March 2026
46 posts: 46 entries
March 1, 2026
How a VLA Controls a Robot Arm: GR00T N1.5 System Architecture from Camera to Motor
I built a robot arm system that uses NVIDIA’s GR00T N1.5, a Vision-Language-Action (VLA) model. The system picks up objects from a table with only a camera, natural language instructions, and 50 demonstration episodes. After it worked end-to-end, I wanted to record the full system architecture for anyone who wants to understand how all the pieces connect.
[... 909 words]March 2, 2026
OpenTelemetry for AI Agents: How the Strands SDK Instruments Traces, Metrics, and Token Usage
I explored the Strands Agents SDK and found a comprehensive, production-ready OpenTelemetry integration built in. That surprised me. If you build AI agents and want visibility into what actually happens at runtime, this is worth understanding. By runtime I mean model calls, tool executions, latencies, and token usage.
[... 1,377 words]RDF, ROS, and Sim-to-Real: Understanding Robot Description Files
When you start to work with robot simulation, you immediately meet a file called something.urdf. This is true whether you use Isaac Sim, Gazebo, or MoveIt. It’s one of those things that seems simple on the surface but connects to everything in the robotics stack. Here’s a clear breakdown of what URDF is, what it isn’t, and how it fits alongside ROS.
ROS 2 Humble: Complete Installation Guide with Turtlesim from Zero to First Node
This is a complete walkthrough for installing ROS 2 Humble on Ubuntu 22.04 and running your first robot simulation with Turtlesim. I wrote this after I completed the process myself. The official docs are thorough but scattered across many pages. This puts everything in one place, from locale setup to writing your first Python node.
[... 2,194 words]March 4, 2026
XR-Robotics with Pico 4 Ultra: VR Teleoperation Setup from Headset to Robot Simulation
I configured XR-Robotics with a Pico 4 Ultra headset to teleoperate robot arms in simulation. The later goal is to collect demonstration data for imitation learning. The setup covers a PC that runs Ubuntu, a Python teleoperation stack, and a VR headset that acts as the human interface. Here’s the complete step-by-step guide.
[... 2,637 words]March 5, 2026
Complete Guide: Setting Up XRoboToolkit for Robot Teleoperation with Pico 4 Ultra on WSL2
A step-by-step guide to XR-based robot teleoperation with the Pico 4 Ultra headset, XRoboToolkit, and MuJoCo simulation. Everything runs on Windows WSL2.
[... 1,293 words]How to Save 90% on Agent Token Costs with Prompt Caching on AWS Bedrock
How I reduced my AI agent’s input token costs by 90% with prompt caching on AWS Bedrock. Includes real pricing data and hands-on examples that use Strands Agents.
[... 2,661 words]March 6, 2026
Finding the Perfect Prompt: Combining DSPy’s Optimization with Strands Agents for Cost-Effective Multi-Agent Systems
How we used Bayesian optimization to find better prompts automatically, and how that made cheap models perform like expensive ones.
[... 2,453 words]March 7, 2026
Scaling Agents: The Definitive Open-Source Guide — From 1 Agent to 100 Agents, 1 Tool to 100 Tools, Managing Context
Tool Wall: Every tool’s JSON schema goes into the system prompt. At 15+ tools, models start selecting wrong tools. At 50+, token usage explodes and accuracy plummets.
[... 4,460 words]How Pi Builds Its System Prompt at Runtime — And the Innovations That Make It Stand Out
A close look at the open-source coding agent that assembles its brain on the fly.
[... 2,937 words]How Claude Team Agents ACTUALLY Connect — No Fluff
Agents are separate processes. They don’t share memory. They don’t call each other’s functions. They communicate through files on disk and CLI commands that Claude Code provides as tools.
[... 2,393 words]How AWS Strands Agent Loop Works
Strands uses the ReAct pattern. This is a recursive loop:
[... 672 words]How AWS Strands Hooks Work
Hooks are an event-driven extensibility system — a way to inject custom logic at specific points in the agent lifecycle without modifying core code. Think of them as middleware/interceptors.
[... 713 words]March 8, 2026
Agentic Engineering Patterns — Key Takeaways from Simon Willison’s Guide
Simon Willison recently published an excellent guide on agentic engineering patterns. It collects practical lessons from building with AI coding agents. Here are the key takeaways that matter most for AI agent developers, distilled from his full guide.
[... 583 words]OpenClaw / ClawdBot Architecture — How a Telegram AI Bot Actually Works
OpenClaw (ClawdBot) is a Telegram bot powered by Claude Opus. It delivers daily AI news digests, runs scheduled jobs, and maintains persistent conversations. Here’s the full architecture and how every piece connects.
[... 1,205 words]OpenClaw vs Claude Code Agent Teams — Architecture Comparison
OpenClaw and Claude Code Agent Teams share DNA:
[... 1,188 words]Why .md Files Are the Agent: How ClawdBot Turns Markdown Into a Living Assistant
You’d expect an AI agent to consist of code: Python classes, orchestration frameworks, complex pipelines. But ClawdBot (OpenClaw) does something different. Its agent is mostly .md files sitting in a folder. Plain text. Markdown. The kind of thing you’d write documentation in.
[... 1,516 words]Why Every Coding Agent Is TypeScript (And Every ML Framework Is Python)
Every major coding agent uses TypeScript: Claude Code, OpenCode, Pi, Amp. None of them uses Python. This isn’t a coincidence. It’s architecture. To understand why, you need to start with the origin stories.
[... 2,989 words]Multi-Agent Is Two Problems: Why TypeScript and Python Each Win Half"
Will multi-agent be done better in JavaScript than Python? No. They solve different types of multi-agent. This is the most important distinction nobody is making clearly enough.
[... 1,364 words]March 9, 2026
Context Engineering for AI Agents: 6 Techniques from Claude Code, Manus, and Devin
I studied how production AI agents like Claude Code, Manus, and Devin actually work. The single most important concept is not prompt engineering. It is context engineering: the art of controlling exactly what goes into the model’s context window, and what stays out.
[... 2,126 words]playwright-cli: How to Give Your AI Coding Assistant a Real Browser
If you use Claude Code (or any AI coding assistant), there’s a tool that makes browser automation easy: playwright-cli. It’s a command-line wrapper around Microsoft’s Playwright. It lets you control a real browser from your terminal: navigate pages, click buttons, fill forms, take screenshots, and scrape content. Here’s how to install and configure it, and why it’s genuinely useful.
[... 1,108 words]Build a Research Engine in Claude Code: YouTube Search → NotebookLM → Synthesized Insights in 5 Minutes
I built a research engine inside Claude Code. It searches YouTube, feeds results into Google NotebookLM, and lets me query across all the sources. All of this happens without leaving the terminal. Here’s exactly how it works and how to build it yourself.
[... 1,186 words]Top Claude Code Skills: What 20 YouTube Videos and 2.3M Views Agree On
I researched 20 YouTube videos on Claude Code skills. I added all of them to Google NotebookLM and asked it to synthesize the top skills across every source. Here’s the result. The ranking uses two measures: how often the videos mentioned each skill, and how impactful creators found it.
[... 860 words]10 Hidden Concepts in Strands SDK Hooks That You Won’t See by Reading the Code
The Strands SDK hook system looks simple on the surface. You register a callback, and you receive an event. But there are 10 hidden concepts buried in the design that you’ll never see by just reading the code. Here’s what actually happens under the hood.
[... 1,391 words]From Webcam to Robot Brain: How Vision-Language Models and Vision-Language-Action Models Actually Work
I built a webcam app that sends live frames to Claude and GPT-4o for real-time scene understanding. Along the way, I discovered how fundamentally different this is from what robots like OpenVLA do with the same camera input. Here’s the full pipeline. It starts with photons that hit your webcam sensor and ends with tokens that come back from the cloud.
[... 1,770 words]March 10, 2026
The Complete Beginner’s Guide to Robotics — From Your First Camera to Foundation Models
This is everything you need to go from zero to building, sensing, and coding robots at home. We’ll go in this order:
[... 4,214 words]March 11, 2026
How Everything Connects — NVIDIA’s Cosmos Pipeline from Simulation to Real-World Robots
Training robots and autonomous vehicles is fundamentally dangerous and expensive. You can’t crash 1,000 cars to teach collision avoidance. You can’t let a robot fall off cliffs to learn edge detection. NVIDIA’s solution is an end-to-end pipeline that generates synthetic data. The data is so realistic that AI models trained on it transfer directly to the real world. Here’s how every piece connects.
[... 1,777 words]How Firecracker MicroVMs Power AgentCore Runtime — From 125ms Boot to Auto-Scaling AI Agents
AWS needed to run Lambda functions: millions of them, at the same time, for strangers on the internet. Containers were not isolated enough, and full VMs were too slow. So AWS built Firecracker, a microVM that boots in ~125 milliseconds with ~5 MB of memory overhead. It gives you hardware-level isolation and lets you pack thousands of microVMs onto a single server. Now Amazon Bedrock AgentCore Runtime uses the same technology to run AI agent tools. Here’s exactly how it all works.
[... 2,562 words]AgentCore Runtime vs Lambda — Scaling, Warm Pools, and Why Fixed 8 GB Boxes Exist
Amazon Bedrock AgentCore Runtime uses Firecracker microVMs to run AI agent tools in isolated environments. But if you used Lambda before, it sounds familiar: serverless, auto-scaling, pay-per-use. So why does AgentCore exist? Here is the complete picture:
[... 1,540 words]March 12, 2026
Inside an AgentCore microVM — Ports, Cold Starts, and the Sidecar Pattern
When you deploy an agent on Amazon Bedrock AgentCore Runtime, your Docker container runs inside a Firecracker microVM. But what actually happens inside that microVM? Here’s the complete picture:
[... 1,408 words]