Skip to content
View anant-pw's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report anant-pw

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
anant-pw/README.md

Anant Jain — Principal QA Engineer | SDET | AI-Augmented Testing

14+ years in QA & Test Automation · Playwright · Python · Java · Selenium · LangChain · Groq

🌐 Socials

LinkedIn Email


💻 Tech Stack

Python Playwright FastAPI GitHub Actions Java Selenium Jenkins SQLite Jira Swagger


About Me

Senior QA Engineer and SDET with 14+ years of experience across enterprise software, digital transformation, and AI-augmented testing. Strong foundation in both manual and automated testing — UI, API, performance, and exploratory.

Over the past year, I've been building applied AI projects that extend traditional QA with LLM-driven capabilities: autonomous test generation, self-healing selectors, multi-agent execution, and AI-assisted triage. These are real, runnable frameworks — not tutorials.

Open to: SDET, QA Engineer, QA Lead, AI Engineer (QA focus) roles.


Flagship Projects

🛡️ Sentinel QA

Autonomous QA Engine — AI generates, human approves, Playwright executes, LLM triages.

A full testing lifecycle orchestrated by AI. Converts unstructured requirements into structured YAML test plans, routes through a human-in-the-loop approval gate, executes via Playwright, and uses LangChain agents to triage failures and draft Jira-ready bug reports.

Python Playwright LangChain SambaNova Groq Ollama FastAPI SQLite Allure pytest-xdist

View repo


🤖 Playwright + Ollama Framework

AI-driven exploratory browser testing — no fixed scripts, LLM decides what to test.

Instead of hardcoded selectors and flows, the framework feeds live DOM state to a local LLM (Ollama/Llama3), which decides the next action dynamically. Includes AI bug detection, screenshot validation, Allure reporting, and Jenkins CI integration.

Python Playwright Ollama LangChain Allure Jenkins pytest

View repo


⚡ Playwright + Groq Framework

Cloud LLM variant — same autonomous testing approach with Groq's ultra-fast inference.

Python Playwright Groq LangChain Allure

View repo


Tech at a Glance

Area Tools
Test Automation Playwright, Selenium, pytest, pytest-xdist, TestNG, Allure
AI / LLM LangChain (LCEL), Groq, SambaNova, Ollama, sentence-transformers
API Testing FastAPI, REST Assured, Swagger, Postman
CI/CD GitHub Actions, Jenkins
Languages Python, Java
Tracking & Reporting Jira, Allure, Streamlit, Plotly

📊 GitHub Stats


Pinned Loading

  1. sentinal_qa_phase3 sentinal_qa_phase3 Public

    Sentinel QA Phase 3 — full cognitive QA ecosystem: AI generates test plans, Streamlit HITL approval, parallel Playwright execution via pytest-xdist, autonomous Jira bug triage with SQLite memory

    Python

  2. VerdictAI VerdictAI Public

    LLM evaluation framework — multi-judge scoring, hallucination detection, regression tracking, and Streamlit dashboard. YAML-driven test suites with Groq + Cerebras judges

    Python

  3. qa-rag-pipeline qa-rag-pipeline Public

    RAG pipeline for QA knowledge — chunk, embed, and query test cases and bug reports using Qdrant vector DB, sentence-transformers, Groq LLM, and Streamlit UI

    Python

  4. playwright-groq-framework playwright-groq-framework Public

    Full autonomous QA system — Groq (cloud) + Ollama (local) LLM backends, auto-login, smart crawling, API testing, self-healing, visual detection, Allure reports

    Python

  5. playwright-ollama-framework playwright-ollama-framework Public

    AI-driven exploratory browser testing — LLM observes live DOM and decides next action; no fixed scripts, self-healing selectors, Allure + Jenkins CI

    Python 2 3

  6. playwright-ollama-framework-parallel-agents playwright-ollama-framework-parallel-agents Public

    Multi-agent parallel browser testing — simultaneous AI agents crawl multiple URLs with stealth mode, visual bug detection via llava, and per-agent Allure reports

    Python