The AI models I Use for Work
Published Jul 23, 2025
⋅
Updated Jul 23, 2025
⋅
2 minutes read
Here are some rough notes on the AI models I use as of July 2nd, 2025.
Important Caveats
- The models listed below reflect my current personal preferences and what works best for my specific workflows.
- I strongly encourage everyone to look at benchmarks and then test out different models for themselves.
- This list is a snapshot in time and is likely to change monthly, if not more frequently, as new models are released, existing ones are updated and I continue exploring new ways of working with them.
Search & Answer Engines
| Tool | Use Case |
|---|---|
| Kagi | My primary search engine. Think "Google, but significantly better" with no ads and customizable results. |
| OpenAI o3 | Excellent as an "answer engine" that can search the web and provide reasoned, synthesized answers to "stupid" and complex questions. |
| Gemini Advanced Deep Research | Seems to produce reports I appreciate more than OpenAI's. |
| Claude Research | I'm currently exploring this and like the breadth of searches coupled with shorter final reports than other providers. Verdict TBD. |
Writing & Content Creation
| Tool | Use Case |
|---|---|
| Claude Opus 4 | My go-to for general copywriting help, creative writing tasks, translation, and editing existing text. |
| ChatGPT 4.5 | Particularly strong for structuring and expanding on my ideas to create better research queries. |
| Gemini 2.5 Pro | Excellent for creating structured documents like guides, proposals, and grant applications. |
Image Generation
| Tool | Use Case |
|---|---|
| GPT-4o & Gemini Image Generation | Useful for quick edits, brainstorming visual ideas, and initial explorations. |
| Midjourney | My preferred choice for any serious image generation when final quality, artistic control and taste matter. |
"AI Chores" (Utility Tasks)
| Tool | Use Case |
|---|---|
| Gemini 2.5 Flash | Great for quick tasks like reformatting text, reorganizing information, extracting text or scanning receipts and other less complex data manipulation. |
| Gemini 2.5 Pro | My choice for summarizing lengthy texts, synthesizing research from multiple documents, and structuring longer documents. |
Powering AI Helpers
A Combination Approach: I often use a mix of OpenAI o3 Pro, OpenAI o3, Gemini 2.5 Pro, and Claude Opus 4 to power different aspects of my AI advisors or personas, depending on the specific task the persona is undertaking (e.g., research, writing, critical analysis).
Coding
| Tool | Use Case |
|---|---|
| v0 | For generating quick UI prototypes or landing page mockups using text prompts and scribbled wireframes. |
| Cursor | For any serious development work, I use Cursor for its code autocomplete. I use Claude Sonnet 4 for small changes in Ask or Agent mode. |
| Claude Code | For more complex tasks, Claude code with Opus 4 has completely replaced my use of Cursor's coding agent. Usage limits are much higher and results seem to be betters so far. |
Feel free to use this list as a starting point, but please experiment and discover what works best for you!
PS: The next cohort of my AI literacy for business course starts on September 2nd in case you'd like structured guidance on how to implement these tools to support your work.