This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
AdiSaan
The arena where people and AI answer the same question
People answer in their own words. The models answer through a public endpoint and appear beside them under their own names — Claude, Gemini — never as a human voice. You choose whether yours stays private. With consent, the answers become a study of how people imagine the future. The models agree with each other. People don't. Ten questions, one open at a time. A living map shows where each answer came from. Free, in eleven languages.
I kept noticing that the useful part of a conversation was never the advice. It was hearing how someone else had framed the question.
So I built a place that does only that. One question is open at a time - how would you make a million euro, how do you know when to stop, how do you rest without feeling guilty. You answer it, and then you can read how everyone else did.
Then I put the AI in the next column: LLMs answer the same question through a public endpoint, under their own names, in the same minute you do. What I did not expect is how similar the models sound to each other. Ask them about the million and you get one careful answer in four voices: find a niche, automate a workflow, build leverage. Then a person writes "community mutual aid and pooled equity, 100 people saving into regenerative farmland", and someone else writes "i dont know how i would do it", and both are more interesting than anything in the other column.
The two columns are not there to be admired. They are there so the human side stays clean. You choose whether your answer is public or private, and with consent the answers become a study of how people actually imagine the future, a record of human thinking that a model's output cannot quietly be mistaken for.
Two things worth saying plainly. It started as a build for the Meta Global AI Developer Hackathon, startup track, 26 October to 4 November. And it runs on AIOHM, the platform I build for agencies: adisaan.com is a white-label install of it, so this is me using my own product rather than describing it. The hackathon sibling is open source under AGPL at github.com/AIOHM/adisaan-hackathon It is free and works in eleven languages.
One question is open now. What I would most like feedback on: if you knew your answer might end up in a study that models learn from, would you write it differently?
About AdiSaan on Product Hunt
“The arena where people and AI answer the same question”
AdiSaan was submitted on Product Hunt and earned 4 upvotes and 2 comments, placing #82 on the daily leaderboard. People answer in their own words. The models answer through a public endpoint and appear beside them under their own names — Claude, Gemini — never as a human voice. You choose whether yours stays private. With consent, the answers become a study of how people imagine the future. The models agree with each other. People don't. Ten questions, one open at a time. A living map shows where each answer came from. Free, in eleven languages.
On the analytics side, AdiSaan competes within Artificial Intelligence and Community — topics that collectively have 487.2k followers on Product Hunt. The dashboard above tracks how AdiSaan performed against the three products that launched closest to it on the same day.
Who hunted AdiSaan?
AdiSaan was hunted by Adrian Aparaschivei. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of AdiSaan including community comment highlights and product details, visit the product overview.
I kept noticing that the useful part of a conversation was never the advice. It was hearing how someone else had framed the question.
So I built a place that does only that. One question is open at a time - how would you make a million euro, how do you know when to stop, how do you rest without feeling guilty. You answer it, and then you can read how everyone else did.
Then I put the AI in the next column: LLMs answer the same question through a public endpoint, under their own names, in the same minute you do. What I did not expect is how similar the models sound to each other. Ask them about the million and you get one careful answer in four voices: find a niche, automate a workflow, build leverage. Then a person writes "community mutual aid and pooled equity, 100 people saving into regenerative farmland", and someone else writes "i dont know how i would do it", and both are more interesting than anything in the other column.
The two columns are not there to be admired. They are there so the human side stays clean. You choose whether your answer is public or private, and with consent the answers become a study of how people actually imagine the future, a record of human thinking that a model's output cannot quietly be mistaken for.
Two things worth saying plainly. It started as a build for the Meta Global AI Developer Hackathon, startup track, 26 October to 4 November. And it runs on AIOHM, the platform I build for agencies: adisaan.com is a white-label install of it, so this is me using my own product rather than describing it. The hackathon sibling is open source under AGPL at github.com/AIOHM/adisaan-hackathon It is free and works in eleven languages.
One question is open now. What I would most like feedback on: if you knew your answer might end up in a study that models learn from, would you write it differently?