7 min read
Your LLM Judge Is Untested Code
Your agent has tests. The thing grading them doesn't. Five rules for a judge you can trust.
Tagged Agents
8 articles on Agents.
8 min read
Your AI Agent Has No Stack Trace. Here's How to Debug It Anyway.
The 4 observability decisions to make before launch: trace every step, one ID end to end, five numbers on a dashboard, and logs that link to the trace.
6 min read
6 MCP Servers That Make My Coding Agent Actually Useful in 2026
The MCP servers I actually reach for when building features and shipping production apps.
8 min read
5 Resilience Patterns for AI Agents
Checkpoints, scoped retries, idempotent tools, and run budgets: how production agents survive the failure math of 20-step loops.
9 min read
7 Identity Patterns for AI Agents in Production
Your agent isn't a user. Stop authenticating it like one.
8 min read
The 3 Layers of Testing AI Agents
Mock the model and your suite goes green while testing nothing. Here's what to run instead, from unit tests to live alerts.
9 min read
Don't Start With Multi-Agent
One good agent beats five mediocre ones. Here's the pressure that tells you when the split is finally worth it.
9 min read
Your Agent Isn't Dumb. Your Tools Are.
7 rules for tool definitions a model can't misread, starting with the sentence that fixes the most bugs.