From LangGraph to AgentCore: A Practical Guide to Building Effective AI Agents
How orchestration frameworks, model reasoning, coordination, and managed runtimes fit together.
Read postAgentic systems
Orchestrating tools, reasoning, and multi-agent workflows.
Related skills
- LangGraph
- AWS Strands
- AgentCore
- Multi-agent orchestration
- MCP
Selected writing · 11
Choosing the Right AI Agent Framework — A 2025 Guide for Builders
A historical qualitative guide to agent libraries, platforms, and runtimes, with corrected portability and product categories.
Read post
Agent Frameworks Compared
A feature-by-feature comparison of LangGraph, LangChain, CrewAI, AWS Strands, Google ADK and deepagents, built as a decision matrix you can weight against your own needs.
Read post
Building Agents That Last: The Anatomy of Scalable AI Systems
When we talk about AI agents, it helps to think in human terms. A useful agent system needs a skeleton, hands, a mind, a brain, a library, a body, guardrails, and skin.That’s not poetry — it’s the anatomy of every serious agent framework being built today. And the leaders across Anthropic, OpenAI, Google, AWS, Microsoft, …
Read post
Building a Multi-Agent Orchestration System on AWS
Routing requests to the right specialist and executing each as a multi-step agentic task are two different jobs. This reference design treats the responsibilities separately.
Read post
Making Applications Model-Agnostic by Design
Routing only pays off if the application survives the swaps. What it takes to move between models without rewriting logic or shipping silent regressions.
Read post
Building an Agent Factory
SonderMind's input-middleware pipeline with three-tier routing, reported in a mental-health deployment, and the harness rules that generalise from it.
Read post
Designing Virtual Team Members
The intern model: agents as long-running specialists with a defined scope, one VM each, improving themselves over time.
Deep dive · AI Engineer World's Fair 2026Read post
Build Loops That Compound
Verification is what separates a loop that compounds from one that merely repeats — Sonar's case for verified agent loops, a control-theory recipe for loop design, and how to bound loops that spin out.
Deep dive · AI Engineer World's Fair 2026Read post
AI Engineer World's Fair 2026
Four days, 300 speakers, 39 tracks. Five themes carried across all of it: harness engineering and software factories, agent loops, evals and observability, the unsettled argument about agent memory, and the shift from burning tokens to proving value.
Read post
AI Minions at Scale: Orchestrating Chaos with Clarity
This is my breakdown of what AI tooling really feels like—part myth-busting, part field manual, and all grounded in lived experience. Spoiler: AI isn’t a magic wand. It’s a fleet of brilliant but forgetful minions. 🧩 Myth 1: “AI is a computer with a natural language interface.” False. This might be the most dangerous misconception …
Read post