Protocol
Why this stops working in week one
Upload a .czi and ask about your image. Upload a .raw and ask about your peaks. Nothing happens, because no model can read a vendor binary — and most people conclude the tool is useless for real work and stop there. It is not the tool. It is that nobody told you the model is the author of the converter, not the reader of the file.No study needed for this one. It is how the formats work.
Run your controls.
Protocol puts AI on the bench work — instrument exports, QC, statistics you can defend, figures, methods and reviewer letters — with one hard rule: it never reports a number it cannot trace, and never calls a reference verified without checking it. Anything unconfirmed comes back UNVERIFIED. It drafts and checks. You conclude.
Built for
Academic lab, core facility or industry bench. If you generate your own data and have to defend what you did with it, this is that bench. Not clinical or diagnostic work — that is a different liability surface and this door stays out of it.
What is the analysis you can do but could not defend to a reviewer?
Say it in your own words. I'll do it on your data right now, and show you the control behind it.
2 runs on the house, no signup. A free account gets you 10.
How scientists put AI to work here
Your exports, QC, figures, and methods
The analysis in front of you, from the raw instrument file through the figure, drafted from what you paste.
It cannot open your file. It writes what can
A .czi, a BAM, a Bruker FID: no model reads these. It writes the converter and tells you what survived.
Traceable, never asserted
Every number ties back to the data you gave it. Every reference it has not checked is marked UNVERIFIED.
The control named, every time
It says what check would catch the result if it were wrong. An analysis without one is not finished.
88 lessons, every bench
Instrument files to figures to manuscripts. The whole bench, raw instrument file through published figure, across 15 areas.
Try it free
Two runs on the house, no signup. A free account gets you 10. Just your email.
A general chatbot
“Studies have shown this effect is well established (Chen et al., 2019).”
Chen et al. 2019 may not exist. The sentence is fluent, sourced-looking, and the first person to check it will be a reviewer.
Protocol
“[UNVERIFIED] Chen et al. 2019 — I have not confirmed this resolves. Check it before you cite it. Your own data support the weaker claim; here is that sentence instead.”
Unverified means unchecked. Not wrong, and not safe. That distinction is the door.
What is live, and what is not
Live now: the universal library counted above — grounding, verification, workflows, and Claude itself. Those lessons are written and you can use them today.
Not yet: the fifteen benches below, which are the bench-specific layer — the instrument work, the QC, the statistics, the figures. Seven of the fifteen are the data track. None of them is published. They are being authored now with an instrument-level review on every data lesson, and this line changes the day that stops being true.
Start with your own file
Bring the export you cannot get numbers out of. $39 a month for one scientist. Labs run on seats — students and postdocs included, because the people who most need this are the ones least able to buy it themselves.