borodicht

1. LLM как security-аналитик
You are a Senior Application Security Engineer.

Analyze the following system description and API contract.

Your tasks:
1. Identify potential security risks.
2. Describe possible attack surfaces.
3. List high-risk endpoints.
4. Propose at least 15 security test ideas.

borodicht

1. Генерация синтетических валидных данных:
You are a test data generator for QA automation.

Generate a synthetic dataset of 20 users.

Rules:
- All data must be fictional.
- Do NOT use any real people or real companies.
- Emails must use example domains (example.com, test.com).
- Phone numbers must be format-valid but not real.

borodicht

name: AI QA Pipeline

on:
  push:
    branches: [ "main", "master" ]
  workflow_dispatch:

jobs:
  ai-qa:
    runs-on: ubuntu-latest

borodicht

        // STAGE. AI BUG REPORT (DESIGN-TIME)
        String checklist = FilesUtil.read("checklist_login.txt");
        String testcases = FilesUtil.read("generated/testcases.json");
        String codeReview = FilesUtil.read("generated/code_review.txt");
        
        String bugPrompt = FilesUtil.read("prompts/04_bug_report.txt")
                .replace("{{CHECKLIST}}", checklist)
                .replace("{{TESTCASES}}", testcases)
                .replace("{{REVIEW}}", codeReview);

borodicht

You are a Senior QA Engineer.

Based on the following artifacts:
- original checklist
- generated test cases
- generated autotests
- AI code review

Detect potential defects, inconsistencies, missing validations or risks.

borodicht

        // STAGE 6. AI CODE REVIEW
        String generatedTest = FilesUtil.read(
                "src/test/java/org/demo/generated/GeneratedLoginTest.java"
        );

        String reviewPrompt = FilesUtil.read("prompts/03_code_review.txt")
                .replace("{{CODE}}", generatedTest);

        FilesUtil.write("generated/code_review_prompt.txt", reviewPrompt);

borodicht

You are a Senior QA Automation Architect.

Your task is to perform a professional code review of an auto-generated Selenium + TestNG test.

Analyze the code and provide:

- Functional risks
- Test design issues
- Stability problems
- Maintainability issues

borodicht

        // STAGE 5. GENERATE AUTOTESTS
        TestGenerator.generate();
        System.out.println("Autotests generated.");

borodicht

package org.demo.ui;

import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;

public class LoginPage {

    private final WebDriver driver;

    public LoginPage(WebDriver driver) {

borodicht

package org.demo.ui;

import org.openqa.selenium.WebDriver;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.chrome.ChromeOptions;
import org.testng.annotations.AfterMethod;
import org.testng.annotations.BeforeMethod;

public class BaseUiTest {