Ramya
Authappan
QE Architect/Independent Consultant
"Self Healing Playwright Test Workflow using Github Actions and Claude Agent SDK"
"Self Healing Playwright Test Workflow using Github Actions and Claude Agent SDK"
Wed May 13 - 5:30 AM EDT/New York (See in local time)
Add to Calendar
05/13/2026 5:30 AM
05/13/2026 05:50 AM
America/New_York
#WTGC2026
"Self Healing Playwright Test Workflow using Github Actions and Claude Agent SDK"
#WTGC2026
"Self Healing Playwright Test Workflow using Github Actions and Claude Agent SDK"
https://www.womentech.net/ringcentral
https://www.womentech.net/ringcentral
"Self Healing Playwright Test Workflow using Github Actions and Claude Agent SDK"
"Self Healing Playwright Test Workflow using Github Actions and Claude Agent SDK"
Don’t miss out and join visionaries, innovators, and thought leaders from all over the world at the Women in Tech Global Conference.
Vote by Sharing
Unite 100 000 Women in Tech to Drive Change with Purpose and Impact.
Do you want to see this session? Help increase the sharing count and the session visibility. Sessions with +10 votes will be available to career ticket holders.
Please note that it might take some time until your share & vote is reflected.
Session: Self Healing Playwright Test Workflow using Github Actions and Claude Agent SDK
Modern web applications demand robust end-to-end test coverage, yet maintaining Playwright test suites at scale remains a persistent engineering challenge. Flaky tests, selector drift, and timing issues can consume significant developer time—time better spent on feature development.In this talk, I'll share how we built a fully autonomous test healing pipeline that transforms how our team handles E2E test failures. Our system leverages the Model Context Protocol (MCP) to create an intelligent agent that doesn't just identify failures—it fixes them.What you'll learn:The Architecture: How Playwright Test Healer integrates with MCP to provide AI agents with deep test context, browser automation capabilities, and codebase awareness
CI/CD Integration: Our approach to embedding the healing workflow seamlessly into GitHub Actions, including failure detection, triage, and automated fix generation
Developer Experience: How we simplified the entire workflow to a single slash command—/fix-playwright-test <test_file>—that triggers autonomous debugging, generates fixes, and commits suggestions directly to your PR
Real-World Impact: Quantitative results showing reduced mean-time-to-recovery, increased test stability, and reclaimed developer hours
The result? A paradigm shift from reactive debugging to proactive test maintenance. When tests fail in CI, an AI agent analyzes the failure, navigates the application, identifies the root cause, and proposes fixes—all without human intervention.This isn't just about fixing broken tests; it's about reimagining developer productivity in the era of AI-assisted development.
Key Takeaways
- How Playwright Test Healer integrates with Claude Agent SDK and MCP for AI-powered test context
- How Single slash command triggers autonomous debugging and fixes using AI agents
- Seamless GitHub Actions workflow for automated test healing and intelligent failure analysis
- Quantitative results: reduced MTTR, increased test stability, reclaimed developer hours
Bio
I'm Ramya Authappan — a QE Architect/Consultant at Razion Technologies with 15+ years of experience transforming quality engineering practices across enterprise and high-growth tech companies. My career spans roles at Juniper Networks, Amazon, Freshworks, GitLab, and now Circle, where I've consistently delivered measurable improvements in test reliability, developer velocity, and release confidence.After leading engineering teams for several years and exploring the engineer–manager pendulum concept by Charity Majors, I deliberately returned to hands-on engineering to focus on the cutting edge of test automation and AI-driven quality engineering — where I believe the most impactful work is happening today.
At Circle, I'm pioneering the integration of AI into our quality processes, working with advanced Playwright automation, Claude Code MCP, and Buildkite MCP to build self-healing test systems that automatically diagnose, repair, and optimize themselves. This initiative aims to significantly reduce flaky tests and manual intervention while improving deployment confidence.
Previously at GitLab, I led a distributed quality engineering team across multiple time zones, architecting scalable CI/CD pipelines and establishing quality frameworks that supported rapid product growth. At Freshworks, I built comprehensive test frameworks for microservices architecture and championed Consumer-Driven Contract testing across the organization. My time at Amazon involved optimizing large-scale test suites, reducing execution time from hours to minutes through intelligent parallelization.
Beyond my technical work, I'm passionate about building inclusive tech communities. As Director of Women Who Code Chennai (2018-2024), I mentored speakers, organized educational meetups, and created pathways for women to advance in technology careers.
Portfolio: https://ramya-site.vercel.app/
