Akshay Parkhi's Weblog

On ai-agents 43 physical-ai 18 ...

Recent

Feb. 12, 2026

IAM Permissions for BedrockAgentCoreApp Observability

Your AgentCore runtime role needs these permissions to emit logs, traces, and metrics:

[... 144 words]

6:57 pm / ai-agents

CloudWatch Log Streams for BedrockAgentCoreApp

When you deploy an agent with AWS Bedrock AgentCore, two types of log streams appear in CloudWatch:

[... 127 words]

6:39 pm / ai-agents

Jan. 28, 2026

What BedrockAgentCoreApp Does Internally

It’s Starlette (not FastAPI)!

[... 176 words]

4:14 pm / ai-agents

ClawdBot—Setup

Setup Claude bot using the tutorial below:

[... 127 words]

2:11 pm / ai-agents

Amazon Strands Agent Hooks—AgentInitializedEvent

It’s a notification that says “Hey, the agent is ready!”

[... 89 words]

3:24 am / ai-agents

Jan. 27, 2026

My First Blog

10:48 am

«« first « previous page 3 / 3

Highlights

OpenUSD: Advanced Patterns and Common Gotchas. - March 28, 2026
OpenUSD Mastery: From Composition to Pipeline — A SO-101 Arm Journey - March 25, 2026
Learning OpenUSD — From Curious Questions to Real Understanding - March 19, 2026
7 Mental Models for Building Agent Skills (From Anthropic's Internal Playbook) - March 18, 2026
From Prompt Engineering to Harness Engineering: Building Infrastructure for Autonomous Agents - March 18, 2026
The Agent Loop Iceberg — 10 Hard Problems Hiding Beneath the Simple Loop - March 15, 2026
Autoresearch and Context Rot — How a Stateless Agent Loop Avoids Memory Problems (And Where It Breaks) - March 13, 2026
How Skills Work in AI Agents — From Lazy-Loading Instructions to LLM Attention Weights - March 13, 2026
Coding in the AI Agent Age — Why Typing Code Is Dying But Engineering Is Thriving - March 13, 2026
Mental Models in the AI Agent Age - March 13, 2026
I Ran 100 Parallel Tool Calls on AgentCore — The microVM Didn't Break, But the LLM Did - March 12, 2026
The 95% Rule: Why Your Agent Is Slow and How to Prove It - March 12, 2026
What Actually Happens When You Call invoke_agent_runtime() - March 12, 2026
Inside an AgentCore microVM — Ports, Cold Starts, and the Sidecar Pattern - March 12, 2026
AgentCore Runtime vs Lambda — Scaling, Warm Pools, and Why Fixed 8 GB Boxes Exist - March 11, 2026
How Firecracker MicroVMs Power AgentCore Runtime — From 125ms Boot to Auto-Scaling AI Agents - March 11, 2026
How Everything Connects — NVIDIA's Cosmos Pipeline from Simulation to Real-World Robots - March 11, 2026
The Complete Beginner's Guide to Robotics — From Your First Camera to Foundation Models - March 10, 2026
From Webcam to Robot Brain: How Vision-Language Models and Vision-Language-Action Models Actually Work - March 9, 2026
10 Hidden Concepts in Strands SDK Hooks That You Won't See by Reading the Code - March 9, 2026
Top Claude Code Skills: What 20 YouTube Videos and 2.3M Views Agree On - March 9, 2026
Build a Research Engine in Claude Code: YouTube Search → NotebookLM → Synthesized Insights in 5 Minutes - March 9, 2026
playwright-cli: How to Give Your AI Coding Assistant a Real Browser - March 9, 2026
Context Engineering for AI Agents: 6 Techniques from Claude Code, Manus, and Devin - March 9, 2026
Multi-Agent Is Two Problems: Why TypeScript and Python Each Win Half" - March 8, 2026
Why Every Coding Agent Is TypeScript (And Every ML Framework Is Python) - March 8, 2026
Why .md Files Are the Agent: How ClawdBot Turns Markdown Into a Living Assistant - March 8, 2026
OpenClaw vs Claude Code Agent Teams — Architecture Comparison - March 8, 2026
OpenClaw / ClawdBot Architecture — How a Telegram AI Bot Actually Works - March 8, 2026
Agentic Engineering Patterns — Key Takeaways from Simon Willison's Guide - March 8, 2026
How AWS Strands Hooks Work - March 7, 2026
How AWS Strands Agent Loop Works - March 7, 2026
How Claude Team Agents ACTUALLY Connect — No Fluff - March 7, 2026
How Pi Builds Its System Prompt at Runtime — And the Innovations That Make It Stand Out - March 7, 2026
Scaling Agents: The Definitive Open-Source Guide — From 1 Agent to 100 Agents, 1 Tool to 100 Tools, Managing Context - March 7, 2026
Finding the Perfect Prompt: Combining DSPy's Optimization with Strands Agents for Cost-Effective Multi-Agent Systems - March 6, 2026
How to Save 90% on Agent Token Costs with Prompt Caching on AWS Bedrock - March 5, 2026
Complete Guide: Setting Up XRoboToolkit for Robot Teleoperation with Pico 4 Ultra on WSL2 - March 5, 2026
XR-Robotics with Pico 4 Ultra: VR Teleoperation Setup from Headset to Robot Simulation - March 4, 2026
ROS 2 Humble: Complete Installation Guide with Turtlesim from Zero to First Node - March 2, 2026