marcosomma

I am building a small experiment inspired by Stripe Minions. Not related to OrKa. This is a different...

I saw a video today that made me laugh, then made me a bit worried. It was one of those jokes that...

A Two-Stage Curator That Pays for Itself I watched Claude Code feed 108,894 bytes of seq 1 20000...

This is a follow-up to I Tried to Turn Agent Memory Into Plumbing Instead of Philosophy. If you...

There is a special genre of AI idea that sounds brilliant right up until you try to build it. It...

People usually talk about intelligence as if it starts with language, tools, or raw brainpower. I do...

I have spent the last year trying to talk about AI as an engineering discipline. Not AI as a content...

For a long time, “senior developer” was a fairly consistent signal. You expected someone who could...

Let’s start with a statement that should be obvious but still feels controversial: Large Language...

I have always loved one idea in machine learning. The idea that you can sharpen a model by forcing...

The confession I spent the first six months of serious AI pair programming producing what...

Music taught me that “coordination” is not a metaphor. It is a physical constraint. You can feel it...

A branch-only experiment that stress-tests custom agent registration, trust boundaries, and...

I Built a Multiagent Workflow to Understand My Impostor Syndrome A dark, dry, self-deprecating field...

Building a useful AI assistant is no longer about a single clever prompt. Once you have tools,...

Evaluating LLM agents is messy. You cannot rely on perfect determinism, you cannot just assert...

Why OrKa 0.9.10 Wraps GenAI Inside Deterministic Systems I will start bluntly. I like generative...

I have been working with AI for a while now. Not as a tourist. Not as a weekend hacker. Deep in it....

Introduction Modern veterinary medicine often deals with complex clinical cases that...

Cognition, for me, did not start in a lab or a code editor. It started in a field, in the mud,...

I think I have a strange "talent" that is both a gift and a curse. I tend to see certain problems...

Over the past 8 months I have been quietly building my own cognition layer for AI systems. Not a...

TLDR: GraphScout explores candidate reasoning paths, Plan Validator grades those plans across...

OrKa is not a chatbot kit. It is a modular cognitive architecture that executes graphs of purpose...

I rewrote a big slice of OrKa’s documentation after some painfully honest feedback. The summary of...

When One AI Agent Isn't Enough Imagine you're building a research assistant. You ask your...

TL;DR Orcas live in tight family groups, speak with recognizable accents, learn skills from elders,...

TLDR: final agent is always logged, GraphScout multi hop paths execute completely, timestamps are ISO...

Introduction Believing in a theory that runs against the dominant paradigm is never easy....

Introduction When I first started building OrKA-reasoning, I quickly realized a recurring...