Hiring AI systems can encode hiring manager biases in ways that look like objective scoring, so testing these tools with adversarial prompts—submitting identical resumes with different names, backgrounds, or histories—reveals whether the system treats all candidates fairly. Understanding where AI hiring systems are vulnerable protects you from being rejected by flawed automation.
Adversarial prompting involves deliberately crafting inputs designed to expose weaknesses, biases, or inconsistencies in an AI system, and in hiring contexts it is used to test whether screening tools disadvantage applicants with criminal records or employment gaps.
Reentry advocates and job seekers who understand adversarial prompting can use it to audit the AI tools they rely on, identify where bias may reduce their visibility, and adjust their application materials to perform more equitably across different screening systems.
Peri can explain this concept, give practical examples, help you decide whether it applies to your situation, or recommend a journey if appropriate.
Explore related journeys or tell Peri what you're working through.