Spartans Summit 2026

Opening Note

Welcome to Spartans Summit 2026

Session

The Symbiosys Effect: AI & I

Nowdays using artificial intelligence in software testing is kinda standard. Agentic AI, GenAI, AI Agents and so on is just few examples of the last couple months that are monopolizing our time. But are they are going to totally replace standard processes in SDLC? Is the human in the loop? And how software tester can keep up with all the changes around these buzzwords? In this talk we will deep dive into the past, present and future of Software Testing and try to uncover the balance between human and machine.

Ioannis Papadakis

Head of QA, Snappi

Session

Evaluating AI Agents: Testing and Tooling for Reliable Outcomes

As AI agents become more capable and widely used, ensuring their reliability requires new testing approaches. In this session, you’ll learn how to evaluate AI agents through scenario-based testing, intent validation, and end-to-end outcome checks to ensure they behave correctly within real-world business contexts.

Asmita Parab

Technology Consulting - QE Manager, EPAM Systems

Session

Hallucination Hunters: A QA Engineer's Guide to AI Evaluation

As AI becomes part of modern applications, testing systems that don’t always produce the same output introduces new challenges. In this session, you’ll learn how to extend your existing test automation skills to evaluate AI responses, detect issues like hallucinations, and apply practical evaluation techniques to ensure the quality of AI-powered features.

Gaurav Khurana

Senior Test Consultant, Microsoft

WORKSHOP

Master MCP for Testing: Build, Secure & Scale Your Testing

This workshop introduces Model Context Protocol (MCP) and how it can transform modern testing workflows by addressing common automation and scalability challenges. Through a hands-on live build session, participants will create a custom MCP testing tool, explore integrations with tools like Appium and WebDriverAgent, and understand how MCP enables more flexible and intelligent testing systems.

Sai Krishna

Director of Engineering, TestMu AI

Srinivasan Sekar

Director of Engineering, TestMu AI

PANEL DISCUSSION

From Pilot to Pipeline: How Teams Are Actually Scaling AI in Quality Engineering

This panel explores how teams are moving beyond AI pilots to real adoption in quality engineering. Experts will discuss practical use cases, evolving testing strategies, and the metrics that help teams successfully scale AI across the testing pipeline. The conversation will also highlight cultural shifts, skills, and mindset changes needed to make AI a reliable part of modern testing workflows.

Harinee Muralinath

Director, Thoughtworks

Jaydeep Chakrabarty

Director of AI in Tech, Piramal Finance

Pricilla Bilavendran

Team Leader, Billennum

Rahul Parwal

Specialist, ifm engineering

Siddhant Wadhwani

Engineering Manager - SDET, Newfold Digital

Session

Stop Writing Tests. Start Training Models

AI-augmented testing systems do not improve by adding more tests; they improve by learning from data, signals, and feedback loops. Test engineers must therefore rethink their role—from test execution to model enablement. This includes curating high-quality training data, defining behavioral constraints, and continuously validating model outputs against real system risks.

Rohit Mehta

Practise Head QAT, Pratham Software

Session

Agentic AI for Testing: A Self-Updating Quality System That Writes, Runs, Explains, and Governs Tests

“AI in testing” often stops at test-case generation or a chat-based assistant. This talk introduces a more differentiated approach: an agentic quality system that continuously converts product change into verified coverage, explains failures with evidence, and enforces governance so teams can trust what ships.

Partha Sarathi Samal

Quality Engineering Manager, Paramount