Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsAfter 15 years working in quality assurance, xulingfeng says starting at a new AI-agent startup brought back the unsettling feeling of being the new person who “has no idea what I’m doing.” In a September 22, 2026, DEV Community post, the author reflects on unfamiliar workflows, the value of understanding before judging, and the tension between sharing hard-won experience with AI agents and being replaced by them.
Why a veteran QA professional felt new again
xulingfeng describes a career spanning manual testing, automation, test development, and test management. After a layoff, a former colleague contacted the author about a tester opening. The author put themself forward, met with the CTO and HR, and began work at a young startup building AI agents for an undisclosed vertical market. The company is not named in the post.
The reset was not about forgetting how to test. It was about entering a team with its own expectations and ways of working. The author says the first days brought back the feeling of not knowing what they were doing, despite years of experience.
What felt different about the new team’s process
The author describes a sequence that ran from product to requirements, development, testing, and shipping. Compared with the previous workplace, the flow initially seemed messy. But the author cautions that a process feeling unfamiliar is not proof that it is wrong. These are early impressions after two weeks, not an independently assessed account of the startup’s methods or results.
Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Scan for outdated or missing drivers - takes under a minuteDriver Scan →One difference the author appreciated was a slower pace that left testers more room to think and make decisions. The post does not quantify that pace or establish that it improved quality; it records what the author valued while adjusting to the new team.
The rule for joining an unfamiliar team
The practical lesson the author draws from those first two weeks is concise: “So my rule for these two weeks: understand first, judge second.” It is a reminder to learn what a workflow is meant to do and why the team uses it before deciding whether it is effective. That approach leaves room to distinguish a genuine problem from a difference in habits, context, or priorities.
What the fictional Mark story says about AI and experience
The post connects the new role to Mark, a character in xulingfeng’s 36 Stratagems story series. In the fictional plot, a company turns a veteran employee’s experience into a skill and then lays him off. The story’s AI skill achieves a stated 96.8% diagnostic accuracy across 312 historical failure scenarios, then misses a 313th case involving a 450ms retry-window compatibility shim originally written for RabbitMQ and later used with Kafka. An old migration note contains relevant context, which surfaces at 4 AM.
Those figures and events belong to fiction: they are not a QA benchmark, a real incident report, or independently verified system results. The story’s point is that a collection of past answers can miss why a decision made sense in its original context. In Mark’s case, the question is not just why the retry window was 450ms rather than 300ms, but what circumstances and judgment led to that choice.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
The author gives the story this closing line: “The AI didn’t fail because it was wrong. It failed because it was right about yesterday — and yesterday wasn’t running anymore.” It is the author’s fictional framing of how circumstances change, not an expert finding about AI systems in general.
Why the author still sees a role for human review
A reader noticed that the Mark story contained a one-year versus five-year timeline inconsistency. The author says they had missed it despite rereading the story more than 30 times. That anecdote supports a modest point: experienced people can overlook errors, too, and a fresh review can catch what a familiar reader has stopped seeing. The reread count and oversight are reported by the author, not independently verified.
Rank #4
The story therefore does not present human judgment as infallible. Rather, it draws attention to the need to preserve context and to keep checking conclusions against the situation at hand, whether the conclusion came from a person or an automated system.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.The uneasy invitation to turn experience into an agent
The author reports seeing two slogans at the workplace: “Your experience is waiting to be forged into an Agent.” and “Great employees get the work done. Great Agents keep getting it done.” Because the employer is unnamed, these should be understood as the author’s account of workplace signs, not as independently verified company statements.
Best Value
For the author, the slogans capture both an opportunity and a concern. They are curious about translating 15 years of professional judgment into an agent and want hands-on experience. At the same time, the idea of encoding a worker’s expertise raises the possibility that automation could replace that worker. The post’s distinction is between copying conclusions and retaining the reasoning, circumstances, and judgment behind them.
What is happening with the author’s story series
xulingfeng says 30 of the 36 stories in the series are complete and the remaining six are paused while they learn the new job, with the intention of finishing them later. The post also names the older-series paperback AI, Ego & Regret and says it is available on Amazon. Its current listing status is unverified, and the author does not present it as a QA manual or AI-testing recommendation.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
