Sam Fazeli

Of course, if you need to do a 12-month human study, I suspect you have to do a 12-month human study.

But more rapidly finding patients, better drug targeting in terms of identifying the patient that should go in there.

Cutting the white space between finishing phase one to going to phase two.

Talk to us about that, please.

And then see if at the end we can quantify how much time you could or couldn't save from the clinical development side and preclinical side.

Mm-hmm.

But in terms of cutting the time, the one year that it takes from going from the end of phase two to the start of phase three, do you feel there is some space for AI to help you speed that up?

Document production?

Okay.

So let me summarize again.

The time and cost saving comes in the very early parts of drug discovery.

The rest of it's some minor in terms of the development timelines.

Probability of success.

Where do we stand on that?

Do you feel that you should be able to increase the probability of success to get to successful phase three, having generated your molecules with AI and the help of AI?

I think so.

Okay.

If you were to give me a number-

Give me a number.

I mean, just for conversation, right?