AI Agents in Go

Section

Findings

Measured results from the book’s recorded runs, each with its method, its sample size, and what it can’t show.

  1. Measured mistakes Every failure on this page happened in a recorded run of the book’s code, and each comes with its task, its models, how many runs it rests on, the date, and the chapter. What went wrong, how often, and what the code changed because of it.chapters 1, 4, 7, 9, 10, 12, 13, 14, and 15
  2. One sentence decided 79 of 80 first moves A sentence added to an MCP tool’s description, a tool the model hadn’t called yet, steered the first move of four models in 79 of 80 replies. A label marking the text as the server’s cut that to 57. What was tested, what it can’t show, and the defenses that work upstream of the model.chapter 10

Each finding comes from live runs recorded for Building AI Agents in Go, on the models and dates it names. Small samples get said out loud: a finding gives the number of runs behind each figure, and what a different sample might have shown.