All Articles
Archive
28 posts spanning 2025–2026
My AI Agent Passed Every Check. 67% of It Was Wrong.
My AI agent's report passed every validation check. 67% of its facts were wrong. Here are 3 detection layers I built ...
Why AI Agents Hallucinate: Search Returns Headlines, APIs Fix It
My AI agent got 10 of 15 financial claims wrong using web search. Switching to structured APIs fixed every one. Here'...
Why Local LLMs Hallucinate When Your AI Agent Has Search
Local models got 10 of 15 financial claims wrong, even with web search. The root cause: search returns headlines, not...
The Production AI Agent Playbook: 8 Disciplines for Reliable LLM Systems
A practical playbook for building AI agents in production. Architecture, error handling, monitoring, security, and co...
Monitoring AI Agents in Production: 4 Layers That Actually Catch Failures
Four monitoring layers I added to my AI agent after a 709K-character runaway slipped past every health check. Here's ...
How to Test AI Agents Before They Break Production
Unit tests aren't enough for AI agents. Learn the three testing layers that prevent hallucinations and tool failures ...
MCP Server Security: 8 Vulnerabilities I Found and Fixed
SSRF, prompt injection, path traversal: I audited my MCP server (3,000+ downloads) and found 8 vulnerabilities. Every...
How to Reduce AWS Lambda Costs: 10 Practical Tips
10 practical tips to cut your AWS Lambda bill, from hidden CloudWatch costs to memory right-sizing, Graviton2, and kn...
How to Build an MCP Server in Python with FastMCP 3.0 (Full Code)
Notes MCP server in Python with FastMCP 3.0: tools, resources, prompts, SQLite persistence, and in-process testing. U...
No articles found for this topic.