The latest articles on DEV Community by MG-Duan (@mduan). https://dev.to/mduan https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4206809%2F97baef27-c367-4418-bcad-26d7ddfc5c92.png https://dev.to/mduan en MG-Duan Sun, 25 Oct 2026 15:17:34 +0000 https://dev.to/mduan/we-open-sourced-our-ai-testing-platform-from-requirement-docs-to-executable-test-cases-4m8g https://dev.to/mduan/we-open-sourced-our-ai-testing-platform-from-requirement-docs-to-executable-test-cases-4m8g <p>Every tester knows the drill: a requirement document lands, and you spend the next few days manually translating it into test case tables — preconditions, steps, expected results. Then the API/UI automation scripts you wrote last quarter break because one page changed.</p> <p>We got tired of it, so we built <strong>WHartTest</strong> and open-sourced it: an AI-driven test automation platform that turns requirement documents into executable test cases — and helps fix them when they fail.</p> <h2> What it does </h2> <p><strong>Functional test case generation.</strong> Upload requirement documents (with an online editor built in). AI generates complete cases — preconditions, steps, expected results — grounded in your project knowledge base. Cases are managed in list or mindmap view, with drag &amp; drop, P0–P3 tags, and export to PNG/JSON.</p> <p><strong>API automation.</strong> From an API definition, AI generates request steps, assertions, variable extraction, and pre/post scripts. When a run fails, AI reads the logs and responses to locate the problem and proposes fixes.</p> <p><strong>UI automation.</strong> AI generates page operation steps and element locators. Runs capture logs, screenshots, video, and Playwright traces. When a locator breaks or an assertion fails, AI analyzes the evidence and suggests repairs. Since v2.8.0 there is a frame-stream Playwright recorder: you record interactively and create elements/steps as you go — no more hand-writing scripts.</p> <h2> Under the hood </h2> <ul> <li>Django 5.2 + DRF backend, Vue frontend, monorepo architecture</li> <li>LangChain/LangGraph orchestration for multi-turn reasoning</li> <li>RAG knowledge base: document chunking, vectorization, reranking</li> <li>MCP (Model Context Protocol) tool calling</li> <li>A Skills system: <strong>WHart-SkillHub</strong> (new in v2.8.1) is an open skill center — install skills with natural language or one CLI command; Skills management is natively integrated in both desktop and web clients</li> </ul> <p>Other recent highlights: smart dual-mode execution (script / pure-AI / dual), AI self-healing failure diagnosis, multi-format API doc import &amp; export (OpenAPI, Swagger, Postman, HAR, curl, Apifox, YApi...), and operation audit logs.</p> <h2> Facts &amp; links </h2> <ul> <li> <strong>GitHub</strong>: <a href="https://github.com/MGdaasLab/WHartTest" rel="noopener noreferrer">https://github.com/MGdaasLab/WHartTest</a> (1.1k+ stars, 940+ commits)</li> <li> <strong>Website</strong>: <a href="https://wharttest.mgdaas.com/" rel="noopener noreferrer">https://wharttest.mgdaas.com/</a> </li> <li> <strong>Docs</strong>: <a href="https://docs.wharttest.mgdaas.com/" rel="noopener noreferrer">https://docs.wharttest.mgdaas.com/</a> </li> <li>Self-hostable; strong security note: the Skills module has elevated system permissions — deploy in trusted/internal networks</li> <li>License: Apache 2.0 with additional conditions (see the LICENSE file; versions up to v2.6.0 were MIT)</li> </ul> <p>We'd love feedback from QA engineers: how is AI-generated test case generation working out in your teams? What would you want next?</p> ai automation opensource testing