Content by syedarshad (2)

syedarshad walks through a practical workflow for testing AI agents with LangSmith, using Azure OpenAI as the target model. The guide shows how to build an evaluation dataset, run LLM-as-judge scoring (correctness and hallucination checks), and interpret per-example and aggregate results with tracing and experiment views.

syedarshad walks through moving from brittle Playwright selector-based automation to agent-driven testing using GitHub Copilot (GHCP) agents and Model Context Protocol (MCP), including a practical setup flow in VS Code, confidence-scored element discovery, and fallback strategies for more resilient E2E tests.