Don't ask if devs cheat with AI
test if they're good with it. The technical assessment that grades how skillfully candidates work with AI: reading its output, fixing it, prompting it, and overriding it when it is wrong. Scored alongside the fundamentals that still decide whether someone can ship.

반응 (1)
비슷한 프로덕트
설명이 비슷한 순
Spec27
spec27.aiSpec-driven validation for AI agents
Good AI Task
goodaitask.coma tool for asking AI what it can and can't do
Corepoints
corepoints.aiScreen Candidates for AI Proficiency at Scale (Demo Run)
Agent-skills-eval
github.comTest whether Agent Skills improve outputs
Deltix
app.deltix.aiAI Driven Testing