An agent makes an architectural decision, the session ends, and the repository holds the result without any underlying reasoning. Three months later, someone looks for the rationale and finds the commit. This talk highlights the problems this creates in ongoing projects, ranging from onboarding and code reviews to the question of why an agent proposes the exact same rejected solution for the third time. After that, we explore the countermeasures: documented decisions, logged tool calls, and a wiki that agents can read and write themselves.
Tell me the audience, the format and the date. Bios, photos and this abstract are ready to copy in the press kit.
JSNation US
Telling your AI coding agent “please don't commit directly to main” is about as effective as asking your cat not to knock things off the table. LLMs are non-deterministic by…
JS & Angular Days
In diesem halbtägigen Workshop lernst du, wie du dein KI-Coding-Setup so aufsetzt, dass du produktiv in Angular-Applikationen arbeiten kannst. Wir starten mit KI-gestützten…
Frankfurter Buchmesse
Wenn eine neue Kollegin anfängt, arbeitet sie die ersten Wochen unter Anleitung. Erst wenn geklärt ist, wer die Ergebnisse prüft und wo die Kompetenzgrenzen liegen, agiert sie…