Test Pyramid for AI Agents
Traditional testing assumes that given the same input, you get the same output. Agents break that assumption immediately. Learn how the test pyramid evolves when verifying agentic software.
Karpathy’s LLM Wiki as Agent Memory
A practical look at how Karpathy’s LLM Wiki pattern can serve as long term agent memory, turning raw sources, markdown pages, and schema instructions into a living knowledge system for semantic, entity, episodic, summary, and procedural memory.
Agent Memory
When we talk about agent memory, I don't think we really consider what memory actually is. In this piece, I look at various types of memory and explore ways to implement them.
3 Design Principles for Creating Agent Skills
How to design effective agent skills when codifying tribal knowledge
Stop Closing the Door. Fix the House.
I've been seeing more and more open source maintainers throwing [...]
Building an Agentic Engineering Org
About 95% of our engineers are regularly using AI to assist with their development efforts. They are mostly working outside of the IDE, with many running 3-5 agent instances in parallel. Then there's a small population that is actively building our internal agent orchestrator in preparation for the inevitable.
How 7 AI Agents Worked Together to Build an App in One Hour
What if I told you that you could build a [...]
Agents, Subagents, and Multi Agents: What They Are and When to Use Them
A straightforward explanation of agents, subagents, and multi-agents, and how agents are organized to work together
Did Skills Kill MCP?
An overview of Agent Skills vs MCP
MCPs for Developers Who Think They Don’t Need MCPs
Lately, I've seen more developers online starting to side eye [...]
MCP Sampling: When Your Tools Need to Think
Learn how MCP Sampling lets your tools call the AI instead of the other way around.
How I Taught GitHub Copilot Code Review to Think Like a Maintainer
Open source maintainers are getting more contributions than ever, thanks to AI-assisted coding. That's great for community growth but it also means a flood of PRs to review. Here's how I taught GitHub Copilot Code Review to think like a maintainer.
How DevRel is Leading AI Adoption
As AI reshapes how we develop software, DevRel professionals find themselves not just promoting tools, but helping entire communities navigate uncharted territory.
5 Boring Tasks I Gave to My AI Agent Today (That Saved Me Hours)
Forget the flashy demos. Here's everyday use cases for AI.
3 Prompts to Test for Agent Readiness
A series of prompts to test an LLM's capabilities to be used with AI agents
How I Use Goose to Plan My Week with Asana and Google Calendar MCPs
Use MCPs with Goose to automate task management and enhance productivity.
6 Essential Tips for Working with Goose
Practical tips to help you use Goose more effectively and efficiently.
Agentic AI and the MCP Ecosystem
A 101 introduction to AI Agents
Wait, are we just handing over system access to the AI agents?
David Fowler recently asked an excellent question that’s been on [...]
Connecting AI Agents to Your Systems with MCP
Learn how MCP standardizes integrations and fosters an ecosystem for the future of AI-enabled tools