I’ve been developing something I call the Universal Research Pass.
It started as a way to stop ChatGPT from doing the usual:
question → search a few things → summarize → answer
Instead, I wanted it to behave more like an actual research process.
So the Research Pass makes the AI do things like:
The simple interface is literally:
Research Pass this: [whatever you want to understand] The user doesn’t need to know the methodology underneath it.
Here’s the part I’m interested in now:
I don’t want to keep improving this by myself.
I froze the current system as v1.0 and built a public GitHub lab around it because I want independent people to test it on questions I would never think to ask.
I specifically want people to find:
There’s also an initial 10-case benchmark, structured failure reports, improvement proposals, a testing protocol, and version history.
Use the same model in two fresh conversations. Chat A:
Ask something you genuinely want to know normally.
Chat B:
Load Research Pass v1.0 and ask:
Research Pass this: [the exact same question] Then compare them.
I’m much more interested in where Research Pass loses than people telling me it’s cool.
And please test the canonical version once before modifying it. After that, fork it, shorten it, rewrite sections, optimize it for another model, whatever you want.
If your modification is better, I want to know why, what cases it improved, and what it accidentally made worse. I’m not claiming this is some “ultimate prompt.” That’s actually what I’m trying to find out.
My current suspicion is that the interesting part isn’t the wording of the prompt at all — it’s whether a structured research protocol like this can make AI-assisted research more reliable across completely different people, models, and subjects.
So genuinely:
break it.