@yihui_indie: I've been away from the workplace for too long. I'm now very curious about QA work in big companies—is it still the same workflow as before? That is, after finding a bug, you file a ticket to the developers. Because I've realized that when I submit a bug to the devs now, the submitted bug itself is a prompt for AI. I think…
Summary
After leaving the workplace, the author is curious whether the workflow of QA in big companies remains the same—submitting a ticket after finding a bug—and believes that submitting a bug can itself be seen as a prompt for AI, so it might be better to directly let AI modify the code.
View Cached Full Text
Cached at: 05/31/26, 12:48 PM
I’ve been away from the workplace for a long time. I’m now curious about how QA works in big companies—is it still the same workflow as before? That is, file a ticket for RD after finding a bug.
Because I’ve realized that when I file a bug for the developers now, the bug report itself is essentially a prompt for AI. I feel it might be more efficient to just pull the corresponding branch and send it directly to AI for fixing.
Similar Articles
@Ryrenz: Most people using coding AI just say “help me fix this bug,” then spend half an hour wrestling with it. Change the phrasing and it gets it right the first time. 1. Have it look before acting “Don't write code yet. Read the relevant files and tell me how this feature currently works; I'll confirm before you change it.” 2. Stuck bug “Don't guess. Add log…
A practical tip on how to use coding AI more effectively. It lists 12 concrete prompt examples—such as having the AI read the code before modifying it, changing only the necessary parts, and writing rules into AGENTS.md—to reduce back-and-forth and make the rules stick long-term.
@bozhou_ai: https://x.com/bozhou_ai/status/2074030629956780417
Based on Anthropic employee Thariq's article "A Field Guide to Fable", the author rethinks the management of unknowns in AI programming workflows. It proposes methods such as blind spot scanning, multi-version prototyping, AI interviews, implementation notes, and quizzes, emphasizing the importance of discovering unknown factors before coding to reduce rework.
@ThisisHan1_: Recently built a development pipeline and wanted to share the thinking behind it. I was inspired by loop/goal engineering and auto-goal (letting the agent write its own goals and spawn subtasks). But what really clicked for me was...
This development pipeline first creates a rough prototype to elicit user feedback, turning every 'that's not right' reaction into a checkable rule. Then AI agents independently develop and validate against those rules, catching issues early and avoiding self-deception.
How do you write a bug ticket differently now that you know an AI agent might pick it up before a human does?
The article discusses the emerging shift in how engineers write bug tickets to be understood by AI agents, noting increased documentation rigor and workflow challenges.
@vikingmute: Great workflow, now it's also my main workflow for developing new features and new ideas: Grill - let AI fiercely question every detail until clear -> Research - separately analyze difficult areas and create a research document (optional) -> PRD - gen...
VikingMute shares their main workflow for developing new features and ideas: using AI (Grill) to drill down on details, Research to analyze difficulties, generating a PRD, breaking it into independent Issues, step-by-step implementation, and finally Review. This is a supplement to Matt Pocock's seven-stage AI development method.