2026-Using Gen AI & AI Agent in Software Automation Testing

Explore how generative AI uses large language models to generate software code and manual test cases, and learn tokenization, data sources, and free tier access.

Harness ChatGPT and GPT models to generate simple selenium c-sharp dotnet login tests for app.somi.com, with setup, locator weighting, and wait mechanisms.

Explore how ChatGPT uses AI agents to perform research operations, including online search, deep research, enterprise automation comparisons between Playwright and Selenium, and an 80% reduction in test execution time.

Discover how cloud models like Claude's sonnet and opus power generative ai for test automation, including prompt engineering and auto generation of selenium c# framework code and page object models.

Discover how to run LLaMA from Meta locally for software testing, enabling data privacy, cost savings, and self-contained inference with GPT for all and other local tools.

Download and run llama 3.1 locally with the GPT for all tool, install on Mac, Windows, or Ubuntu, manage models offline, and generate Selenium automation code in Java.

learn to run old lama locally offline on macOS by downloading a model via the command line, then generate selenium code in Java for Amazon.com with a page object model.

Learn to run llama 3.2 locally with vision to analyze images, handle image generation, and support automation testing with Selenium, Playwright, and Java.

Run a local GPT OS model on your machine using open-source large language models, including a 20-billion-parameter option that runs on 16 gb ram, with real-time search.

Leverage generative AI to create manual test cases that precede automation, and practice writing and validating test scenarios using a simple app across online and offline ChatGPT versions.

Create manual test scenarios for a web app using a large language model by analyzing page source and role-assigning prompts, covering login and navigation tests.

Generate manual test data with Gen AI using prompts to cover login and create new employee pages, including validation messages and number field checks like salary and duration.

Leverage local large language models to generate manual test scenarios and test data, handling prompt size limits and token capacities for thorough validation and edge cases.

Generate BDD scenarios in Gherkin format using ChatGPT, create feature and scenario outputs for manual and automated testing, and visualize with mind maps or Mermaid drawings for automation teams.

Analyze product requirements with grounded models and a Notebook LM to extract objectives, scope, and acceptance criteria for a cloud customer engagement platform.

Blend multiple sources to ground test requirements with offline grounded models, using local docs indexing to fuse information for SAS configuration costs, the project budget, and hosting region.

Explore retrieval augmented generation (rag), combining external and static knowledge to generate context-aware, accurate responses, and apply it to test planning, test case generation, and estimations.

Use a context-aware rag to fuse documents with the Gemini 1.5 pro model and generate test plans and cases for Project Phoenix's chat, email, and dashboard, with 30s response time.

Explore how generative AI enables automated UI testing with large language models, generating and refactoring test code for Cypress, Playwright, and Selenium; integrate AI tools like Copilot and Tabnine.

Generate automated UI tests with ChatGPT in Selenium and page object model using Java and TestNG, including page source scraping, locators, page objects, and refactoring to a custom employee type.

Explore how generative AI explains and documents test code, refactors automation scripts, and assists data driven testing with data providers and Selenium examples.

Explore gen ai based development tools like GitHub Copilot and Tabnine that write, explain, refactor, and generate unit tests within the IDE, enabling secure, enterprise-ready coding for automated testing.

Explore how AI pair programming provides real-time code suggestions for test automation, enabling you to write assertions, refactor code, and optimize WebDriver workflows.

Explore how generative AI enhances software automation testing with Playwright and ChatGPT, generating page object model code, UI tests, and assertions, plus tools like zero step and auto playwright.

Explore generative AI-powered playwright with zero step, leveraging GPT-3.5 and GPT-4 to enable AI-driven tests via natural language prompts and no locators.

Explore how generative AI enables automated complex workflows in Playwright using a zero step approach and natural language prompts to replace locators, test edits in tables, and verify outcomes.

Explore how auto playwright adds AI to Playwright tests, install via npm, set OpenAI API key, and compare free auto playwright with zero step, noting speed, caveats, and costs.

Explore Test Trigger, an AI-powered tool that converts plain English test instructions into end-to-end UI automation tests with no code, enabling behavioral driven test creation and rapid test generation.

Master creating automated test cases with testRigor using plain English prompts to perform edits, deletes, and logins, verify values, and generate shareable test reports.

Explore automating a flight reservation on Cleartrip with test trigger, turning manual test steps into automated flows using AI and ML, via reference locators and date picker interactions.

Learn to automate a complex e-commerce checkout workflow on the New Zealand PB Tech site using test trigger, with referential selectors, price verification, login, and reusable rules.

Create reusable rules in test trigger to standardize and shrink test steps for Android purchases, checkout, and cart verification, enabling bulk replacement across hundreds of tests.

Learn how to parameterize test data to reduce flakiness in automated scenarios using stored values and reusable rules with test trigger.

Test phone calls and SMS in your app using test trigger with Twilio integration, verifying ringing and delivery through the Twilio dashboard.

Explore how the shared test suite in testRigor enables inheriting reusable rules and test data across suites, reducing keystrokes and enabling consistent business logic.

Learn to automate web tests with test trigger's Chrome extensions for record and playback, using AI-generated plain-English steps without writing code.

Learn to perform api testing with test trigger, issuing get and post requests, saving responses to variables, and verifying results with json paths on a fake json server.

Explore how generative AI enhances API testing for microservices. Learn to use Swagger and Postman, test get/post/put/delete operations, and generate robust scenarios with a large language model.

Leverage swagger schemas to auto-generate RestSharp API tests in csharp .net, using a builder pattern and schema-driven prompts to cover all endpoints, serialization, and edge cases.

Leverage postman's post bot AI feature to automatically write and run tests for API requests, generate test scripts from Swagger schemas, and leverage ChatGPT and AI tools.

Leverage generative AI through OpenAI API to generate and validate page object model code for UI automation testing in dotnet, analyzing locators for page changes and ensuring test reliability.

Explore the OpenAI API portal and create API keys, learn where to access billing and API keys, and understand how to call models like GPT-4 with curl and bearer tokens.

Demonstrates building a Selenium C# test with ChromeDriver, using OpenAI to verify page sources, implement a page object model, and set up a xUnit project with OpenAI NuGet.

Read the page object model code and page source, then use the OpenAI API via a NuGet package to verify locators in test code, returning true or false.

Demonstrates running test code with generative AI via the OpenAI API to verify the login page locator from the page source using a page object model, in async tests.

Learn to build visual testing with generative AI for automation testing by comparing user interface images with vision APIs, integrating with Selenium or Playwright, and managing token costs.

Explore the visual comparison scenario to automate image-based regression checks, using vision APIs to identify pixel-level differences between screenshots and return structured JSON diffs for downstream code.

Develop vision code to compare two images using the OpenAI library, passing before and after images as binary data via chat messages and a JSON schema for visual verification.

Fuse vision and page object model comparison in Selenium tests by capturing before and after screenshots, sending them to GenAI for diff, and deserializing results for test output.

Learn to deserialize a JSON response into a differences class with an elements structure of name, first image, and second image using System.Text.Json, enabling precise visual comparison in tests.