Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #10364

Amazon VPC

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

EVENT TIMELINE

5

MODELS · 1 SOURCE · AWS Machine Learning

Deploy NVIDIA NeMo Switchyard (switchyard-server 0.3.0) with LiteLLM v1.102.0 to route requests to Amazon Bedrock via AWS CDK

This sample shows how to use the AWS CDK to deploy LiteLLM (v1.102.0) with the NVIDIA NeMo Switchyard plugin (switchyard-server 0.3.0) on Amazon ECS/Fargate, routing agent requests to models served through Amazon Bedrock. It demonstrates two Switchyard strategies (stage and random), the request flow through VPC-based Bedrock Converse APIs, and benchmark runners to measure cost per solved coding task; the integration is experimental and intended for non-production evaluation.

5.0

COMPANIES · 1 SOURCE · AWS Machine Learning

DXC builds governed multi-model AI substrate for DXC OASIS on Amazon Bedrock

DXC Technology built a governed model substrate for its DXC OASIS operations harness using Amazon Bedrock, giving a single managed interface to multiple foundation models (Anthropic Claude, Amazon Nova, Meta Llama and open-weight families) with Bedrock Guardrails, AWS PrivateLink, serverless scaling and VPC-bound traffic. DXC separates the substrate (model access, uniform security and auditing) from its orchestration/harness layer; since GA in March 2026 DXC OASIS reportedly cut resolution time by 95% across 56 measured use cases and keeps customer prompts/completions inside the AWS data boundary.

7.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Taxbit embeds grounded, role-aware 'Taxbit Assist' AI agent on Amazon Bedrock AgentCore

Taxbit has deployed Taxbit Assist, a cited, permission- and role-aware AI assistant inside its compliance dashboard, built on Amazon Bedrock AgentCore and the Strands Agents SDK. The agent uses Bedrock Knowledge Bases with S3 Vectors for retrieval-augmented responses, Bedrock Guardrails for input screening, per-session isolation and AgentCore memory for context, emits OpenTelemetry traces to CloudWatch for evaluation, and is operated under ISO/IEC 42001 controls; Taxbit says it does not fine-tune models and Bedrock does not use prompts or completions to train models.

6.0

CODING · 1 SOURCE · AWS Machine Learning

Deep Insight demonstrates four-layer context engineering for production AI agents

Part 2 of the Deep Insight series describes a four-layer discipline for managing LLM context in production multi-agent workflows — isolating context architecturally, controlling it via prompts, externalizing to the filesystem, and verifying with agents/safeguards — and shows working code using the Strands Agents SDK and Amazon Bedrock AgentCore. The reference implementation (open source) reports major token savings in practice (a write-and-execute tool reduced per-script context by ~95% and on-demand skill loading cut system-prompt size by ~97%), addressing limits even with Anthropic Claude Sonnet 4.5's 200K-token window.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Condé Nast builds multimodal video discovery with Amazon Bedrock and TwelveLabs Marengo

Condé Nast partnered with the AWS Generative AI Innovation Center to build a multimodal video discovery system using TwelveLabs' Marengo embeddings via Amazon Bedrock and indexed in Amazon OpenSearch Service. The decoupled architecture — embedding generation on Bedrock and low-latency k-NN search on OpenSearch — enables intent-based, image-driven, and timestamped searches across transcripts, audio, and visuals, reducing average discovery time from ~250 minutes to under 2 minutes per task.

6.0