AI Agents & Automation

One is a format. The other is a discipline. Together, they might be how we finally make AI agents reliable. Continue reading on Medium »

As banks race to turn AI into enterprise-wide intelligence, Revolut's PRAGMA model offers a glimpse of where digital banking and financial services may be headi

Memory for agents is still early. There’s basically no standard for it yet, and ask five people what “memory” means and you’ll get five… Continue reading on Med

How autonomous agents are rewriting the platform engineering playbook Continue reading on Devops & AI Hub »

Over the past year, I’ve spent a lot of time following how companies are adopting AI for analytics. Continue reading on Medium »

Over the past year, I’ve spent a lot of time following how companies are adopting AI for analytics. Continue reading on Medium »

Learning about artificial intelligence during a professional development program in China. As AI continues to evolve, one lesson stands… Continue reading on Med

Anthropic extended Claude Fable 5 on paid plans through July 12. These 10 moves, from building Claude Skills to rebuilding Projects, create assets you keep afte

I've built and sold companies before. The pattern that repeats is this: the hardest part isn't the idea, it's the persistent context… Continue reading on Medium

PC Workman is a Windows system monitor with a fully offline AI assistant, built solo, in public, on a 2014 laptop between warehouse and welding shifts. This is

AI agents go beyond chatbots: they perceive a task, reason through clinical and payer rules, take an action inside the EHR or payer system, then verify the resu

Agentic AI ransomware is an extortion attack an LLM runs end-to-end — and JADEPUFFER, the first documented case, gave itself away by… Continue reading on Medium

This post walks through building a serverless image editor where users upload a photo, describe an edit in plain English, and receive the result in seconds. The

In this post, you build an AWS Support Companion using Amazon Bedrock AgentCore. The agent uses Strands Agents as the orchestration framework and connects to AW

In this post, we show how AWS Finance used chat agents and Flows in Amazin Quick to transform two of their most time-consuming workflows.

I am learning agentic AI using a customer support agent for an entertainment joint as a practical project. One of the capabilities needed… Continue reading on M

Gartner warned that over 40% of agentic AI projects may be canceled by 2027. The problem is governance, data access, ownership and ROI.

A full room for the TR Labs talk on evaluating agentic AI — Campus Oerlikon, University of Zurich. Continue reading on Thomson Reuters Labs »

The reliability math, the unplugged wires, and the rules I follow now Continue reading on Medium »

Organizations still running agentic pilots on top of legacy warehouses are behind on the infrastructure required to make AI accountable and scalable.

After completing the MindfulChat challenge, I continued exploring the Lakera Agent Breaker labs. This time, the focus shifts from Memory… Continue reading on Me

From a single chat box to models, research workbenches, and agents that run your analysis for you. Continue reading on Medium »

“Vibe coding” — the development paradigm where you build software by directing autonomous AI agents instead of typing out every single… Continue reading on Medi

Here are five practical steps business leaders can take to build an AI-positive corporate culture that encourages innovation while addressing risk, fear and unc

Winning a Customer Is Hard. Winning Them Back Is Even Harder. Continue reading on Medium »

The fifth and final post of the series: what building agentic systems taught me about the difference between a claim and a record. Continue reading on Medium »

It is usually not the model. It is the happy-path harness around the model: latency, retries, queues, stale retrieval, and the total lack… Continue reading on T

*Stop prompting agents. Start designing loops.* Continue reading on Medium »

Two AI tools tested for Blogger in 2026: England AI for speed vs Norway AI for storytelling Continue reading on Medium »

Centralize model governance without losing over a year of development velocity to building infrastructure from scratch. Engineering organizations routinely unde

Introduction: The Day I Stopped Trusting My Own Agent Continue reading on Medium »

Introduction: The Day I Stopped Trusting My Own Agent Continue reading on Medium »

What is a sub-agent, and when can it be used? Continue reading on Daily diaries »

In this post, we walk through how to get started with MiniMax models on Amazon Bedrock, including the capabilities supported by these models, the service tiers

Many AI initiatives fail not because of poor technology but because organizations lack shared definitions, context and decision-making frameworks. Here's why AI

A no-login alternative to ChatGPT, and why removing one small step changes everything Continue reading on Medium »

The one thing to take away Continue reading on Medium »

These cases are fewer in number, harder to predict and almost always end the same way: a field technician dispatch.

FIFA and Lenovo turned every 2026 World Cup player into a digital twin. The AI avatars now decide matches, and who owns them after July 19 is an open question.

Scribing is one-third of the workflow every visit runs through; it was the first domino to fall, but the next two are ready to be addressed.

OpenAI CEO Sam Altman called for a U.S.-led global AI standards body in the FT. A day later, the FT reported OpenAI offered the U.S. government a 5% stake worth

Google's Open Knowledge Format turns your website's ideas into a linked graph agents can traverse. Here's what that means for how machines understand your site.

For two years, the standard way to give a language model “search” was retrieval-augmented generation (RAG) wrapped in a hand-written agent… Continue reading on

For two years, the standard way to give a language model “search” was retrieval-augmented generation (RAG) wrapped in a hand-written agent… Continue reading on

A defense-in-depth approach for safely executing LLM-generated Python code in production AI systems. Continue reading on Medium »

A defense-in-depth approach for safely executing LLM-generated Python code in production AI systems. Continue reading on Medium »

The boardroom framing shift that changes how CFOs, CEOs, and enterprise leaders think about governing AI — with the data to back it up. Continue reading on Medi

How I adapted isnād–rijāl methodology from classical hadith science into a claim-level provenance framework for multi-agent AI systems —… Continue reading on Me