Used reverse thinking prompts via the NNG Research Assistant to generate bad ideas and surprisingly, they sparked some interesting design directions. AI even guided the process like a creative partner, clustering prompts and suggesting next steps.
Still figuring out how to best use reverse thinking, but the creative energy was real.
#aiexperimentlog #1linkedin
#medsuccess

https://docs.google.com/document/d/1jdN0lmkWmsvg3bM7FWz69mRcn7PmBwowVftvd5e7iKk/edit?tab=t.djn9fxgy1224

Tried out Cohere and ChatGPT to explore one HMW statement deeply — from idea generation to user journey, pros/cons, and feasibility analysis. Learned how powerful AI can be in shaping and critiquing early concepts.
#aiexperimentlog #1linkedin
#highsuccess

https://docs.google.com/document/d/1jdN0lmkWmsvg3bM7FWz69mRcn7PmBwowVftvd5e7iKk/edit?tab=t.vi9qsr8ci66a

Created a character in character.ai based on the user persona for the Pinterest project. So far, the character I created liked both my good idea and the bad idea. But this gave me ideas on how to enrich and improve this experiment.

Google doc: https://docs.google.com/document/d/1kRncIijZV49zbs_3iWEXb2eilikHKYMmuimhQN6S2Xo/edit?usp=sharing

#aiexperimentlog #3pinterest #medsuccess

User stories in the "define" phase of the design process can be generated pretty accurately and give a designer a start. I used one user persona and a user journey map.

Google doc: https://docs.google.com/document/d/17d6sBLnmkoJaDinzEWMJyWoCkw3WQqjNLnf0MkwAeEI/edit?usp=sharing

#aiexperimentlog #3pinterest #highsuccess

Trendwatching AI Innovations Expert felt like I was working with an analyst. However, the amount of information can be overwhelming.

Google Doc: https://docs.google.com/document/d/1nz-w80StWClTs4xOcZOiHwtnYIcSPg8vHN9KRX3U5I0/edit?usp=sharing

#aiexperimentlog #3pinterest #highsuccess

It was time to prioritize the ideas, I used NN/g Research Assistant and Feasibility x Impact Matrix. The top results were predictable and accurate.

Google Doc: https://docs.google.com/document/d/1SN75K1qRZQag_0bWUJZMzDNSxrcs_QemO29bSztR1T0/edit?usp=sharing

#aiexperimentlog #3pinterest #medsuccess

Recreated @kimayac experiment with Claude, creating a 2x2 ideation matrix. For me, Claude didn't make a visualization, and I had to prompt it. The result was confusing.

Google Doc: https://docs.google.com/document/d/1i-OkZv73A6VdS3UgWpBGfcV-mHjqGv6pmJQNwPtmyd8/edit?usp=sharing

#aiexperimentlog #3pinterest #medsuccess

Continuing somewhat with my methodology from the "six hats" experiment, I tried another method: four categories. The results weren't as good as the previous one, but I'm still satisfied with it. Lots of interesting ideas and loving Chat-GPT providing "rationale" for it all. Could be helpful as a tertiary tool for human brainstorming, I reckon !

https://docs.google.com/document/d/1UIt4yc2j2ivxYxK-ODLcGneAr1KbNq7TbIC7T3uA1zI/edit?tab=t.an862luxdldo

#aiexperimentlog #3pinterest #highsuccess

Decided to try something a bit different and go back to square one. Researched tips for better prompt generation and ideation methodology. I asked Chat-GPT to help with "six hats" method ideation regarding the Pinterest Problem. I was impressed ! Definitely sticking with this method for prompting...

https://docs.google.com/document/d/1UIt4yc2j2ivxYxK-ODLcGneAr1KbNq7TbIC7T3uA1zI/edit?tab=t.y9sot7f0vxim

#aiexperimentlog #3pinterest #highsuccess