Building on the last experiment, this one was about remixing Two Concepts into a Unified Design Direction (with and without personal input). I asked ai to combine two of the stronger ideas into one new concept. Without the persona, the idea was generic and lacked emotional depth. Adding a persona made a huge difference: the revised output felt significantly more human-centered and aligned with the user journey.

https://docs.google.com/document/d/1H25BB_ejzukHnM8jRKCNloQpB8IzBeZGbkSmCbHLxeI/edit?usp=sharing

#aiexperimentlog #2Spotify #mediumsuccess

Lastly, after my interview experiment, I asked three of my friends (the fourth went to bed) to attempt to figure out which questions were and weren't AI.

The results were very interesting — but I think the AI questions are a bit too long and don't fit interview best practices.

PS. I think we should do more "non-AI" experiment tie ins...

https://docs.google.com/document/d/1UIt4yc2j2ivxYxK-ODLcGneAr1KbNq7TbIC7T3uA1zI/edit?tab=t.l4dhz2en7nic

#aiexperimentlog #3pinterest #mediumsuccess

This experiment builds on my last one—I let AI generate a wide range of ideas. Same issue: too many broad results, making tighter prompts essential for quality. However, once I focused on a specific angle, AI provided surprisingly structured frameworks.

One standout: rethinking podcast recommendations through cognitive triggers and self-exploration—a fresh direction I hadn’t considered.

https://docs.google.com/document/d/148iE3JBI4wsg59mi5NdBiU3LX6BwxYzC_KijDxO-km0/edit?tab=t.0

#aiexperimentlog #2Spotify #mediumsuccess

I used ChatGPT to generate HMW questions from my Spotify personas. The results came quickly and were well-organized into categories. However, even with prompt limits, the output was overwhelming and lacked prioritization. My biggest challenge when using AI is narrowing down the scope of its generated results.

https://docs.google.com/document/d/1xgXSry_xFcIJLFMjxJAfXDxK-2Sd6KaB95S_eP9WXHA/edit?tab=t.0

#aiexperimentlog #2Spotify #mediumsuccess

Needed faux data for my SAS project, so I had ChatGPT whip up some commercial real estate listings. Fed it detailed scenarios, personas, and project goals—what I got? Decent wireframe-ready content (but don’t ask it to budget your rent 💸😂). Honestly, way better than Lorem Ipsum for prototyping, and I can see this being a handy tool for ideation too. Quick, easy, and surprisingly fun to experiment with.

https://docs.google.com/document/d/1UIt4yc2j2ivxYxK-ODLcGneAr1KbNq7TbIC7T3uA1zI/edit?tab=t.yk0r95nsyy6m

#aiexperimentlog #3pinterest #mediumsuccess

Put ChatGPT to the test for songwriting ideas—because if there’s one thing I love, it’s a clever concept. AI held its own, but let’s just say… its ideas leaned more ridiculous than refined. AI’s take? Let’s just say it’s got enthusiasm. Still, this experiment got me thinking—can AI-generated absurdity spark unexpected genius? 🤔🎶

https://docs.google.com/document/d/1UIt4yc2j2ivxYxK-ODLcGneAr1KbNq7TbIC7T3uA1zI/edit?tab=t.9ey8m9yb41r2

#aiexperimentlog #3pinterest #mediumsuccess

In this experiment, I want AI to guide me to identify key insights from the persona which I can use for my next Ideation phase. The results were mostly expected, reinforcing the importance of a researcher’s own judgment. However, the AI introduced the P.A.T.H. framework, which I found surprisingly useful for analyzing my personas.

https://docs.google.com/document/d/1X-RO1_-bvqe93FV5Yn8en4HeT1WqjJbydIZnv9hboyE/edit?tab=t.0
#aiexperimentlog #2Spotify #mediumsuccess

Tested ChatGPT for uncovering hidden user motivations and patterns in Pinterest behavior from a simulated quantitative dataset I generated in my Experiment 2. At first, it kept giving me structured tables instead of qualitative insights, but after some nudging, it got there.

Find log here - https://docs.google.com/document/d/1SyJeGzKBqSUd0F4UuBZ_TpCZCSMvY_RwyUnonzSjJrA/edit?usp=sharing

#3pinterest #aiexperimentlog #mediumsuccess

A silly experiment, but an experiment nonetheless... I decided to test Photoshop's "generate image" feature by creating a series of pies. This doesn't apply to any of my three small study questions, but I "chased the fun" as Laura suggested last Friday.

If anyone would like to play with this functionality, I'd love to see some more pies ! I want to push and break Photoshop's tool and see what it can and cannot do.

https://docs.google.com/document/d/1UIt4yc2j2ivxYxK-ODLcGneAr1KbNq7TbIC7T3uA1zI/edit?tab=t.dlxq5zvrstiz

#aiexperimentlog #3pinterest #mediumsuccess

@siqijiang I based on Siqi's experiment log, retest the persona Ai assistant to let it generate a persona for me from a UX research perspective. Although AI is considerate and solves accessibility issues for elderly users, it defaults to younger users and overemphasizes the preference for commercial content for Chinese users.

https://docs.google.com/document/d/1lf84CCVCywnqnqCC9I-b0-iY-Qov7FN0d7JKtl12_qg/edit?tab=t.0#heading=h.hvyv5qk554ie

#aiexperimentlog #2Spotify #mediumsuccess