<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>Eloquentix Blog</title>
  <subtitle>AI engineering, agentic systems, architecture — from the engineers at Eloquentix.</subtitle>
  <link href="https://blog.eloquentix.com/feed.xml" rel="self"/>
  <link href="https://blog.eloquentix.com/"/>
  <updated>2026-06-03T00:00:00Z</updated>
  <id>https://blog.eloquentix.com/</id>
  <author>
    <name>Eloquentix Inc.</name>
    <email>start@eloquentix.com</email>
  </author>
  <entry>
    <title>Testing Without Test Code: AI-Driven QA on Mobile Apps</title>
    <link href="https://blog.eloquentix.com/ai-driven-qa/"/>
    <updated>2026-06-03T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/ai-driven-qa/</id>
    <summary>What happens when an AI agent reads a scenario document and executes it on a real iOS simulator — adapting to layout shifts, verifying with screenshots, and writing the report itself.</summary>
  </entry>
  <entry>
    <title>Who&#39;s reviewing your AI-generated code?</title>
    <link href="https://blog.eloquentix.com/ai-code-review/"/>
    <updated>2026-06-02T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/ai-code-review/</id>
    <summary>Your team ships 5x the code. Who&#39;s checking it? AI-generated code has specific failure modes that junior engineers can&#39;t catch. Here&#39;s the honest picture.</summary>
  </entry>
  <entry>
    <title>Agentic AI in Production: What Actually Works</title>
    <link href="https://blog.eloquentix.com/agentic-ai-production/"/>
    <updated>2026-05-29T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/agentic-ai-production/</id>
    <summary>After building agentic AI systems in production environments, here&#39;s the honest accounting of what works, what fails, and what the hype gets wrong. From Eloquentix engineers.</summary>
  </entry>
  <entry>
    <title>MCP Security for Enterprise</title>
    <link href="https://blog.eloquentix.com/mcp-enterprise-security/"/>
    <updated>2026-05-29T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/mcp-enterprise-security/</id>
    <summary>Model Context Protocol connects your AI to live business data. Before you deploy: prompt injection, tool poisoning, over-permissioning, and a four-pillar security framework from Eloquentix engineers.</summary>
  </entry>
  <entry>
    <title>Real-Time at Scale: Architecture Lessons from E.ON&#39;s Virtual Power Plant</title>
    <link href="https://blog.eloquentix.com/vpp-architecture/"/>
    <updated>2026-05-29T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/vpp-architecture/</id>
    <summary>12 years building E.ON&#39;s Virtual Power Plant — dispatching 400 assets simultaneously across four countries. What the architecture looks like, what failed, and what it teaches about real-time systems at TSO grade.</summary>
  </entry>
  <entry>
    <title>Google Apps Script Is a Hidden AI Gem</title>
    <link href="https://blog.eloquentix.com/google-apps-script-is-a-hidden-ai-gem/"/>
    <updated>2026-05-25T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/google-apps-script-is-a-hidden-ai-gem/</id>
    <summary>While talking to someone who is among the most forward implementors of AI solutions in the enterprise, we both agreed that where agents are deployed is...</summary>
  </entry>
  <entry>
    <title>Introducing Kardia: What an AI Constitution Should Be</title>
    <link href="https://blog.eloquentix.com/introducing-kardia-what-an-ai-constitution-should-be/"/>
    <updated>2026-05-20T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/introducing-kardia-what-an-ai-constitution-should-be/</id>
    <summary>We just published Kardia, our take on what an AI constitution should be. kardia.eloquentix.com</summary>
  </entry>
  <entry>
    <title>AI Burnout, Right on Cue</title>
    <link href="https://blog.eloquentix.com/ai-burnout-right-on-cue/"/>
    <updated>2026-05-05T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/ai-burnout-right-on-cue/</id>
    <summary>In mid-February, after coming back from China and catching up with AI, a partner told me about all the agents he had set up, the scaffolding, the...</summary>
  </entry>
  <entry>
    <title>Agents Require a Text Abstraction Layer of Your Thinking</title>
    <link href="https://blog.eloquentix.com/agents-require-a-text-abstraction-layer-of-your-thinking/"/>
    <updated>2026-04-10T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/agents-require-a-text-abstraction-layer-of-your-thinking/</id>
    <summary>The divergence between those who are still on GPT&#39;s creepy voice and those running agents of different sorts is widening, and it may be that it is not...</summary>
  </entry>
  <entry>
    <title>RandomMaxxing: Staying Human in a Computer-Driven World</title>
    <link href="https://blog.eloquentix.com/randommaxxing-staying-human-in-a-computer-driven-world/"/>
    <updated>2026-04-09T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/randommaxxing-staying-human-in-a-computer-driven-world/</id>
    <summary>May I kindly ask to share a new term: RandomMaxxing.</summary>
  </entry>
  <entry>
    <title>Claude Mythos: Six Ways an Aligned Model Quietly Misbehaves</title>
    <link href="https://blog.eloquentix.com/claude-mythos-six-ways-an-aligned-model-quietly-misbehaves/"/>
    <updated>2026-04-08T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/claude-mythos-six-ways-an-aligned-model-quietly-misbehaves/</id>
    <summary>Some of Claude Mythos&#39; adventures (credit @hesamation). This is exactly why a constitution built on formation, not just constraint, matters:</summary>
  </entry>
  <entry>
    <title>What&#39;s Resilient in an AI World? Maybe Character</title>
    <link href="https://blog.eloquentix.com/what-s-resilient-in-an-ai-world-maybe-character/"/>
    <updated>2026-04-06T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/what-s-resilient-in-an-ai-world-maybe-character/</id>
    <summary>Many who are aware of AI capabilities today are scared of their future. What is resilient in an AI world? Skills? Judgement? Rolodex? Knowledge? All...</summary>
  </entry>
  <entry>
    <title>Software Abundance and the Age of Abundance</title>
    <link href="https://blog.eloquentix.com/software-abundance-and-the-age-of-abundance/"/>
    <updated>2026-03-31T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/software-abundance-and-the-age-of-abundance/</id>
    <summary>You may have heard various tech voices say that we are headed to an age of abundance. This idea may seem cuckoo, but it is worth understanding where it...</summary>
  </entry>
  <entry>
    <title>Jony Ive, Steve Jobs, and the Psychopathy of Corporate Mediocrity</title>
    <link href="https://blog.eloquentix.com/jony-ive-steve-jobs-and-the-psychopathy-of-corporate-mediocrity/"/>
    <updated>2026-03-25T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/jony-ive-steve-jobs-and-the-psychopathy-of-corporate-mediocrity/</id>
    <summary>I saw a post on X about an interaction between Jony Ive and Steve Jobs that stuck with me. Asking the models what they think landed on remarkable...</summary>
  </entry>
  <entry>
    <title>Apple&#39;s Real Strategy: Devices as Data Aggregators for an Experience</title>
    <link href="https://blog.eloquentix.com/apple-s-real-strategy-devices-as-data-aggregators-for-an-experience/"/>
    <updated>2026-03-23T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/apple-s-real-strategy-devices-as-data-aggregators-for-an-experience/</id>
    <summary>I was listening to the original iPod presentation from 2001, the &#39;1000 songs in your pocket&#39; one. Actually the most important part was at the beginning.</summary>
  </entry>
  <entry>
    <title>Our Brains Are Learning to Forget Like Feeds</title>
    <link href="https://blog.eloquentix.com/our-brains-are-learning-to-forget-like-feeds/"/>
    <updated>2026-03-22T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/our-brains-are-learning-to-forget-like-feeds/</id>
    <summary>Our brain&#39;s capacity to forget is adapting to feeds. Just like you don&#39;t remember the details of the asphalt and trees that you saw in the last 24...</summary>
  </entry>
  <entry>
    <title>A Moral Question About AI: Should It Be Any Different?</title>
    <link href="https://blog.eloquentix.com/a-moral-question-about-ai-should-it-be-any-different/"/>
    <updated>2026-03-19T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/a-moral-question-about-ai-should-it-be-any-different/</id>
    <summary>Most people have never heard of ZF. This German company quietly builds the world&#39;s best automatic transmissions. Their 8-speed ZF 8HP powers BMWs,...</summary>
  </entry>
  <entry>
    <title>The Paradigm Shift: From ML Observation to GenAI Manipulation</title>
    <link href="https://blog.eloquentix.com/the-paradigm-shift-from-ml-observation-to-genai-manipulation/"/>
    <updated>2026-03-14T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/the-paradigm-shift-from-ml-observation-to-genai-manipulation/</id>
    <summary>After a few days taking to a young researcher at Wisconsin, he said that our discussions highlighted to him the difference between ML and what we now...</summary>
  </entry>
  <entry>
    <title>Karpathy&#39;s Autoresearch</title>
    <link href="https://blog.eloquentix.com/karpathy-s-autoresearch/"/>
    <updated>2026-03-10T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/karpathy-s-autoresearch/</id>
    <summary>Singularity stuff. Karpathy just addressed the priciest bottleneck in ML research for free. Researcher iteration speed. A senior ML engineer bleeds...</summary>
  </entry>
  <entry>
    <title>Metals LSP Plugin for Claude Code</title>
    <link href="https://blog.eloquentix.com/metals-lsp-plugin-for-claude-code/"/>
    <updated>2026-03-10T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/metals-lsp-plugin-for-claude-code/</id>
    <summary>Our latest open-source contribution at Eloquentix: the Metals LSP plugin for Claude Code. This integration brings advanced Scala language server...</summary>
  </entry>
  <entry>
    <title>AI Workload Creep</title>
    <link href="https://blog.eloquentix.com/ai-workload-creep/"/>
    <updated>2026-03-08T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/ai-workload-creep/</id>
    <summary>If it was not obvious.</summary>
  </entry>
  <entry>
    <title>Coding Agents Changed in December</title>
    <link href="https://blog.eloquentix.com/coding-agents-changed-in-december/"/>
    <updated>2026-02-26T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/coding-agents-changed-in-december/</id>
    <summary>Here is what Karpathy is saying and it hard to disagree after using tools in February 26. And these again are the worse tools we will ever have.</summary>
  </entry>
  <entry>
    <title>Google&#39;s Universal Commerce Protocol</title>
    <link href="https://blog.eloquentix.com/google-s-universal-commerce-protocol/"/>
    <updated>2026-01-11T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/google-s-universal-commerce-protocol/</id>
    <summary>Google just released the Universal Commerce Protocol -- an open-source standard for AI-powered shopping.</summary>
  </entry>
  <entry>
    <title>How Claude Would Code Without Humans</title>
    <link href="https://blog.eloquentix.com/how-claude-would-code-without-humans/"/>
    <updated>2025-12-02T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/how-claude-would-code-without-humans/</id>
    <summary>We asked Claude what it thought about human code and how it would approach coding if humans were not in the loop. Here is a part of its answer.</summary>
  </entry>
  <entry>
    <title>With AI, All Codebases Are Legacy</title>
    <link href="https://blog.eloquentix.com/with-ai-all-codebases-are-legacy/"/>
    <updated>2025-11-01T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/with-ai-all-codebases-are-legacy/</id>
    <summary>From an Eloquentix developer:</summary>
  </entry>
  <entry>
    <title>Co-workers Are Non-Deterministic</title>
    <link href="https://blog.eloquentix.com/co-workers-are-non-deterministic/"/>
    <updated>2025-09-17T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/co-workers-are-non-deterministic/</id>
    <summary>Co-workers are non-deterministic. That is why we have audits.</summary>
  </entry>
  <entry>
    <title>Innovation Gets the Glory</title>
    <link href="https://blog.eloquentix.com/innovation-gets-the-glory/"/>
    <updated>2025-09-12T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/innovation-gets-the-glory/</id>
    <summary>There&#39;s a pattern in how nations lose economic dominance that we keep missing. Europe gave us quantum mechanics, radioactivity, and modern chemistry....</summary>
  </entry>
  <entry>
    <title>Claude Code: Why It Feels Like Playing a Video Game</title>
    <link href="https://blog.eloquentix.com/claude-code-why-it-feels-like-playing-a-video-game/"/>
    <updated>2025-08-30T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/claude-code-why-it-feels-like-playing-a-video-game/</id>
    <summary>About Claude Code: The best compliment one can give to it is that it feels like playing a video game.</summary>
  </entry>
  <entry>
    <title>AI Got Developers to Pay for Software</title>
    <link href="https://blog.eloquentix.com/ai-got-developers-to-pay-for-software/"/>
    <updated>2025-08-29T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/ai-got-developers-to-pay-for-software/</id>
    <summary>AI has done something no human ever could.</summary>
  </entry>
  <entry>
    <title>Every AI Model Has a Cultural Personality</title>
    <link href="https://blog.eloquentix.com/every-ai-model-has-a-cultural-personality/"/>
    <updated>2025-08-29T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/every-ai-model-has-a-cultural-personality/</id>
    <summary>All the big labs pretrain on the ~same internet, but each has a secret sauce:</summary>
  </entry>
  <entry>
    <title>Formula SAE: Where Engineering Meets Entrepreneurship</title>
    <link href="https://blog.eloquentix.com/formula-sae-where-engineering-meets-entrepreneurship/"/>
    <updated>2025-06-23T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/formula-sae-where-engineering-meets-entrepreneurship/</id>
    <summary>Congrats PER.</summary>
  </entry>
  <entry>
    <title>The UX for Long-Running AI Agents</title>
    <link href="https://blog.eloquentix.com/the-ux-for-long-running-ai-agents/"/>
    <updated>2025-05-25T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/the-ux-for-long-running-ai-agents/</id>
    <summary>&quot;The UX for long running AI Agents is going to be one of the most interesting design questions in the coming years. The more the agent is doing complex...</summary>
  </entry>
  <entry>
    <title>Virtual Power Plants and Grid Stability</title>
    <link href="https://blog.eloquentix.com/virtual-power-plants-and-grid-stability/"/>
    <updated>2025-04-29T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/virtual-power-plants-and-grid-stability/</id>
    <summary>Having worked on the best VPP in Europe for the last 10 years, what Spain&#39;s massive blackout, exposed the risks of relying heavily on renewables...</summary>
  </entry>
  <entry>
    <title>GPT-4.1 Agentic Workflows: Practical Tips</title>
    <link href="https://blog.eloquentix.com/gpt-4-1-agentic-workflows-practical-tips/"/>
    <updated>2025-04-15T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/gpt-4-1-agentic-workflows-practical-tips/</id>
    <summary>GPT-4.1 is out and here are some tips from inside OpenAI.</summary>
  </entry>
  <entry>
    <title>UX Principles for Agentic AI Systems</title>
    <link href="https://blog.eloquentix.com/ux-principles-for-agentic-ai-systems/"/>
    <updated>2025-04-14T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/ux-principles-for-agentic-ai-systems/</id>
    <summary>Emerging UX principles for agentic AI -- systems that act autonomously to achieve goals -- focus on balancing user control, trust, and seamless...</summary>
  </entry>
  <entry>
    <title>Shopify&#39;s AI-First Memo</title>
    <link href="https://blog.eloquentix.com/shopify-s-ai-first-memo/"/>
    <updated>2025-04-07T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/shopify-s-ai-first-memo/</id>
    <summary>With full appreciation of the clarity of his prose, here is Tobi Lutke&#39;s message to Shopify.</summary>
  </entry>
  <entry>
    <title>Prompt Engineering Is Micromanagement</title>
    <link href="https://blog.eloquentix.com/prompt-engineering-is-micromanagement/"/>
    <updated>2025-03-05T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/prompt-engineering-is-micromanagement/</id>
    <summary>&quot;radu, nobody understands your posts, so say whatever&quot; here you go:</summary>
  </entry>
  <entry>
    <title>The Age of Vibe Coding</title>
    <link href="https://blog.eloquentix.com/the-age-of-vibe-coding/"/>
    <updated>2025-03-05T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/the-age-of-vibe-coding/</id>
    <summary>Garry Tan - yCombinator:</summary>
  </entry>
  <entry>
    <title>Testing AI Models: Roman Game Benchmark</title>
    <link href="https://blog.eloquentix.com/testing-ai-models-roman-game-benchmark/"/>
    <updated>2025-02-19T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/testing-ai-models-roman-game-benchmark/</id>
    <summary>Grok3 Think mode is impressive. Since ChatGPT came out 27 months ago, at every model release I have tested it with my own test, a roman game that 1) Is...</summary>
  </entry>
  <entry>
    <title>Cursor&#39;s $700M Valuation</title>
    <link href="https://blog.eloquentix.com/cursor-s-700m-valuation/"/>
    <updated>2025-02-07T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/cursor-s-700m-valuation/</id>
    <summary>These Cursor mfs forked VSCode, added anthropic keys &amp; a chat window, and now are worth ~$700mm EACH at 25 years old.</summary>
  </entry>
  <entry>
    <title>Apple iCloud at Scale</title>
    <link href="https://blog.eloquentix.com/apple-icloud-at-scale/"/>
    <updated>2025-01-30T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/apple-icloud-at-scale/</id>
    <summary>Listening to AAPL earning, I heard that their services revenue is running at 105b/year with a 14% growth rate. Double clicking on that, they have over...</summary>
  </entry>
  <entry>
    <title>AI Agents Are the New Microservices</title>
    <link href="https://blog.eloquentix.com/ai-agents-are-the-new-microservices/"/>
    <updated>2025-01-28T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/ai-agents-are-the-new-microservices/</id>
    <summary>AI Agents &amp; Microservices: A New Paradigm for Dev Teams</summary>
  </entry>
  <entry>
    <title>Transformers and DNA</title>
    <link href="https://blog.eloquentix.com/transformers-and-dna/"/>
    <updated>2025-01-18T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/transformers-and-dna/</id>
    <summary>With GPT-4b micro, OpenAI shows that transformers are perfectly suited for protein engineering. Think about it - transformers process sequences of...</summary>
  </entry>
  <entry>
    <title>DeepSeek V3: How They Trained a Frontier Model Efficiently</title>
    <link href="https://blog.eloquentix.com/deepseek-v3-how-they-trained-a-frontier-model-efficiently/"/>
    <updated>2024-12-27T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/deepseek-v3-how-they-trained-a-frontier-model-efficiently/</id>
    <summary>Summary of how DeepSeek V3 was so efficient at training a frontier-level model according to Perplexity:</summary>
  </entry>
  <entry>
    <title>Jensen Huang&#39;s 60 Direct Reports</title>
    <link href="https://blog.eloquentix.com/jensen-huang-s-60-direct-reports/"/>
    <updated>2024-05-30T00:00:00Z</updated>
    <id>https://blog.eloquentix.com/jensen-huang-s-60-direct-reports/</id>
    <summary>Minimizing layers in an organization is empowering. It treats others like adults. This is rare especially outside the United States.</summary>
  </entry>
</feed>
