Objective The goal of this post is to show, with real numbers from a working system, how to decide whether an agentic system should be a single agent or multiple agents working together. I’ve read about cases where multi-agent systems helped, for example: Anthropic’s research system: a lead agent sends several research agents to investigate … Continue reading Multi-Agent Design Patterns: When Do They Actually Help?→
AI agents kept the crawl and dropped the readers. What the data from Cloudflare and TollBit shows, what the industry is building to let agents pay for content, and what still has to happen for creators to keep publishing on the open web.
Objective In Part 1, I compared ways to choose which model should answer a support request. This post continues that experiment with a second decision: how long should that model choice last—a whole conversation or just one question? The small pilot illustrates a method, not a general recommendation. I compared four policies on six new … Continue reading Model Routing, Part 2: Choosing the Scope→
Objective How do you choose a model router for your own application? I tested six classifiers on a marketplace support agent to compare cost against answer quality. This small study demonstrates the decision process, not a general ranking of products. Both GPT-5 nano and GPT-5 answered 18 support cases: 16 single-turn and two two-turn cases, … Continue reading Model Routing, Part 1: Choosing a Classifier→
I built a daily AI digest using Jev to classify posts and Claude to summarize the best ones—for about four cents a day. This post walks through the architecture, measured cost savings, quality checks, and practical trade-offs of scheduling the workflow with GitHub Actions and Claude Code routines.
Token price, benchmark scores, model size, and context windows can all be misleading. Here are seven common model-selection misconceptions—and the real-world examples that challenge them.
We created Model Academy to connect concepts that are often taught separately—model weights, inference systems, and GPU execution. This is the story behind the academy, our complementary perspectives, and why we chose an interactive approach to explain how AI models produce answers.
Deterministic CI tools should produce the evidence. AI should generate targeted probes, interpret the combined results, and help the human reviewer decide where to focus.
I tested three AI code review approaches on the same pull request defects to understand what each option gives you, what you must build yourself, and where the real tradeoffs are.
AI-native coding assessments should not ban AI or allow unlimited delegation. SignalLoop explores a third model: constrain collaboration, adapt assessments at the role level, and evaluate the engineering process through evidence.
The first article in this series, Enterprise AI Adoption: Requirements for Security, Governance, and Scale, defined the problem: enterprises consume AI through coding tools, standalone hosted applications, custom agents, and enterprise knowledge systems, but need consistent controls across identity, credentials, data, cost, providers, and operations. The second article, A Reference Architecture for Governed Enterprise AI, … Continue reading Prescribed Enterprise AI Architectures for Small, Mid-Size, and Large Organizations→
In the first article in this series, Enterprise AI Adoption: Requirements for Security, Governance, and Scale, we identified four ways enterprises consume AI and seven requirements that apply across them. Those requirements cover identity, non-human credentials, cost governance, security and data controls, model flexibility, optimization, and observability. This article translates those requirements into a reference … Continue reading A Reference Architecture for Governed Enterprise AI→
AI adoption inside enterprises rarely begins with a coordinated platform strategy. It usually starts with individuals and teams selecting tools that solve immediate problems. A developer subscribes to an AI coding assistant. Another team builds an application using a foundation-model API. Employees begin using standalone cloud applications such as ChatGPT, Claude, Gemini, or Codex. A … Continue reading Enterprise AI Adoption: Requirements for Security, Governance, and Scale→
A perspective from the data layer of humanoid robot training I recently spent time working on egocentric video data — first-person footage of humans doing everyday things with their hands — and how it could be used to train humanoid robots. It’s a narrow problem, but it forced me to answer a bigger question: what … Continue reading VLAs Are Winning. World Models Will Win.→
AI assistants are no longer just chat windows. The same assistant now appears as a web app, desktop app, mobile app, browser extension, IDE extension, command-line tool, local agent, and cloud worker. That is powerful, but it creates a new problem: deciding which interface to use, and keeping context alive when moving between them. This … Continue reading AI Assistants Have Many Interfaces. Context Is the Real Product.→
AI coding tools are now good enough that the question is no longer “Should I use them?” For me, the more useful question is: how do I use them without letting LLM cost grow unnecessarily? The obvious answer is to use cheaper models. That helps, but it is not the full answer. In practice, the bigger … Continue reading My Multi-Agent Coding Setup to Lower LLM Cost→
✨ Summary Large Language Models (LLMs) have powered the AI wave of the last 3–4 years. While most are closed-source, a vibrant ecosystem of open-weight and open-source models has emerged. As a long-time AI user, I wanted to peek under the hood: how do GenAI models work, and what happens when you actually run them … Continue reading 🖥️ Running Local LLMs: Experiments and Insights→
I have been using Perplexity’s Comet browser for the past two weeks, and it has completely changed the way I use browsers 🌐. I’ve been a Chrome user for as long as I can remember, but after trying out Comet for two weeks, I finally made it my default browser ✅. Comet functions not just … Continue reading AI Browsers Are Here — My Experience with Perplexity’s Comet→
Introduction I have been a Cursor user for vibe coding for 3 months. I was very skeptical about using Claude Code and Gemini CLI at first, since I wasn’t comfortable with the idea of using a terminal as an AI agent. But in the last 1–2 months, I’ve been trying them both — and it … Continue reading The Rise of CLI-Based AI Coding Agents: Claude code vs Gemini CLI→