kamal

AgentOps: Operationalize agentic AI at scale with Amazon Bedrock AgentCore

by

When you build agentic AI solutions, you face unique operational challenges. Agents make unpredictable decisions, costs spiral unexpectedly, and debugging non-deterministic failures seems impossible. Agentic AI applications don’t just execute predetermined workflows. They reason, adapt, and make autonomous decisions, and DevOps practices need to be adapted. That’s where AgentOps comes in, the operational discipline for … Read more

Accelerate LLM model loading and increase context windows with GPUDirect on Amazon FSx for Lustre and TurboQuant

by

If you’re iterating on deploying large language models (LLMs) on AWS GPU instances, you’ve probably noticed the larger the model to be loaded into GPU High Bandwidth Memory (HBM), the longer the painful wait until the GPUs are ready for inference. As models grow to hundreds of billions of parameters and GPU environments grow ever … Read more

Amazon Quick integration with time-series databases for market intelligence using MCP

by

Model Context Protocol (MCP) integration in Amazon Quick transforms how financial analysts access time-series market intelligence, removing the need for complex database queries. As a financial analyst, you navigate millions of stock trades flowing through markets every second, searching for patterns that drive trading decisions. Financial institutions often use time series databases to analyze high-frequency … Read more

What Burndown Charts Miss About Real Software Delivery

by

This article argues that common software-delivery metrics such as burndown charts, velocity tracking, and percentage-complete estimates misrepresent how software is actually built. Because development is exploratory, nonlinear, and shaped by discovery, the author contends that demos, narratives, and shipped outcomes provide a more accurate picture of progress than process metrics designed primarily for reporting and … Read more

Platform Engineering Will Eat Software Engineering and That’s a Good Thing

by

I’ve been watching a slow convergence over the past 3 years and I think it’s time to name it. Platform engineering is not a specialisation of software engineering. It is becoming the context in which all software engineering happens. The distinction that used to exist product engineers who build features, platform engineers who build the … Read more

How to Architect a Scalable AI Tech Stack

by

The rapid evolution of artificial intelligence has fundamentally transformed how businesses operate, compete, and deliver value to their customers. At the heart of this transformation lies a critical yet often overlooked element: the AI tech stack. Building intelligent solutions requires more than just cutting-edge algorithms or massive datasets. It demands a carefully architected foundation that … Read more

Your MVP Is Probably Too Big

by

A lot of MVPs stop being “minimum” somewhere around the second planning session. A dashboard gets added because investors might ask for it. Permissions because enterprise customers may eventually need them. Analytics because every serious product has analytics. A settings page. An admin panel. An onboarding flow with tooltips. And slowly, the product stops being … Read more