How I Use AI Tools Personally
Rather than offering a general introduction about myself (as I did last year), I believe sharing how I practically and pragmatically use AI tools provides a better window into my enthusiasm and approach. This article serves as both a personal benchmark and a more authentic way to showcase my AI preferences (including my taste!).
My Current AI Toolkit
Most Frequently Used Models
Additional Tools by Use Case
Search & Deep Research
Strategy: Use multiple tools in parallel, then validate, verify, compare, and combine all findings.
Quick Fact-Checking
(on Twitter/X)
Proofread
Vibe Coding
Voice/Video Interaction
Image Generation
Document/Data Visualization
How I Use AI in Detail
General Use, Search, and Deep Research
My go-to models currently are o3 (the best model in my opinion) and Gemini 2.5 Pro (accessed via Google AI Studio). For quick searches, ChatGPT's online search capability has improved significantly, so I often use GPT-4o directly. If the results aren't satisfactory, I'll retry the search with o3.
Example Search Process
-
1
Start with GPT-4o for the initial search
-
2
If the results are unsatisfactory, rerun the query using o3 (for complex query, I will use o3 directly)
-
3
For more critical topics, run the same query on Gemini and Perplexity as well
-
4
Compare the information across all platforms
-
5
Validate and verify the findings, then combine the insights to build a complete understanding
For instance, when researching information for my annual physical check-up, I start by using o3 for an initial search and then leverage its capabilities for Deep Research.
UHIP Green Shield Physicals
Medical information research example
Comprehensive analysis of health insurance coverage options and recommended medical check-ups for students...
UofT Residency Research
Cross-verification example
Detailed comparison of on-campus housing options, rental costs, and living arrangements at University of Toronto...
Deep Research Highlights
For topics warranting Deep Research, I use ChatGPT, Gemini, Grok, and Perplexity with identical prompts to compare their outputs. An interesting application was analyzing whether to take a summer course. I provided detailed personal information across different models. Ultimately, I referred to their analyses but decided against the course. Deep research is much better than general online advice for such personalized decisions. The final decision is from myself.
Graduation Timing Analysis
Deep analysis of graduation timing for Canadian residency
Canada PR Prospects Analysis
Comprehensive analysis of permanent residency prospects in Canada
(Those two websites were generated by Deep Research content with my visualization tool in one shot.)
The capabilities demonstrated in Deep Research are moments where I first felt a glimpse of AGI this year.
Prompt Enhancement
I also enhance my original prompts after drafting them when necessary. With more advanced models, simply typing "improve the prompt" is often enough.
For general users, the most important prompt technique isn't mastering complex methods, but rather clearly articulating what you want and providing sufficient background information.
Writing & Proofreading
As a non-native English speaker, proofreading is an essential use case for me. AI tools consistently outperform my own abilities in this area.
English Translator GPT
For general proofreading and translation refinement
Email Refiner GPT
Specifically optimized for professional email communication
For more formal or high-stakes writing, I turn to GPT-4.5 for proofreading or use Claude 4 Sonnet to enhance the overall quality and maintain nuance in complex content.
Voice and Video Interaction
I increasingly use voice/video interaction, especially in practical situations like cooking where I can show ingredients and get instant feedback.
Voice and video interaction with AI assistants provides a more natural and hands-free experience
Grok
Grok's voice mode
ChatGPT
ChatGPT's voice mode
Language Learning Applications
These tools are excellent for language learning. One of my proudest creations is my IELTS Speaking Simulator, which provides realistic speaking practice with detailed feedback.
IELTS Speaking Simulator
Visualization (Transforming Documents into Web Content)
A new and highly useful application I discovered this year is the ability to easily transform documents into visually stunning websites and even slide decks. My first experience with this, visualizing a 60-plus-page document in early March, was the second time I truly felt the proximity of AGI. It feels like having a superpower.
Since then, I've visualized numerous items using Claude 4 Sonnet and Gemini 2.5 Pro. I started with raw APIs, then experimented with Poe. Now, through 'vibe coding,' I use my own File Visualizer and Cursor for further modifications.
(Even this website was created using this approach!)
Visualization Tools
Examples of My Visualizations
PQC Companies Analysis
TIM5303B Assignment
Beyond the Numbers
Data-Driven Product Decisions
AI-Assisted Note-Taking
Research Paper
Deep Research Guide
For Canadian SMEs
Epic Road Trip
Ottawa to St. Pierre & Miquelon
Literature Review Guide
Scoping Reviews with AI Tools
Media Generation
I primarily use GPT-4o for image generation. When I first tried this feature in March 2025, it was the third time I truly felt the presence of AGI.
For one-page content that isn't too lengthy, I use it directly, though my usage has decreased after the initial excitement. The quality of AI-generated images continues to improve.
Honestly, I rarely use AI for audio and video generation. The barrier to creating exactly what I want is still quite high for these formats, though I'm monitoring progress in this area.
A Personal Avatar Upgrade Story
Another usage happened on May is that Thanks to an "Airbnb-style soft isometric icon" prompt, I finally updated my avatar. My previous avatar was one I manually sketched in PowerPoint 11 years ago!
Ever since creating that flat design, I've wanted to upgrade it to a skeuomorphic style, but I didn't have the profound design skills to make it happen and meet my standards. So, every time I tried a new image-generation AI tool, I'd upload my old avatar, hoping for an upgrade—but nothing felt right. It was the Airbnb-style prompt that finally helped me overcome that hurdle.
Old Avatar (2014-2025)
New Avatar (2025)
To make this powerful prompt accessible and efficient, I've fine-tuned it multiple times and created a new GPT: the "3D Avatar Icon Maker." Now, you can just visit my GPT, upload your image, and get your 3D isometric avatar instantly! You can access it for free—even without ChatGPT Plus.
3D Avatar Icon Maker
Create a 3D isometric avatar from your image
It's truly fantastic to see these results—and this is just the beginning!
Vibe Coding
Cursor is my go-to "vibe coding" tool right now. I also experiment with other tools concurrently, typically inputting the same prompt into each to see if they can deliver the desired result in just a few shots. For me, a key indicator of AGI in this context is the ability of the AI to deliver on my articulated thoughts in one-shot without needing further clarification or conversation.
Cursor
My primary vibe coding tool, utilizing two powerful models:
Projects Created with Vibe Coding
File Visualizer
Transform your plain documents into stunning, interactive websites
Advantage Builder
Tool for program advantage building, created by Lovable and modified in Cursor
Cursor's agent mode has significantly expanded my capabilities (felt the Jagged AGI again!). However, it struggles with backend issues, often requiring multiple rounds of conversation.
"Vibe coding" currently excels for personal and small projects, especially for users without deep technical backgrounds. To further empower developers like myself, we need more powerful models with longer context windows and improved techniques.
Miscellaneous Tools
Meeting Notes
Notion AI Meeting Notes feature is amazing! Previously used Limitless AI for such tasks.
Browser
Experimented with AI browsers like Dia and Comet, but still prefer Arc.
What Services I Subscribe To
Some of my friends are curious about which AI services I subscribe to. Currently, I am not paying for any AI services, thanks to the following student benefits:
Current Benefits
ChatGPT Plus
2-month free student offerClaude API
$50 credit (student developers)Perplexity Pro
1-year free for my university
Cursor Pro
1-year free for students
Past Subscriptions
Gemini Advanced
Subscribed to experience Gemini Deep Research, but for tasks other than deep research, Gemini 2.5 Pro in Google AI Studio is better.
ChatGPT Plus & OpenAI API
Plan to subscribe after free period ends. Used OpenAI API for testing purposes.
That's all for May 2025's update.
While drafting this piece, I realized it's comprehensive enough to serve as an annual review. Surprisingly, it's only May 2025—not even halfway through the year! I'm excited to see what's ahead.