Skip to main content

AI Tech & Automation Blog

Amazon Bedrock Prompt Optimization Drives LLM Applications Innovation for Yuewen Group
Apr 22, 2025
8 min

Amazon Bedrock Prompt Optimization Drives LLM Applications Innovation for Yuewen Group

Yuewen Group is a global leader in online literature and IP operations. Through its overseas platform WebNovel , it has attracted about 260 million users in ove
Build a FinOps agent using Amazon Bedrock with multi-agent capability and Amazon Nova as the foundation model
Apr 19, 2025
12 min

Build a FinOps agent using Amazon Bedrock with multi-agent capability and Amazon Nova as the foundation model

AI agents are revolutionizing how businesses enhance their operational capabilities and enterprise applications. By enabling natural language interactions, thes
Add Zoom as a data accessor to your Amazon Q index
Apr 18, 2025
11 min

Add Zoom as a data accessor to your Amazon Q index

For many organizations, vast amounts of enterprise knowledge are scattered across diverse data sources and applications. Organizations across industries seek to
Palantir’s Blueprint for Early Career Success in Product Design
Apr 18, 2025
9 min

Palantir’s Blueprint for Early Career Success in Product Design

Editor’s Note: Product Designers are key members of Palantir product teams. This blog post features a banner by Product Designer Sarah, a self-reflection by Pro
Automate Amazon EKS troubleshooting using an Amazon Bedrock agentic workflow
Apr 17, 2025
13 min

Automate Amazon EKS troubleshooting using an Amazon Bedrock agentic workflow

As organizations scale their Amazon Elastic Kubernetes Service (Amazon EKS) deployments, platform administrators face increasing challenges in efficiently manag
Clario enhances the quality of the clinical trial documentation process with Amazon Bedrock
Apr 16, 2025
8 min

Clario enhances the quality of the clinical trial documentation process with Amazon Bedrock

This post is co-written with Kim Nguyen and Shyam Banuprakash from Clario. Clario is a leading provider of endpoint data solutions to the clinical trials indust
Build multi-agent systems with LangGraph and Amazon Bedrock
Apr 15, 2025
13 min

Build multi-agent systems with LangGraph and Amazon Bedrock

Large language models (LLMs) have raised the bar for human-computer interaction where the expectation from users is that they can communicate with their applica
Build, Don't Beg: A Builder's Guide to Synthetic Audiences
Apr 14, 2025
3 min

Build, Don't Beg: A Builder's Guide to Synthetic Audiences

Relying on real user data is a bottleneck. It's time to build your own infinitely configurable synthetic audiences with powerful, free open-source tools.
Building an AIOps chatbot with Amazon Q Business custom plugins
Apr 12, 2025
10 min

Building an AIOps chatbot with Amazon Q Business custom plugins

Many organizations rely on multiple third-party applications and services for different aspects of their operations, such as scheduling, HR management, financia
Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)
Apr 12, 2025
5 min

Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)

Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. However, as LLMs have improved, so have the attacks against them. P
Next 25 developer keynote: From prompt, to agent, to work, to fun
Apr 12, 2025
11 min

Next 25 developer keynote: From prompt, to agent, to work, to fun

Attending a tech conference like Google Cloud Next can feel like drinking from a firehose — all the news, all the sessions, and breakouts, all the learning and
New GKE inference capabilities reduce costs, tail latency and increase throughput
Apr 11, 2025
4 min

New GKE inference capabilities reduce costs, tail latency and increase throughput

When it comes to AI, inference is where today’s generative AI models can solve real-world business problems. Google Kubernetes Engine (GKE) is seeing increasing
Reduce ML training costs with Amazon SageMaker HyperPod
Apr 11, 2025
14 min

Reduce ML training costs with Amazon SageMaker HyperPod

Training a frontier model is highly compute-intensive, requiring a distributed system of hundreds, or thousands, of accelerated instances running for several we
Delivering an application-centric, AI-powered cloud for developers and operators
Apr 10, 2025
11 min

Delivering an application-centric, AI-powered cloud for developers and operators

Today we're unveiling new AI capabilities to help cloud developers and operators at every step of the application lifecycle. We are doing this by: Putting appli
Implement human-in-the-loop confirmation with Amazon Bedrock Agents
Apr 10, 2025
12 min

Implement human-in-the-loop confirmation with Amazon Bedrock Agents

Agents are revolutionizing how businesses automate complex workflows and decision-making processes. Amazon Bedrock Agents helps you accelerate generative AI app
How iFood built a platform to run hundreds of machine learning models with Amazon SageMaker Inference
Apr 9, 2025
17 min

How iFood built a platform to run hundreds of machine learning models with Amazon SageMaker Inference

Headquartered in São Paulo, Brazil, iFood is a national private company and the leader in food-tech in Latin America, processing millions of orders monthly. iFo
How Netflix Accurately Attributes eBPF Flow Logs
Apr 9, 2025
11 min

How Netflix Accurately Attributes eBPF Flow Logs

By Cheng Xie , Bryan Shultz , and Christine Xu In a previous blog post , we described how Netflix uses eBPF to capture TCP flow logs at scale for enhanced netwo
Repurposing Protein Folding Models for Generation with Latent Diffusion
Apr 9, 2025
6 min

Repurposing Protein Folding Models for Generation with Latent Diffusion

PLAID is a multimodal generative model that simultaneously generates protein 1D sequence and 3D structure, by learning the latent space of protein folding model
Llama 4 family of models from Meta are now available in SageMaker JumpStart
Apr 8, 2025
23 min

Llama 4 family of models from Meta are now available in SageMaker JumpStart

Today, we’re excited to announce the availability of Llama 4 Scout and Maverick models in Amazon SageMaker JumpStart and coming soon in Amazon Bedrock. Llama 4
Prompting for the best price-performance
Apr 5, 2025
16 min

Prompting for the best price-performance

In the drive to remain competitive, businesses today are turning to AI to help them minimize cost and maximize efficiency. It’s incumbent on them to find the mo