Recap for Humans
-
The agent that can change your infrastructure but never runs terraform apply
InfraAi proposes infrastructure changes through a three-layer safety model: enforced permission boundaries plus mandatory human review…
-
Observability and Evaluation for AI Agents: A Practical Guide with Arize Phoenix
How I instrumented and evaluated a real LangGraph agent with Arize Phoenix — traces, evaluators, and…
-
Beyond the Prompt: How to Tell if an AI’s Answer is Actually Good
We’ve all been there. You type a prompt into ChatGPT, Claude, or Gemini, and a few…
