Nikhil David
I build research tools that show their evidence, so you can check the answer against the source yourself.
Who I am
I have experience on both sides of this problem. As a psychology student and research intern I did the work ORA is built for, reading sources, checking claims against them, and writing from evidence.
As an AI content analyst I judged AI output for accuracy, reasoning and safety, and saw how often it's confidently wrong in ways that are easy to miss.
ORA is the tool I wanted in both jobs. A tool that shows you its evidence, sentence by sentence, so you don't have to take the answer on trust.
Good looking software isn't the whole story
Anyone can make software that looks like it works. Making it work well enough to be trusted, and actually used, is the harder and more important part.
That's where my background fits. Between AI analysis and psychology research, I know how to design evaluations and studies that show whether a system really does what it claims, and where it falls short. That testing is what turns a good-looking demo into something you can actually rely on.
What I can build for you
ORA is a working example of what I can build. Give me a hard information problem and I'll make something verifiable, that runs where your data lives, and fits how your team actually works.
If your team reviews evidence for systematic reviews, evidence synthesis, HTA submissions, regulatory work, or compliance, we can define one bounded workflow and adapt ORA to its sources, review criteria, and outputs.