Jags's Blog

Building an AI Agent That Debugs Your Tests

From flaky test frustration to automated root-cause analysis

Jul 6, 20261 min read31

Part 4: Building Evals - How Do You Know Your Agent Is Getting Smarter?

The eval suite that turns every wrong answer into a permanent guard

Jul 6, 20269 min read21

Part 3: Securing an AI Agent Against Its Own Input

Four layers of defense for an AI that reads untrusted data

Jul 6, 20267 min read

Part 2: Teaching an AI Agent to Reason — Skills, Phases & Dead-End Triggers

How structured Chain-of-Thought stops an LLM from jumping to wrong conclusions

Jul 6, 20268 min read14

Part 1: Why I Built an AI Agent to Debug My Playwright Tests

From 60-minute debugging sessions to 2-minute automated diagnoses

Jul 6, 20266 min read13

Papershelf

Papershelf

Dive into the World of LLMs and Test Automation with my research-focused blog post & papers

Jan 14, 20251 min read22

My 2025 Bookshelf

My 2025 Bookshelf

Pages Yet to Turn: The Books I'm Looking Forward to in 2025

Jan 8, 20251 min read10

Mastering API Testing: A Comparison of HAR Files and Mocking Techniques

Mastering API Testing: A Comparison of HAR Files and Mocking Techniques

Using HAR Files vs Mocking: A Guide to Testing API Interactions

Sep 18, 20243 min read94

Mastering Playwright: Learn secure HAR-Based Mocking in Playwright

Mastering Playwright: Learn secure HAR-Based Mocking in Playwright

Mastering Secure HAR-Usage in Playwright: Best Practices Inside

Sep 18, 20242 min read847