AI TRIAGE AGENT: REAL BUG OR FALSE FAILURE?

Internship

• Field: AI ENGINEERING
• Duration: 6 months
• Paid internship with a flexible workplace model allowing remote and on-site work where possible.

Problem

Many nightly test failures are not real product bugs, such as locator changes, slow pages, popups, used data, or a down environment. Each failure is currently replayed and triaged by hand, causing real bugs to be reported late.

Key tasks

• Build an AI agent that replays failed test steps on the application by label and role rather than broken locators.
• Turn vague expected results into concrete checks covering UI, network, console, and database behavior.
• Classify each failure as a real bug, script issue, environment issue, data issue, or flaky failure.
• Draft bugs in Azure DevOps.
• Enforce safety through test-environment restrictions, an action allow-list, a step budget, and an auditable trace.

Success criteria

• Verdict accuracy of at least 80% compared with QA decisions.
• Zero actions outside the allowed scope.
• Less triage time per failure.
• False failures closed without manual replay.

Candidate profile and requirements

• Final-year engineering student in software, AI, or data.
• Python, LLM APIs, prompt and agent design.
• Playwright or Selenium and Azure DevOps API are a plus.
• Curious, research-minded, and comfortable with uncertain outputs.