AI + Verification Workflow
I use AI as a thinking and documentation tool, not as a replacement for my own judgment. In support engineering and cybersecurity, speed matters, but accuracy matters more. My workflow is to use AI to brainstorm, clarify, and organize ideas, then verify important claims through documentation, testing, logs, or my own reasoning before trusting the result.
How I Use AI
- Brainstorming before building: When I am stuck on a feature, workflow, or debugging issue, I use AI to list possible approaches before deciding which one makes the most sense.
- Organizing messy information: If I have scattered notes from a project, lesson, or troubleshooting process, I use AI to help turn them into a clearer outline or explanation.
- Clarifying technical concepts: When I am connecting ideas across WordPress, cybersecurity, APIs, or systems thinking, I use AI to explain unfamiliar concepts in simpler terms. I still verify important details through documentation or testing.
- Improving communication: For portfolio writing, support-style explanations, or peer responses, I use AI to make my ideas clearer while keeping the final wording grounded in what I actually understand.
Verification in Practice
A real example of this workflow is my Calendar AI Assistant project. The goal of that project was to let a user type a natural-language request like “study for physics tomorrow 2–4” and turn it into a structured Google Calendar event. AI was useful for thinking through the architecture, brainstorming missing details, and organizing the user flow, but I still had to verify the actual logic myself.
For example, I had to check whether the user input included the required event details, such as title, date, start time, and end time. If information was missing, the system needed to ask a follow-up question instead of guessing. I also had to think through where human confirmation belonged before the event was created. That verification step matters because an AI-generated interpretation can sound correct while still being wrong, incomplete, or unsafe to trust automatically.
This taught me that AI is strongest when it helps create a plan, but the final responsibility is still mine. I need to test the workflow, check the API behavior, confirm the data structure, and make sure the output matches what the user actually intended.
Why This Matters for My Career Path
This workflow matters for my career path because support engineering and cybersecurity both depend on careful verification. In support work, a quick answer is not enough if it does not actually solve the user’s problem. In cybersecurity, trusting an unverified answer can create risk. My goal is to use AI to move faster while still checking evidence, protecting sensitive information, and making careful decisions.
For a WordPress support engineering role, this means I can use AI to brainstorm possible causes for an issue, but I should still verify through documentation, dashboard settings, logs, plugin behavior, or testing. Long term, this same mindset supports my cybersecurity goals because it trains me to think in terms of evidence, risk, and responsible decision-making.