The Fifth Elephant OSAI meet-up - Hyderabad edition

The Fifth Elephant OSAI meet-up - Hyderabad edition

Call for Proposals - make a submission; give visibility to your work

Pavan Kumar Mantha

AI Based Agile Story Development

Submitted Aug 27, 2025

In this session, I will showcase an open-source AI platform that automatically generates user stories and test scenarios directly from initiatives and epics provided in CSV or Excel formats. Powered by a multi-agent LLM framework, the platform goes beyond generation by saving all outputs in a semantic vector database (Qdrant). This means teams can later retrieve and query their stories or test cases using natural, context-driven questions—without needing to remember exact keywords.

We’ll walk through the end-to-end flow: ingesting initiatives and epics, generating structured user stories and test scenarios, and persisting them into Qdrant for semantic search. Along the way, I’ll highlight how this approach bridges the gap between agile planning and intelligent knowledge retrieval, offering a more scalable way to manage backlogs and QA processes.

Key Takeaways

  • How to automatically generate user stories and test scenarios from high-level initiatives/epics using multi-agent LLMs.

  • Why semantic storage + retrieval (via Qdrant) makes backlogs context-aware, enabling smarter search and reuse compared to traditional keyword search.

Beneficial For

  • Product Owners & Scrum Masters who want to accelerate backlog creation.
  • QA Engineers & Test Leads looking to auto-generate robust test cases.
  • Engineering Leaders & Architects exploring AI-driven backlog and knowledge management.
  • OSS Enthusiasts & AI Builders keen on combining LLMs with vector databases for real-world agile workflows.

About Speaker
I’m M K Pavan Kumar, Distinguished AI Architect at Equal and a research scholar at IIITDM Kurnool. With 15+ years of experience across ERP, Insurance, and Aerospace domains, I focus on building GenAI and Agentic platforms at scale. As an open-source contributor, I’ve created frameworks like GRAS, Bootstrap-RAG, and CodeEvals, and authored 140+ technical blogs on applied Generative AI. My work spans multi-agent orchestration, memory-centric architectures, and semantic retrieval systems, and I regularly speak at global AI and developer communities.

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

Jump starting better data engineering and AI futures

Supported by

Community sponsor