I'm Murilo, a senior QA automation engineer in Fortaleza, Brazil.
Most bugs that hurt don't crash anything. A role sees data it shouldn't, a slow response overwrites a newer one, a data check stays green while the pipeline is broken.
I built six open-source labs around exactly that kind of failure, and every one of them runs in CI. Over the next weeks I'll post one real finding from each.
94 tests passed. The feature did nothing.
The check was reading its own log entry, so it passed no matter what the code did.
Since then, I don't trust a test until I've watched it fail:
1. Remove the thing the test guards
2. Run it: it should fail
3. Put it back: it should pass
If step 2 passes, the test is useless.
Across ~1,900 tests on a production platform, this is the habit my client valued most. Do you check that your tests can fail?
This matters even more when AI writes the tests, because it will happily write a check that agrees with the code. I now ask for a deliberate break first and only trust a test once it goes red.
Most Claude Code sessions go wrong in the first message.
Not because the model is weak, but because the starting prompt is vague: “fix this bug” or “add tests.” With nothing else to go on, the model starts editing before it has looked at the repository, and you spend the next ten minutes steering it back.
What changes the outcome is the order of the work. Inspect the repo first. Learn the existing conventions. Plan before editing. Make focused changes, add or update tests, run real commands to verify, then summarize what changed. A prompt that builds that sequence in means you don’t have to remember to ask for it every time.
I put together a set of 2,000 prompts around that workflow, covering areas like debugging, testing, security, architecture, APIs, and cloud. They come as JSON, CSV, and JSONL, so you can browse them, filter them, or feed them into your own scripts.
Plan before editing is the step I see skipped most. When I build with Claude, asking it to restate the repo's conventions back to me before any change catches most wrong assumptions early.
A business owner told me she spent 3 hours every morning just copying customer details from emails into a spreadsheet.
I built her a simple automation. Now it takes zero minutes, and it runs while she sleeps.
That’s the part people miss about automation. It’s not about fancy tech. It’s about getting your time back.
Here are 3 signs your business is ready for automation:
1. You do the same task more than 3 times a week.
2. You copy and paste between different apps.
3. Things slip through the cracks because everything depends on you remembering
If you said yes to even one, you’re losing time and money right now.
I help businesses and creators automate the boring stuff so they can focus on what matters.
Follow me for practical automation tips every week, and DM me if you want help with your own workflow.