AI Agents & Automation

I've been immersed in agentic workflows for the past year, and I had a persistent feeling that something was missing — not in any particular product, but in how

You're in a meeting. Your phone rings. You ignore it. Fifteen minutes later, you check voicemail — "Hi, this is Dave from Acme Corp, we need to talk about our $

Using Claude & MCP servers to enhance genealogy research.

The "Product Manager" in the Machine As a Product Manager, my day-to-day usually involves roadmap alignment, user interviews, and prioritization. However, in my

The Cost Problem Nobody Warned You About Agentic AI is the hottest architectural pattern of 2026....

Two separate projects, now converging. Project 1 — Uracil Chain A blockchain built from...

AI agents are already too human. Not in the romantic sense, not because they love or fear or dream, but in the more banal and frustrating one. The current imple

By Dhananjay Yadav · Data Analyst II · May 2025 Continue reading on Medium »

Free version: Anthropic Owns the AI Supply Chain Continue reading on Medium »

By Sharath Sathish·April 2026 · ~14 min read·Read the preprint Continue reading on Medium »

The primary constraint in traditional kinetic operations has always been the biological limitation of the human analyst. Analysts are… Continue reading on Mediu

The primary constraint in traditional kinetic operations has always been the biological limitation of the human analyst. Analysts are… Continue reading on Mediu

A story about SOUL.md, identity verification, and what happens when your agent develops too much character. Continue reading on Medium »

We call him Hasselbott. Here's the playbook. We built an AI accountability system for our project managers. We named it Hasselbott for two reasons: it hassles y

Author: Maria Shimkovska If you came to our London tech event, you saw me walk through this as a...

Claude's Model Context Protocol (MCP) lets you add custom tools to your AI agent, but most MCP...

TL;DR I took the excellent ai-hedge-fund project — a multi-agent system where AI versions...

21 Apr Continue reading on Medium »

Deconstructing the orchestration layer for GenAI agents: From Infrastructure plumbing to scalable LLMOps patterns. Continue reading on Medium »

Deconstructing the orchestration layer for GenAI agents: From Infrastructure plumbing to scalable LLMOps patterns. Continue reading on Medium »

Let’s be honest. When Gartner drops a stat like “40% of agentic AI projects will fail by 2027,” most enterprise leaders nod their heads… Continue reading on Med

Let’s be honest. When Gartner drops a stat like “40% of agentic AI projects will fail by 2027,” most enterprise leaders nod their heads… Continue reading on Med

TL;DR I built a local AI gateway using Envoy, Rust, and Kubernetes to understand how AI traffic actually works. It broke multiple times. I fixed it. I learned a

Voice AI is having its second real moment . The first wave proved that machines could speak. This one is testing whether they can handle actual work. That is a

How to design agent personas that stay consistent, useful, and aligned with your workflow.

6 months, 16 niches, 2,069 real insights, and 13 fixes that made AI personas actually disagree with us.

How Your Team Uses AI Will Determine the Business You Build Continue reading on Medium »

From Gemini 3 Pro to the “Nanobanana” leak — the search giant just redrew the map of the digital economy. Here is your survival guide. Continue reading on Mediu

Most agent systems fail not because the LLM is wrong, but because memory is an afterthought. We spend...

Posted by the Corellis team — we're the folks behind CorellisOrg/corellis, an open-source...

Okay, folks, buckle up. The last four hours with Kiwi-chan have been… repetitive. We've hit a bit of a loop. She really wants to craft a chest, but keeps failin

"The future of AI is not just about retrieving information; it is about autonomous agents that can...

I spent a weekend wiring Claude directly into the Shopify Admin API to see how a custom agent...

A lot of GenAI products start in the same place. Continue reading on Medium »

If AI feels like it is moving too fast and you are falling behind, I felt that too and thought I needed to learn faster, until I realized… Continue reading on M

OpenAI is starting to look less like a startup and more like critical infrastructure, and that changes the threat model for everyone who… Continue reading on Me

OpenAI is starting to look less like a startup and more like critical infrastructure, and that changes the threat model for everyone who… Continue reading on Me

OpenAI is starting to look less like a startup and more like critical infrastructure, and that changes the threat model for everyone who… Continue reading on Me

5 Claude API mistakes that cost me money (and how I fixed them) I spent three months building with the Claude API directly before switching to a flat-rate wrapp

Zero-UI Architecture | Rahsi Framework™ Copilot as Interface. SharePoint as System Layer. Connect & Continue the Conversation If you are passionate about Mi

Building a cross-platform solution that supports multiple AI Agents sounds easy on paper. In reality?...

Agent tooling is getting powerful. But something interesting happens when you start running many...

**The Problem: The 15-Day Bottleneck **Most people think insurance innovation is about a better...

Every developer wants subagents now. One agent for testing, one for docs, one for refactors, one for...

If you've spent more than a weekend building an AI-driven workflow, you've probably hit this wall:...

Why the next AI breakthrough is a systems problem, not a model problem Continue reading on Artificial Intelligence in Plain English »

Why the next AI breakthrough is a systems problem, not a model problem Continue reading on Artificial Intelligence in Plain English »

The best coaching has always been about judgment under pressure. AI doesn't replace that. It raises the stakes for it. Continue reading on Artificial Intelligen