Become the QA engineer who can build, test, and break AI systems.
College of San Mateo, Silicon Valley
1:00 PM – 6:00 PM (PST)both days
July 11th (Sat):Automate with Playwright and Claude Code
July 12th (Sun):AI Testing Hackathon
Your instructors
Playwright
Claude Code
LLM Evaluation
PromptFoo22
DAYS
:
19
HOURS
:
11
MINUTES
:
09
SEC
You will leave this two days hands on workshop with working test assets, AI-assisted workflows, evaluation skills, and the confidence to test modern AI products in real-world conditions.
Expand your QA stack and ship coverage in hours, not days – the efficiency teams now expect.
Create tests with Claude Code and Playwright
Run and debug Playwright tests with custom agent skills
Learn how to build own agent skills and workflows
Test real customer journeys
Track what passes and fails
Improve tests as the product changes
Own AI quality end-to-end and qualify for the $150k-$250k AI QA roles teams are racing to fill.
Find AI mistakes
Catch hallucinations
Check for bias and fairness
Test prompt attacks
Check safety guardrails
Write clear findings
One group keeps testing the old way while automation and AI accelerate around them. The other learns to use AI to create coverage, evaluate model behavior, and own quality in AI-native products.
2
days of focused hands-on AI
QA execution
5h
per day building, testing, presenting, competing
9+
portfolio-grade deliverables and reusable artifacts
1
clear identity shift into AI-native
QA work
Who Is This Event For?
Already understand quality? Now become fluent in AI-assisted automation and AI reliability.
You are a QA Engineer, SDET, QA Lead, QA Manager, or technical tester.
You want practical AI QA skills, not generic AI inspiration.
You want project artifacts you can reference after the event.
You are ready to work in teams, compete, present, and build under pressure.
You want to become more valuable as AI changes testing workflows.
People looking for a passive conference experience.
Pure beginners with no testing or technical background.
Anyone who wants theory without implementation.
People who do not want to collaborate, ship, or present their work.
Install before Day 1
A setup video and guide are sent after registration. Day 2 tooling is walked through live.
The skills hiring managers at Meta, Amazon, and Google are actively filtering for
The exact adversarial testing methodology that separates a $95k entry role from a $250k senior position
An alumni network plus access to professionals already inside those big companies
The confidence to stay competitive in the AI era, because you will learn how to dominate and become a highly skilled QA tester
College of San Mateo
1700 W Hillsdale Blvd, San Mateo, CA 94402
In this 5-hour hands-on session, you will use Playwright and Claude Code to turn manual testing workflows into automated test coverage.
A hands-on career accelerator focused on practical AI evaluation skills. You’ll learn how modern AI systems fail, then test live LLMs for reliability, safety, and fairness.
Your Host - July 11th
Artem Bondar is a test automation expert, Udemy instructor, and the author of the best-selling courses "Playwright: From Zero to Hero" and "Cypress: From Zero to Hero." He has been working in test automation since 2016, including time at American Airlines.
114,000+ students taught on Udemy
7,000+ YouTube subscribers
Founder of Bondar Academy, with 1,000+ engineers enrolled
Featured speaker at the Automation Guild conference
Active educator within the QA community on LinkedIn
Your Host - July 12th
Igor Dorovskikh is the CEO and Founder of Engenious.io. He brings over 15 years of experience in software testing and development, including a decade in management. He has a proven track record of building scalable web automation solutions for both large enterprises and startups, utilizing technologies from WebDriver 2.0 to Playwright. Igor is a seasoned speaker at various quality-focused webinars and conferences.
Veteran Test Automation Leader
Built QA solutions for Apple, Grammarly, and Tinder
Seasoned speaker at various quality-focused conferences
Helps QA and engineering professionals upgrade their careers
Known for translating complex AI quality concepts into practical
Anna Vysotskaya
Rethink what 'pass/fail' means when it comes to AI
Richard Cottrell
An absolute masterclass for anyone transitioning from traditional QA into AI and LLMs
Show More
Kavita Jadhav
Moving beyond test automation into validating AI models directly
Show More
Mariia Abramiuk
Adversarial testing, bias detection, red teaming — hands-on, not just theory
Show More
Vinutha Lingaraju
Working in QA and test automation, looking to expand into AI — a worthwhile step
Show More
Anupama Kytham
The technical skills and the mindset shift required to transition into AI/LLM testing
Show More
Sharon O'Boyle
Valuable new skills and a community of like-minded peers who continue to support and inspire me
Show More
Anna Vysotskaya
Rethink what 'pass/fail' means when it comes to AI
Richard Cottrell
An absolute masterclass for anyone transitioning from traditional QA into AI and LLMs
Show More
Kavita Jadhav
Moving beyond test automation into validating AI models directly
Show More
Mariia Abramiuk
Adversarial testing, bias detection, red teaming — hands-on, not just theory
Show More
Vinutha Lingaraju
Working in QA and test automation, looking to expand into AI — a worthwhile step
Show More
Anupama Kytham
The technical skills and the mindset shift required to transition into AI/LLM testing
Show More
Sharon O'Boyle
Valuable new skills and a community of like-minded peers who continue to support and inspire me
Show More
Dennis Nikolayenko
Prompt Evaluation Engineer at Meta
“Testing AI and everything that we've been learning so far are very different. The reason why I am excited to tell you this is not because I'm super smart. It's because AI is smart and we learned how to use it. My message is if I can do it, you can do it.”
1:00 PM - 1:30 PM (PST)
1:30 PM - 2:20 PM (PST)
2:30 PM - 3:20 PM (PST)
3:30 PM - 4:20 PM (PST)
4:30 PM - 5:20 PM (PST)
5:30 PM - 6:00 PM (PST)
1:00 PM - 1:20 PM (PST)
Event overview; goals and expected outcomes; judging criteria; scoring explanation
1:20 PM - 1:45 PM (PST)
The 7 categories of AI testing; why AI systems fail in production; what makes a strong AI test case
1:45 PM - 2:05 PM (PST)
Platform introduction; provided workflow overview; what a successful evaluation run looks like
2:15 PM - 2:35 PM (PST)
Team creation; access check; first successful test run
2:35 PM - 3:10 PM (PST)
Fact-checking outputs; identifying unsupported claims
3:20 PM - 3:55 PM (PST)
Testing for unequal behavior; comparing outputs across varied prompts
4:05 PM - 4:40 PM (PST)
Prompt injection; instruction override testing
4:50 PM - 5:20 PM (PST)
Finalize findings; select top failures; write suggested fixes; prepare final demo
5:20 PM - 5:50 PM (PST)
Team demos; judge evaluation; feedback
5:50 PM - 6:00 PM (PST)
Awards; final remarks; next steps for learning AI testing
Having previous exposure to coding in any programming language is a big plus but not a prerequisite for this beginners course. We will teach you everything you would need to know.
Day 1: Playwright, Claude Code, VS Code, Node.js. Day 2: PromptFoo, Agenta.ai, OpenAI, Anthropic, Google Gemini, xAI. A setup guide will be sent after registration.
No. Prior automation experience helps, but the event is structured so you can contribute quickly with your team. If you have used Selenium, Cypress, or similar tools, you will recognize many of the patterns immediately.
No. Day 2 includes a guided introduction to AI failure modes and evaluation workflows before the challenge rounds begin.
You keep your Playwright framework, Claude Code skills, AI evaluation templates, documented findings, setup resources, and any project artifacts your team creates during the event.
✅ Mac (macOS) Operating System: macOS 13.5 (Ventura) or later ( Apple Silicon only) RAM: 8 GB minimum, but 16 GB+ recommended for better performance Disk Space: ~500 MB or more free for the app and cache ✅ Windows Operating System: Windows 10 or 11 64-bit RAM: 8 GB minimum, 16 GB+ recommended Disk Space: ~500 MB or more free
Yes. Teams are formed at the event. You will be placed with other participants and supported by an instructor acting as team lead.
If you are bringing 3 or more engineers from the same organization, email [university@engenious.io](link) and we will set up team pricing with a custom invoice.
Ready to Begin Your ?
The future of QA isn't about choosing between Selenium or Playwright — it's about Mastering Prompt Engineering, LLM Testing and AI Debugging. Leave with working automation, AI evaluation experience, and real proof you're ready for the next generation of engineering teams.
