Blog_dumb

AI as accessibility: what happened when a neurodivergent solutions architect stopped fighting his brain and started building. In this post, I share how AI serves as an accessibility tool for neurodivergent professionals. The system is built on Amazon Quick on your desktop, an AI-powered desktop and web assistant that compensates for executive function gaps every […]

This post is co-written with Vijay Venkatesh, CTO at Bluesight. If you build software for hospitals, you know that compliance work scales poorly. Hospitals managing 340B Drug Pricing Program compliance face a compounding data problem. Proving that a Group Purchasing Organization (GPO) purchased drug qualifies for an exception requires cross-referencing each purchase against several sources

When you deploy generative AI agents into multi-tenant production architectures, you face a specific identity problem: when an agent calls a downstream API on behalf of a user, whose identity travels with the call? Running the call as the agent’s service identity collapses the audit trail, because every downstream system must trust the agent unconditionally.

Deploying generative AI models to production requires finding the right combination of instance type, serving container with settings, and optimization strategy. This process typically requires a long iteration cycle of optimization and manual benchmarking. In April 2026, Amazon SageMaker AI launched this inference recommendations, so customers can programmatically get data-driven, production-ready configurations through APIs. This

Model customization transforms general-purpose AI models into specialized enterprise assets. By fine-tuning foundation models (FMs) on domain-specific data, businesses teach AI their unique workflows, terminology, and deep domain specialization, along with strict adherence to brand voice and fewer hallucinations. For enterprises, this is more than an optimization. It’s the creation of proprietary intellectual property. A

In dentistry, image quality determines whether a claim is paid or denied. Up to 20 percent insurance claims are initially denied, with missing or low-quality images among the leading causes. Yet quality assessment has traditionally been a manual, after-the-fact process. A clinician reviews an X-ray hours or days after capture, discovering problems only when a

In this post we show how to build a semantic layer on AWS using Stardog’s Semantic AI Application over Amazon Aurora and Amazon Redshift, and how to run a Strands Agents agent on Amazon Bedrock AgentCore that queries the layer to answer customer 360 questions across both sources without extract, transform, and load (ETL). The

An artificial intelligence (AI) agent can process an invoice, help adjudicate a claim, or classify a support ticket in a proof of concept. But running these agents across thousands or even millions of work items in a production environment introduces an entirely different set of challenges. At enterprise scale, success depends on much more than

This post was co-written with Daniel Han and Michael Han from Unsloth. Deploying large foundation models (FMs) stored at their original 16-bit floating-point precision (BF16 or FP16) is expensive. They need large GPU instances, driving up serving costs, and slowing down iteration cycles. Quantization addresses this by reducing the numerical precision of a model’s weights

When Model Context Protocol (MCP) tools underperform, the cause is rarely the protocol itself but the tool design. Many teams start by exposing an existing API as-is and trusting the agent to figure out the rest. It is a natural way to extend APIs to agentic systems and generative AI coding tools. For straightforward use