Submissions
The Fifth Elephant OSAI meet-up - Hyderabad edition
The Fifth Elephant
The Fifth Elephant

The Fifth Elephant OSAI meet-up - Hyderabad edition

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

Accepting submissions

Not accepting submissions

📜 Speaking policies and guidelines One speaker per talk. No co-speakers or joint presenters. Vendor-neutral submissions. Talks must focus on technical concepts, case studies, and real-world learnings. expand

📜 Speaking policies and guidelines

  • One speaker per talk. No co-speakers or joint presenters.
  • Vendor-neutral submissions. Talks must focus on technical concepts, case studies, and real-world learnings.
  • If your intention is to showcase a product, platform, or tool, you’re welcome to submit a (paid) pitch session, or run a sponsored workshop to teach your tool/product/platform. (Reach out to sales@hasgeek.com for sponsored workshops and pitch sessions.)
  • We strongly encourage talks that involve open source technology, tools, or frameworks - especially those built or adopted within your organization.
    The goal is to ensure the audience can take back learnings and technology they can experiment with or implement independently.

Guidelines for submissions

BEFORE you begin writing your submission, please give some thought to the following:

  • Who is the audience for your session? Think about their interests, work roles, challenges, age or experience as you decide this.
  • What problem/pain are you trying to solve (for the audience)? This should be something that is communicated clearly so that they have a sense of your session’s importance.
  • What will be the scope of your session? This will help identify the central topic or theme and should describe broad areas you plan to cover during the session?
  • How will participants benefit from your session? Think of practical and specific ways in which they will be able to apply the knowledge they gain, and beyond just general awareness.
  • What is the appropriate format for your session, given the audience and objectives that you have in mind?

The most successful talks and sessions are those where presenters are able to abstract an actionable insight from a common pain area, enlighten the audience about something new, provide a fresh perspective, and/or demonstrate innovation.

Here’s a guide for speakers to draft their presentations.

Make a submission

Harini Anand

The BERT Advantage: Deep Dive into Variants, Multimodal Evolution & Open Source Use Cases

Describe Your Session This is an enhanced version of a talk I previously delivered at a workshop organized by Google Developer Student Clubs. The presentation has been refined to highlight the open-source and multimodal capabilities of transformer-based models, making it suitable for submission to the Open Source AI community. The talk explores how BERT-like architectures have evolved into multim… more
  • 3 comments
  • Submitted
  • 22 Mar 2025
Type of session: Sponsored talk (25-35 mins) I am submitting for: Blr OSAI meetup in April 2025

Tricha Anjali

Making GenAI Testable: From Prompt to Production

Describe your session in 2 paragraphs GenAI is transforming the way we build and deploy software — but beneath the surface of working POCs lies a critical challenge: can we test these systems? In traditional software, test-driven development is a given. But with LLMs’ probabilistic outputs and evolving prompts, most AI systems today ship without clear test strategies. This session will look into … more
  • 1 comment
  • Submitted
  • 30 Mar 2025
Type of session: Sponsored talk (25-35 mins) I am submitting for: Blr OSAI meetup in April 2025

Kannan Ramamoorthy

Semantic Search - Beyond Embeddings & Vector DB

Description: It’s a simple claim that for semantic search, “Capture the embedding of the document and save it during indexing”, “Capture the embedding of the query and do the searching”. more
  • 2 comments
  • Submitted
  • 27 Aug 2025
Type of session: 25-35 min talk

Pavan Kumar Mantha

AI Based Agile Story Development

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 ca… more
  • 5 comments
  • Submitted
  • 27 Aug 2025
Type of session: 25-35 min talk

Saurabh Machave

Powering your workstation with local GenAI

Intro This talk will start with the question–why should one use open-source models in the first place? While it seems perfectly normal to make API calls to closed-source models for day-to-day tasks, it comes at the cost of privacy, judicious use of tokens and at the end of the day–money. I will explain how to wire up your code editor to use open-source models for autocomplete and chat, which exte… more
  • 7 comments
  • Submitted
  • 30 Aug 2025
Type of session: 10 mins Lightning talk/demo

Namburi Manikanta

Video thumbnail

Build AI Coding Agents with OpenAI, JavaScript & the Agent SDK

Introduction In this workshop, you’ll learn how to build AI coding agents using OpenAI, JavaScript, and the Agent SDK. We’ll go beyond simple prompts — covering how agents call tools, rewrite prompts for better outputs, and apply guardrails to stay safe and useful. Through live coding, you’ll see the agent generate, improve, and explain code step by step. more
  • 2 comments
  • Submitted
  • 12 Sep 2025
Type of session: Hands-on workshop

Namburi Manikanta

DevSecOps: Using Open-Source Security Tools with Local & Managed LLMs in the SDLC

Session Description: Secure SDLC is no longer just “scan and forget.” In this talk, I’ll show how open-source LLMs locally hosted and managed—can work inside your CI/CD pipeline to make security findings actionable: from static and dynamic analysis to human-readable remediation steps, code diffs, and auto-fix PRs. We’ll stitch together popular OSS scanners (for code, dependencies, containers, and… more
  • 1 comment
  • Waitlisted
  • 12 Sep 2025
Type of session: 25-35 min talk

Kartik

The Dependencies That Kill: How Knowledge Graphs Revolutionize Security in AI-Powered Code Review

Session Description: Traditional security scanners analyze files in isolation, missing the cascading vulnerabilities that emerge from complex dependencies. When a seemingly innocent config change can break authentication across services, or when a utility function modification introduces SQL injection risks in distant components, pattern-matching tools are blind. Through analyzing hundreds of PRs… more
  • 2 comments
  • Waitlisted
  • 13 Sep 2025
Type of session: 25-35 min talk

Amit Upadhyay

From Idea to Production: Reimagining the Software Delivery Lifecycle for the AI-First Era

Session Description: The way we build and ship software is undergoing a fundamental transformation. Traditional approaches to software delivery are being stretched thin by the growing complexity of systems, distributed architectures, and the demand for faster cycles. In this talk, I will introduce the concept of AI First Software Delivery (AIFSD) – a paradigm where AI agents are embedded into the… more
  • 0 comments
  • Under evaluation
  • 15 Sep 2025
Type of session: 25-35 min talk
Akash Sathish

Akash Sathish

Swetha A

Swetha A Co Presenter

Video thumbnail

Mastering Prompt Engineering Across the Software Development LifeCycle

Abstract This workshop will demonstrate how AI assistants can be strategic partners throughout the software development lifecycle (SDLC). We’ll explore how to unlock their full potential with the right prompts, chat modes, instruction files, and Model Context Protocol (MCP). Starting from story grooming and design discussions, participants will learn how to guide AI assistants to act as mentors, … more
  • 3 comments
  • Submitted
  • 15 Sep 2025
Type of session: Hands-on workshop

Nashit Babber

Building Production-Ready RAG Systems: From Hugging Face Models to Self-Healing Pipelines

The excitement around open-source LLMs like Mistral, LLAMA, and models on Hugging Face has democratized AI development. However, the journey from downloading a model to deploying a production-ready Retrieval-Augmented Generation (RAG) system is filled with hidden challenges. This talk bridges that gap by sharing battle-tested strategies for building RAG systems that scale, self-monitor, and integ… more
  • 0 comments
  • Under evaluation
  • 18 Sep 2025
Type of session: 25-35 min talk

Roshni Thomas

Event-Driven Architectures in BFSI: Scaling Legacy Systems to Real-Time Platforms

Description In the BFSI sector, organizations are under constant pressure to respond to market shifts, regulatory demands, and evolving customer expectations in real time. However, many still operate on legacy, batch-driven systems that limit agility and slow down innovation. Event-driven architecture (EDA) offers a way forward by enabling systems to react to business events as they happen, decou… more
  • 0 comments
  • Submitted
  • 18 Sep 2025
Type of session: 25-35 min talk

Himanshu Aggarwal

Architecting for Speed: Building Real-time Search & Recommendation Systems with Modern AI Stacks

The demand for instant, relevant experiences in fast-paced industries necessitates a new generation of search and recommendation systems. This talk will deep dive into the modern AI stack powering these systems. We’ll explore multi-stage architectures, from two-tower models for scalable candidate generation using vector databases, to advanced pretrained and rerankers for pinpoint accuracy. The se… more
  • 0 comments
  • Submitted
  • 19 Sep 2025
Type of session: 10 mins Lightning talk/demo

Karun Japhet

What Happens Before and After the Code? AI Has a Role There Too

Most conversations about AI in software engineering focus on code generation. But for experienced engineers and tech leads, writing code is rarely the hardest part of the job. The real challenges lie in designing systems, clarifying requirements, building shared understanding, and keeping software healthy once it’s live. more
  • 2 comments
  • Submitted
  • 29 Sep 2025
Type of session: 25-35 min talk

Karun Japhet

Maximise the value out of AI Coding Assistants in Software Delivery

Tools like GitHub Copilot, Claude Code, and Codex are changing how we write and ship software. But while they promise faster development, they also raise questions: How do we ensure quality, security, and maintainability when AI is part of the coding flow? What practices help teams use these tools effectively without compromising delivery standards? more
  • 0 comments
  • Submitted
  • 29 Sep 2025
Type of session: Birds of Feather (BOF) session

Sonu Kumar

Video thumbnail

Modernizing Legacy Code with Multi-Agent Systems: Challenges & Lessons

When I was working at Capgemini’s innovation team years ago, one of the biggest projects we tackled was migrating COBOL systems to Java. Back then, GPT-3.5 had just come out, and like many, we were experimenting with what LLMs could (and couldn’t) do. Fast forward to today, the landscape looks completely different. With open source, domain-specific code LLMs and multi-agent AI systems, we’re no l… more
  • 2 comments
  • Submitted
  • 30 Sep 2025
Type of session: Hands-on workshop

Shruti Dhavalikar

Evaluating Agentic Applications in the SDLC: Ensuring Reliability with OSAI

Title Evaluating Agentic Applications in the SDLC: Ensuring Reliability with OSAI more
  • 0 comments
  • Submitted
  • 30 Sep 2025
Type of session: 25-35 min talk
Register

Hosted by

The Fifth Elephant
The Fifth Elephant
Jumpstart better data engineering and AI futures

Supported by

Community sponsor

Meta
Meta