Free Content · Inspired by the book

AI AgentObservability.

First-person field notes from building and debugging AI agents in production—free stories inspired by the book to help you see what happens between a prompt and a 200 OK.

Dany Paredes

Written by Dany Paredes — real production lessons, told in first person.

Free Content · Field Notes

Stories from living among agents.

Each post is a first-person experience from shipping AI agents—the silent failures, the traces that saved me, and the guardrails that stuck.

Core pillars

What you need when you live among agents.

Observability is not another dashboard—it is the habit of making every agent decision inspectable.

semantic.check01

Catch silent semantic failures

Learn why 200 OK can still mean a broken user experience, and how to validate intent vs. tool execution.

otel.spans02

Trace every span end-to-end

Connect prompts, RAG chunks, tool calls, and model responses into one OpenTelemetry timeline.

token.budget03

Control latency and token cost

Spot autonomous retry loops, repeated tool signatures, and TTFT bottlenecks before the bill arrives.

The Book

AI Agent Observability

The complete field guide by Dany Paredes—from OpenTelemetry semantic conventions to production evaluations and cost guardrails.

Explore the book Free stories above are inspired by chapters in the book.