AI Agent for Jira-Integrated Test Case Generation opensource

@hareshfinadiya

Hi, I am Haresh, having 14+ years of experience in Software Testing Industry. - Having unique blend of knowledge in Quality Product Delivery, Processes Management, Functional testing, Integration and regression testing, load and Perfromance Testing which help me to take the Quality of the software to the next level. - Hands on experience on testing Desktop, Web Based, Mobile application and ERP based application. - Hands on experience on automation testing tools on selenium webdriver, jmeter, katalon studio, Appium, cypress, selenium with TestNG freamwork etc.. - Thorough understanding of Product Delivery Life Cycle, Software Testing Life Cycle and Software Development Life Cycle. - Experience in Well conversant with writing Test plan,Test Cases,Bug report, Release Note and Product Health Report. - Worked in various domains like Finance, Retail, Web Portals, Healthcare, ecommnerce, CMS, Eduction Portal, Life Insurance, ERP system etc. - I do have require mobile devices to test mobile view or applications like android and iOS applications. - I have hands on experience with Git, postman, MSSQL Server. Kindly review my profile and let me know you view over the same. Thanks, Haresh

@mohjib092

Hi there, I can build a RAG-based AI agent that connects to Jira, parses attachments (PDF/Word/Sheets), and learns from historical test cases to generate structured, traceable functional test scenarios. I’ll design a scalable AWS architecture using Python, embeddings + vector database, and an LLM to produce ranked test cases with CSV export and requirement traceability. Deliverables include clean source code, deployment guide, demo walkthrough, and post-delivery support. For more follow the chat box ,

@ail5a9f298b597ed

I specialize in building AI‑augmented automation tools for software development pipelines, with extensive experience integrating LLMs, vector databases, and Jira APIs to deliver actionable insights. Using Python and LangChain on AWS, I can create a robust RAG agent that parses Word, PDF, and spreadsheet attachments, retrieves relevant historical test cases from a vector store, and generates ranked functional test scenarios in both plain‑text and CSV formats, complete with traceability links and priority tagging. My prior work automating test‑case generation for enterprise QA teams has consistently met high usefulness benchmarks, ensuring reliable, one‑click Jira integration and seamless deployment in containers or Lambda functions.

@arbu1499

Hi, Your idea of an AI-powered agent that reads Jira tickets, ingests requirement documents, and generates functional test cases is exciting, and it aligns perfectly with my experience building RAG pipelines for QA automation. I can design a solution that integrates seamlessly with Jira via REST API, parses Word/PDF/spreadsheet attachments, and produces structured test cases in both plain text and CSV, fully traceable to requirements. I’d leverage Python with LangChain or LlamaIndex, paired with an appropriate vector store on AWS, to ensure accuracy and relevance while avoiding duplication from your historical test cases. I can also provide full deployment scripts, a clear README, and a demo video for your QA team. Looking forward for your positive response in the chatbox. Best Regards, Arbaz T

@irazon15

I’ll architect a Python‑based RAG agent on AWS: Jira REST ingestion → document parsing (PDF/Word/XLSX) → chunking + embeddings (OpenAI or Claude via Bedrock) → vector store (OpenSearch or Pinecone). A ranking layer compares past test cases to avoid duplication, then generates traceable, structured scenarios (text + CSV) with requirement line references. Containerized (ECS/Fargate) with clear README, setup scripts, demo video, and 30‑day support. Designed to hit the 90% QA usefulness benchmark.

@samliveformusic

Hello There, In my current implementation, I have achieve this task using some popular AI agent. I have good knowledge on AI agent building and where I can help you to achieve the target as defined in the JD. But, my condition - I need permanent role. Let's discuss and close. Regards, Swetang Patel

@rajeshrolen

Hello, I would like to grab this opportunity and will work until you are 100% satisfied with my work. I am an experienced professional with many years of hands-on experience in Testing / QA, Software Testing, Agentic AI Let’s connect in chat so that we can discuss further. Regards, Rajesh Rolen

@haseebsidd07

Hey , I just finished reading the job description and I see you are looking for someone experienced in Testing / QA, Software Testing and Agentic AI. This is something I can do. Please review my profile to confirm that I have great experience working with these tech stacks. While I have few questions: 1. These are all the requirements? If not, Please share more detailed requirements. 2. Do you currently have anything done for the job or it has to be done from scratch? 3. What is the timeline to get this done? Why Choose Me? 1. I have done more than 250 major projects. 2. I have not received a single bad feedback since the last 5-6 years. 3. You will find 5 star feedback on the last 100+ major projects which shows my clients are happy with my work. Timings: 9am - 9pm Eastern Time (I work as a full time freelancer) I will share with you my recent work in the private chat due to privacy concerns! Please start the chat to discuss it further. Regards, Haseeb,

@dishuj5

Hello, Your idea for an AI agent that generates functional test cases directly from Jira tickets using a RAG-based approach aligns perfectly with my QA and Business Analysis expertise. I can help structure this solution from a requirements, validation, and quality perspective to ensure it delivers high-value, usable test scenarios. I will support by: Defining clear functional requirements for Jira API integration and document ingestion (PDF, Word, Excel) Designing traceability mapping between requirements and generated test cases Creating evaluation criteria to meet the 90% usefulness benchmark Preparing validation plans, blind review frameworks, and output format standards (TXT/CSV) Ensuring the workflow is well-documented for AWS deployment With strong experience in requirement analysis, test design, and QA process optimization, I focus on building reliable, measurable, and production-ready solutions. I’d be happy to discuss how we can architect this efficiently. Best regards, dishu WhatsApp: +91 6260233904

@prathmesh332

Hi, I'm intrested in this project If i were building this, i'd keep it simple and reliable rather than over-engineered. The flow i'd design When you provide a Jira ticket key, the system fetches the description, acceptance criteria, comments, and attachments using the Jira REST API. Attachments like PDF, Word, or Excel would be parsed and converted into clean text. I’d make sure the content is structured properly so the model understands context clearly. on top of that i'd build a RAG pipeline where Jira content + requirement documents, Relevant past test cases and acceptance criteria and are combined passed to LLM with strict formatting instructions. The output would always follow a fixed structure The output would always follow a fixed structure: ID, preconditions, steps, expected result, priority, and clear requirement references. CSV export will be built-in so your QA team can directly import it into your test management tool. You’ll get: Clean source code Setup instructions AWS deployment guide Demo walkthrough I’ve worked on RAG-based systems before, so I understand that the key isn’t just generating text it’s making the output structured, traceable, and actually useful for real workflows. Happy to discuss timelines or even start with a small prototype first.

@Spexoid

Hello, This project perfectly aligns with my expertise in QA automation, AI systems, and RAG-based architectures. I can build a production-ready AI agent that integrates with Jira via REST API, ingests requirement documents (PDF, Word, Excel), analyzes historical test cases using a vector database, and generates ranked, non-duplicated functional test scenarios with full traceability mapping. I’ll design the RAG pipeline using Python (FastAPI) on AWS, leveraging OpenAI/Claude models with Pinecone or OpenSearch for embeddings. The solution will include CSV export, traceability matrix, clean source code, deployment guide, demo video, and post-delivery support. Ready to architect and deliver this end-to-end system efficiently.

@karthikresonite

Hello, We are Resonite Technologies, an experienced AI/ML and QA-automation team, and we can build your Jira-integrated AI agent for RAG-based test case generation. Our approach: • Jira REST integration to fetch stories, ACs, comments, attachments • Parsing of PDF/Word/Excel via PyMuPDF, python-docx, pandas • RAG pipeline with semantic chunking and metadata for traceability • Vector DB: Amazon OpenSearch / Pinecone • Hybrid retrieval to reuse past tests and avoid duplication • LLM generation of structured cases (ID, preconditions, steps, expected results, priority, trace links) • CSV/text export + auto traceability matrix • Feedback loop to reach your 90% usefulness target Tech stack: Python, LangChain/LlamaIndex, AWS (Lambda/ECS, S3). Models: GPT/Claude for quality, or Llama 3/Mixtral for cost-efficient hosting. Deliverables: clean source code, README, AWS deployment guide, demo video, and support. We’ve built RAG and AI agents for real workflows and can start with a quick PoC. Best regards, Resonite Technologies

@chiragardeshna

Hi there, I am a strong fit because I have built RAG-based AI agents that integrate with enterprise tools, parse structured documents, and generate traceable, production-ready outputs. I have implemented Jira API integrations, document ingestion pipelines for PDF/Word/Excel, vector-based retrieval systems, and LLM-driven generation with structured CSV exports and requirement traceability mapping. I would architect this in Python using FastAPI, LangChain or LlamaIndex for orchestration, OpenAI or Claude for generation, a vector store such as Qdrant or Pinecone for historical test-case retrieval, and structured prompt templates enforcing ID, steps, expected results, and trace links. I reduce risk by isolating retrieval, ranking, and generation into modular services, validating requirement citations through embedding similarity checks, benchmarking outputs against a labeled QA review set, and containerizing for AWS ECS or Lambda deployment. I am ready to begin immediately and can deliver an MVP with Jira integration and ranked test-case generation within 4 to 6 weeks. Regards Chirag