AI, for real
Traces, evals and guardrails only watch on their own. Connect them and your AI gets better every week. Even OpenAI learned this the hard way with a GPT-4o update it rolled back within days.
AI, for real
A dealership chatbot agreed to sell a new SUV for $1. Prompt injection is OWASP's #1 risk for LLM apps. Here's what a guardrail is, what it checks on the way in and out, and the open-source tools to add one.
AI, for real
Same model name, same prompt, completely different behaviour. Stanford researchers watched GPT-4 go from 97.6% to 2.4% on one task. Here's the cheap weekly habit that catches drift before your users do.
AI, for real
Most 'evals' are a glance at the output and a shrug. Air Canada and Cursor show what that costs. Your first real eval needs no framework: read real outputs, write down what good means.
AI, for real
Everyone is building with AI. Very few teams can prove it works. Here's the one loop this series teaches: trace it, test it, guard it, improve it.
Observability
The words that matter (observability, tracing, evals), the top tools open-source and paid, and how to pick — with sources.