Articles
About muraco.ai
muraco.ai is a blog about how AI actually gets used in work and everyday life, viewed from both hands-on organizational practice and personal product building. It focuses on practical ways of working with AI, AI development and implementation, and internal AI adoption.
Read moreWhat GPT-5.4, the Codex App, and Codex Security Reveal About OpenAI's Direction
Looking at GPT-5.4, the Codex app, and Codex Security from the week of March 2, 2026 together, this article explains how OpenAI appears to be moving beyond conversational and coding AI toward supporting a wider range of work.
Read moreWhat Is OpenAI Codex Security? I Tried It and Was Impressed by How Naturally It Leads to a Fix PR
I tested OpenAI Codex Security on a real GitHub repository and reviewed the full flow from security scanning to fix PR creation. This post covers a concrete SSRF finding and why the experience feels promising for AI-driven development.
Read moreWhat Is Harness Engineering? Designing the Rails That Keep AI Agents Stable
This post explains harness engineering as the outer structure that keeps AI agents stable during long-running, multi-step work. Based on practice, it covers initial alignment, design documents, checklists, handoff notes, review, and the rails around AI-assisted execution.
Read moreInternal AI Adoption Does Not Move Forward with Training Alone
In this rollout, sharing why AI mattered before training turned out to be especially important. Based on a real rollout in an organization of about 70 people, this post looks back on meaning-making, access distribution, and usage observation.
Read moreHow AI Agents Work: Models, Harnesses, Context, and Tools
This article explains how AI agents work and why similar requests can produce different results, using four elements: models, harnesses, context, and tools.
Read moreHow to Use AI Without Losing Yourself: What to Delegate vs. What Not to Delegate
While using AI to refine a product concept, the explanation became more polished even as the reason I wanted to build it in the first place slowly faded into the background. Based on that failure, this article looks at what people should keep in their own hands, what they can delegate to AI, and how to think about that split through Why, What, and How.
Read moreThe First Step in AI-Driven Process Improvement Is to Break Down the Workflow
A common first move in AI-driven process improvement is to look for tasks AI can replace. This article argues for a different starting point: break the workflow down first, redesign as much of it as possible deterministically, and use AI only where it truly belongs.
Read moreHow to Give AI the Context It Needs for Work: A Practical Introduction to Context Engineering
When AI misses the mark at work, the problem is often not prompt phrasing but missing context. Using examples like meeting notes and slide writing, this article explains how to think about the information AI needs and frames that habit as a practical introduction to context engineering.
Read moreWhy I Started Thinking of AI as a Team
This article explains why I stopped thinking of AI as just a tool and started using it as something that works alongside me through clear roles. Drawing on my own experience, I explore why I began thinking of AI as a team.
Read more