The Blog
Writing on agentic AI.
Practical, honest pieces on building and designing agentic AI systems. Field notes from production work, written for engineers, architects, and technology leaders.
- Jun 23 2026
AI Agent Observability Is Not Just Logs
Logs tell you what the system did. Agent observability tells you why it decided wrong. Here is what to observe, what to evaluate, and what to instrument first.
- Jun 17 2026
Why Most Agentic AI Demos Fail in Production
A demo proves an agent can work once. Production asks whether it works repeatedly, safely and within budget. The four gates that decide whether it ships.
- Jun 17 2026
From Deflection to Resolution: How IVA Is Rewiring the Contact Center
Legacy IVR was built to deflect callers. Intelligent virtual agents should resolve them. Why that shift re-prices who wins the contact center in 2026.
- Jun 11 2026
Happy Agents, Better CX: The Signal Your Dashboard Skips
A viral heart-rate experiment ranked the meetings that stressed an engineer most. It points at the CX signal almost no dashboard tracks, and how to use it.
- May 26 2026
Agent Failure Modes Interviewers Probe: Tool Misuse, Loops, Prompt Injection
Senior interviewers do not ask how agents work. They ask how agents break. The seven failure modes that decide most agentic AI system-design rounds.
- May 26 2026
How to Answer "Design an Agentic System" in a System-Design Interview
A playbook for the agentic system-design interview: the seven-part structure interviewers want, a worked example, and the answers that get people rejected.
- May 26 2026
Giving Your Agent Memory: A Minimal Implementation
Memory is one word for four different problems your agent has. Conversation buffer, summarization, episodic recall and semantic retrieval, built from scratch.
- May 26 2026
Tool Calling From First Principles (Before You Touch LangChain)
Function calling, demystified. How a model actually calls a tool, a 40-line example with no framework, and the four things that go wrong in production.
- May 24 2026
The Four Steps of the Agent Loop: Perceive, Decide, Act, Observe
Perceive, decide, act, observe: the four steps of the agent loop, why some courses call the second step reason, and what breaks when each one fails.
- May 24 2026
Agentic AI Interview Questions: 30 Real Questions with Production Answers (2026)
Thirty questions you actually get in a senior agentic AI engineering interview, with production answers from someone who has shipped these systems.