Deploying quantized models on Amazon SageMaker AI with Unsloth
In this post, you will learn four deployment patterns for taking models that have already been quantized with Unsloth and deploying them on AWS infrastructure. The…
Cloud & Big Tech 400 stories
How KTern.AI built agentic AI for SAP on Amazon Bedrock AgentCore
Evolving from a traditional software as a service (SaaS) platform into a next-generation agentic AI platform meant orchestrating multiple specialized agents across long-running enterprise programs. Each…
Disaggregated prefill and decode for LLM inference on SageMaker HyperPod
In this post, we show how to implement DPD with vLLM on Amazon SageMaker HyperPod using the HyperPod Inference Operator.
The Ambulatory Intelligence Gap
Ambulatory care, the outpatient clinics and physician practices where most patients...
Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies
This paper was accepted at the AI4TCI (Workshop on AI for Secure and Trustworthy Critical Infrastructure Systems) Workshop at the International Conference on Availability, Reliability and…
Ask, build, compose: What our 5th Genie Hackathon taught us about Databricks Genie
How Databricks hackathons workWe run these hackathons for a simple reason: the fastest...
Frontier models and production agents: Advancing Microsoft Foundry for the agentic era
Introducing OpenAI's latest frontier model series, the Asia Pacific Data Zone, and product agent capabilities, all generally available in Microsoft Foundry. The post Frontier models and…
MCP tool design: Practical approaches and tradeoffs
In this post, we show where MCP tool design goes wrong and how to fix it with practical context engineering approaches.
Enhancing enterprise inference on Amazon SageMaker HyperPod with data capture, Hugging Face, NVMe, and Route 53 integration
In this post, we walk through five capabilities now available in SageMaker HyperPod inference: multi-tier data capture for auditing and model improvement, direct deployment from Hugging…
Capturing token IDs during agentic interactions for better reinforcement learning
A new Rust proxy called Turnstile sits between the model backend and the agent harness to capture information lost in mere text transcripts.
Incentivizing Temporal-Awareness in Egocentric Video Understanding Models
Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning depends…
Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information…
Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under which it is…
Introducing Claude apps gateway for AWS
Today, we're announcing the Claude apps gateway for AWS, a self-hosted control plane that gives organizations a single point of control over access, cost, and policy…
Navigating a Synapse Migration to Databricks
Azure Synapse has served as a reliable foundation for SQL analytics at scale, and...
Powering scientific discovery: BYOKG and GraphRAG for intelligent pharmaceutical research
In this post, we explore how Graph-based Retrieval Augmented Generation (GraphRAG) is transforming scientific research by combining graph databases with generative AI. With this approach, you…
Automatically sort and prioritize your mailboxes by using Amazon Bedrock
In this post, we show how organizations in the public sector can automate their email management using a generative AI solution powered by Amazon Bedrock.
Building and connecting a production-ready ecommerce MCP server using Amazon Bedrock AgentCore and Mistral AI Studio
In this post, you build and connect that server end to end. You will implement MCP tools, set up two-layer JSON Web Token (JWT) authentication, deploy…
Benchmarking Coding Agents on Databricks’ Multi-Million Line Codebase
At Databricks, the way we build software is changing quickly as we aggressively adopt...
Built to bounce back: How Azure resiliency evolved
Cloud resiliency is about ensuring systems can adapt, recover, and keep functioning within real-world constraints. The post Built to bounce back: How Azure resiliency evolved appeared…
Securing Amazon Bedrock AgentCore Runtime with AWS WAF
This post shows you two architecture patterns that address this problem. Both use an internet-facing ALB with AWS WAF and route traffic through a VPC Interface…
Manage AI applications on Mac with Jamf’s AI Governance and Amazon Bedrock
In this post, we show how you can use Jamf’s AI Governance with Amazon Bedrock to configure, deploy, and validate managed settings for AI applications across…
How to Evaluate an Enterprise Analytics Platform
Most enterprise analytics evaluations are really just dashboard comparisons. That's...
How Imperial College London is accelerating dementia research with a modern data platform
Imagine being unable to tell your doctor whether you're in pain or running a fever...