As field engineers at Databricks, we spend our days inside enterprise AI deployments,...

Messi wanted this empty room to feel a little more like him, but wasn’t sure where to start. So he asked ChatGPT for some ideas. Try it yourself: “Reimagine this room in my style. Surprise me.”

November 3, 2026 — A quiet day lets us share some behind the senes.

Some agent-evaluation questions are narrow and repeatable, and decision models answer exactly that kind of question. This post shows how to connect two decision models, Jev and Strands Decider, to Amazon Bedrock AgentCore Evaluations through code-based evaluators, and how to v…

As artificial intelligence and accelerated computing continue to push the boundaries of what's possible, the latest NVIDIA CUDA release arrives to unlock... As artificial intelligence and accelerated computing continue to push the boundaries of what’s possible, the latest NVID…

Data Mining & Modeling

Marketers shouldn’t have to wait for a new dashboard to understand how a campaign is performing. In an early pilot with OpenAI, Figma is building shared context that helps marketers ask how campaigns are landing and whether they’re converting customers. Teams can get useful in…

Marketers shouldn’t have to wait for a new dashboard to understand how a campaign is performing. In an early pilot with OpenAI, Figma is building shared context that helps marketers ask how campaigns are landing and whether they’re converting customers. Teams can get useful in…

A Siemens report estimates that unplanned downtime costs an average large plant in the surveyed sectors $253 million per year. Whether investigating a failed... A Siemens report estimates that unplanned downtime costs an average large plant in the surveyed sectors $253 million…

Our first open model economy research note for paid subscribers.

Smart Approvals in Amazon Quick reviews eligible agent actions within your existing controls, reducing unnecessary approval prompts while keeping consequential decisions with a person. See how policy sets the boundary, how a classifier reviews actions, and how AWS CloudTrail a…

In production AI agents, context management is the real bottleneck. This post presents a four-layer context engineering framework (architecture, prompts, file-based tools, and verification agents), implemented in working code from Deep Insight, an open source multi-agent data …

This post explores how Indegene built a production-grade, LLM-powered Data Quality Agent in its NEXT Unified Data Platform on AWS. The agent generates context-aware data quality rules, validates them, and produces ready-to-run SQL and Python under human-in-the-loop governance,…

U Mobile, Malaysia's newest 5G network provider, built AiDaH, an agentic AI operations platform on Amazon Bedrock AgentCore that moves beyond AI assistance to autonomous action across telco operations. Nine months after production launch, AiDaH handles over 150 operational sce…

Turn production evidence into prioritized issues and custom evaluations that help you improve prompts, tools, models, memory, skills, and harness code. When you... Turn production evidence into prioritized issues and custom evaluations that help you improve prompts, tools, mod…