Manuel Hernández Giuliani

  DeepSeek V4 Pro vs. Kimi K3: What Months of Real-World AI Agent Work Taught Me This article is based entirely on my personal experience using both models extensively through Pi.dev and my ARAYA framework. It is an independent research exercise, not a sponsored comparison, a reproduction of marketing claims, or an analysis based on technology news. This Is Not a Benchmark Most comparisons between artificial intelligence models begin with public benchmarks, release announcements, pricing tables, or carefully prepared demonstrations. My comparison began somewhere very different: inside real repositories, with incomplete context, conflicting documents, failing gates, distributed agent responsibilities, Git history , runtime evidence, and requirements that could not be considered complete merely because the generated code looked correct. Over several months, weeks, and many hours of intensive use, I worked with DeepSeek V4 Pro and Kimi K3 through Pi.dev while developing and operat...

 The AI industry may be entering a strange phase where narrative engineering advances faster than the underlying engineering itself. That does not mean frontier AI is fake. It is not. The progress is real. Models are improving quickly in coding, search, reasoning assistance, content generation, and cybersecurity analysis. Anyone working seriously in enterprise technology can already see the productivity impact. AI is becoming operationally useful. But something else is happening in parallel. Every few months, another company announces that its newest model is so powerful, so dangerous, or so transformative that humanity must proceed carefully. The language changes slightly each cycle, but the structure remains almost identical: existential concern, dramatic warnings, selective access, media amplification, institutional reaction, investor excitement, and another jump in valuation. At some point, it becomes reasonable to ask whether we are witnessing purely a technological revolution...

    This started while I was preparing my Big Data labs for my students. I wanted something closer to reality. Not only pipelines and Spark jobs, but how AI agents would actually interact with a governed data platform. So I set the environment as it should be in a serious setup. A lakehouse governed with AWS Lake Formation, metadata centralized in AWS Glue Data Catalog, and Spark handling execution. Clean, controlled, auditable. Then I added the missing piece. An agent that needs to understand intent and retrieve context, not just run queries. And almost immediately, the same request appeared. “We need a graph database for ontology.” In AWS terms, that means Amazon Neptune. I see this pattern often, not only with students. Also in real projects. Someone comes with a solution already decided. I always give the same answer. What is the business problem you are trying to solve? Because “I need Neptune” is not a requirement. It is a conclusion. When you force the conversation back...

There’s something powerful about seeing architecture come to life outside of slides and tools. Today I want to recognize Ahra, one of my students, who took the time to translate her understanding of our Big Data labs into a hand-drawn reference architecture. Not only is it correct in structure, but it reflects clarity of thought and ownership of the problem. From ingestion to Bronze using a dual pipeline pattern (batch and streaming), through data quality and standardization in Silver, to consumption-ready Gold for BI and AI use cases, she captured the full journey. Even more interesting, she extended the architecture into Labs 11 and 12, incorporating natural language AI agents capable of querying the data platform using skills, RAG, and process knowledge. This is exactly the mindset we aim for: not just using tools, but designing systems that solve real problems and enable business interaction through AI. Kudos to you, Ahra. This is the kind of thinking that builds real data architec...

Over the past few years, artificial intelligence has moved from promise to pervasive investment. Across industries, organizations have committed significant resources to AI initiatives. New models, new platforms, new capabilities. The pace of innovation has been extraordinary. And yet, a new question is emerging. Not what can we build with AI, but what is actually delivering measurable value. This shift marks an inflection point. We are entering a new phase of AI maturity. One defined not by experimentation, but by accountability. The Illusion of Progress From the outside, the landscape looks impressive. More models. More pilots. More demonstrations of capability. But inside many organizations, a different reality is taking shape. AI initiatives often remain disconnected from measurable business outcomes. Value is assumed, but not always quantified. Success is described in terms of activity, not impact. This is not a failure of technology. It is a reflection of something de...

Value Capture The Third Layer of the AI Story: Value Capture A reflection on how the AI economy is splitting between model builders and infrastructure enablers, and why long-term value will shift toward applications, agents, and business outcomes. In my previous reflections, I explored two dimensions of the current AI wave. First, the responsibility that comes with systems that act. Then, the unprecedented scale of infrastructure investment and its financial implications. There is now a third layer that completes the picture. The structure of value itself. We are starting to see a clear split in the AI economy. On one side, pure-play model companies are scaling rapidly. Revenue is growing at extraordinary speed, but so are losses, driven by compute, training, and inference. On the other side, hyperscalers and enablers are generating strong profits. But they are also committing to massive capital expenditure, with projections of $650–700 billion in AI infrastructure in 2026 al...