Agents Made Code Free. Maintaining It Didn't Get Cheaper. - Dmitry Buykin, Maersk
Source
youtube.com
Author
AI Engineer
Date
Why it matters
AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →-written code is cheap to produce but costly to maintain. The talk gives concrete practices (task replay, expert-owned evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition →, runtime guardrailsThe checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.Full definition →, weekly pruning) and an 18-question audit for AI-coded repos.
Terms in this piece · Glossary
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.