custom Queries adapter lifecycle across accounts

An AWS post describes architecture, infrastructure templates (CloudFormation and Terraform), and operational patterns to automate promotion, routing, and production hardening of Amazon Textract Custom Queries adapters across accounts. It shows a pre-classification routing step using DetectDocumentText and storing adapter IDs in AWS Systems Manager Parameter Store to enable zero-downtime adapter updates, plus recommended security controls (KMS, PrivateLink, least-privilege IAM, CloudTrail/CloudWatch).

5.0

COMPANIES · 1 SOURCE · InfoQ AI, ML & Data Engineering

Perplexity replaces DynamoDB with in-house CobbleDB to cut batch-read latency 5x

Perplexity moved its core search serving tier from Amazon DynamoDB to CobbleDB, an internally developed Rust-based distributed key-value store, splitting durable storage (Pillar) from hot serving (CobbleDB) and using Lorry to aggregate batch files in S3. The change reportedly reduced median batch-read latency from 31.4 ms to 5.60 ms, cut p99 tail latency from 123 ms to 24.2 ms, sustained synthetic throughput up to 500k requests/sec, and lowered overall storage costs by at least 20%.

7.0

MODELS · 1 SOURCE · AWS Machine Learning

AWS packages WhisperX DLC for SageMaker to deliver speaker‑labeled, per‑word timestamps

AWS provides a WhisperX Deep Learning Container (DLC) for Amazon SageMaker that bundles OpenAI Whisper with wav2vec2 forced alignment and speaker diarization to produce per-word timestamps and speaker labels. The GPU-ready container conforms to SageMaker’s serving contract, supports real-time and asynchronous endpoints, and outputs json, verbose_json, srt, and vtt formats (example image tag: whisperx:3.8.6-cu128-amzn2023-sagemaker).

6.0

CODING · 1 SOURCE · AWS Machine Learning

AWS publishes agentic conversational video-intelligence reference architecture using Strands Agents SDK and Bedrock (Claude Sonnet)

AWS published a reference architecture and companion GitHub implementation for an agentic video-intelligence system that uses the Strands Agents SDK and Amazon Bedrock (Anthropic Claude Sonnet) to orchestrate Amazon Rekognition, Amazon Transcribe, and other services based on natural-language queries. The post says previously analyzed videos return answers in under a second and initial analysis of new videos takes about 5–10 minutes; a customer reported an internal ~80% reduction in manual review time (not independently verified).

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Tata Elxsi builds IRIS real-time industrial safety platform on AWS

Tata Elxsi built IRIS (Industrial Real-Time Intelligence System), a serverless, event-driven industrial vision platform on AWS that performs first-pass computer-vision inference at the edge (example edge hardware: NVIDIA Jetson AGX Orin) using AWS IoT Greengrass, uploads filtered frames and compact metadata to Amazon S3, and correlates detections into near-real-time safety alerts; edge filtering reportedly reduces frames sent to the cloud by about 70–80% and the system runs in the AWS Asia Pacific (Mumbai) Region.

5.0

COMPANIES · 1 SOURCE · AWS Machine Learning

AWS shows how to feed Amazon Bedrock Data Automation outputs into Salesforce Agentforce via MCP

An AWS blog post outlines an architecture that uses Amazon Bedrock Data Automation and the Model Context Protocol (MCP) to process unstructured evidence (video, audio, images, documents) stored in Amazon S3 and make structured insights available to Salesforce Agentforce inside the Salesforce console. The pattern uses S3 events, AWS Lambda, DynamoDB and EventBridge, and routes agent queries through Amazon Bedrock AgentCore Gateway to retrieve processed outputs via MCP.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

BMW’s CLEA uses Prophet to detect cost anomalies across 14,000 cloud accounts

BMW Group’s in-house FinOps system, Cloud Efficiency Analytics (CLEA), ingests billing exports (including AWS CUR) and builds per-account-service daily forecasts with Prophet to run daily anomaly detection across roughly 14,000 cloud accounts. The serverless pipeline (Step Functions, Lambda, S3, Distributed Map) processes hundreds of thousands of account-service time series in about 20 minutes and alerts owners when actual spend departs from the forecast; the team reports the compute run costs around $50/month.

4.0

CODING · 1 SOURCE · AWS Machine Learning

Posit's Positron IDE runs on Amazon SageMaker AI with Bedrock-enabled Posit Assistant

Posit published a Positron container image definition that can be registered with Amazon SageMaker AI so administrators can attach the IDE to a SageMaker Studio domain. Running Positron on SageMaker AI lets data scientists query governed AWS data (Athena, Glue, S3) under a Space execution role, launch Spaces on reserved or on-demand SageMaker compute, collaborate in shared or parallel Spaces, and use Posit Assistant with Amazon Bedrock as the model provider inside the customer's AWS account and region.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Benchling runs multi-tenant AI agent code using Amazon Bedrock AgentCore Code Interpreter in VPC mode

Benchling described a defense-in-depth architecture to run AI agent‑generated scientific code across thousands of life‑sciences tenants using Amazon Bedrock AgentCore’s Code Interpreter in VPC mode. The setup places untrusted executions in a separate AWS account (the “Untrusted Code Account”), enforces DNS-level controls with Route 53 Resolver DNS Firewall, restricts network paths to specific VPC endpoints, injects per-job credentials via AWS STS, and runs continuous validation; the architecture reportedly handles >600 code execution sessions per day across >250 tenants per week with zero security incidents.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

AWS publishes serverless Git-metrics dashboard solution using Amazon QuickSight

AWS released a serverless, event-driven pipeline that automatically collects Git metrics from GitHub and GitLab, stores results in Amazon S3, and visualizes analytics with Amazon QuickSight. The solution uses EventBridge Scheduler, Step Functions, Lambda, and CloudFormation parameters, and includes change detection, adaptive chunking, and full/incremental loads to provide near-real-time engineering analytics and support observability in the AI-Driven Development Lifecycle framework.

3.0

CODING · 1 SOURCE · AWS Machine Learning

Build an end-to-end RFI questionnaire workflow with Amazon Quick Automate

AWS Machine Learning published a how-to showing how to build an end-to-end RFI questionnaire workflow using Amazon Quick Automate: read a multi-tab RFI workbook from Amazon S3, use natural-language prompts to extract and structure the data, iterate the workflow conversationally, and write CSV output back to S3. The guide claims this approach can reduce development time from days to hours.

4.0