I would like to share some useful tricks I have learned today. 1. Manage well context window. The context window is the current chat session with Copilot agents. It includes your prompts, system instructions, and historical conversations. The longer the conversation is, the more tokens it costs because the agent will retrieve past context, which may no longer be relevant. 2. Choose right model for right task High reasoning model like Opus, Codex are great for planning, architecture, handling complex bug. Second tier models like Sonnet is great for implementation based on the plan from previous steps. And lower tier model like Haiku for small refactoring. --> An important thing to note is that because agents load historical conversation, so low level of accuracy from beginning can compound the inaccuracy. That's why in the beginning stage like researching, planning, the strongest models are able to produce the best quality. 3. Prompt skill Prompt skill also plays an import...
Playwright is a modern end‑to‑end testing framework developed by Microsoft. It supports multiple programming languages, including TypeScript, JavaScript, C#, and Java, and can run tests across all major modern browsers. Its flexibility and developer‑friendly features make it a compelling choice for UI automation. Here is some core features that I find very useful when working with e2e test with Playwright: 1. Automatic test generation Using the VS Code extension, you can start a recording session where a browser window opens and captures your interactions. As you click, type, and navigate, Playwright automatically writes the corresponding test code for you. After recording, all you need to do is refine the assertions. This feature dramatically speeds up test creation, especially for complex user flows. 2. Pick locator When running your test in the browser, you can activate Pick Locator to visually select any element on the page. Playwright will instantly generate the correct locat...