Notes on science, research, and AI.
Short essays for biopharma scientists. Written by the founding team.
I Used Claude Science for a Formulation Study. Here's What Happened.
A real use case. A real formulation problem. An honest account of what a bench scientist experienced.
What Is Claude Science? A Bench Scientist Breaks It Down
Anthropic just launched Claude Science and the scientific community is buzzing. Here is what it actually is, what it actually does, and what a bench scientist noticed when she tried it.
The Reproducibility Crisis: How Better Experiment Design Fixes It
Most failed replications trace back to decisions made before a single sample was run. Here is how rigorous up-front experiment design turns the reproducibility crisis into a solvable workflow problem.
Choosing the Right Experimental Controls: A Practical Guide
Controls are what separate a result you can defend from a number you have to apologize for. Here is how to choose the right ones for every assay.
Sample Size and Statistical Power: A Bench Scientist's Guide
How to calculate sample size and statistical power before you run an experiment, so you stop wasting reagents on studies that were never built to detect the effect you care about.
Design of Experiments (DOE): A Practical Guide for Life-Science Labs
Design of Experiments lets you optimize assays and formulations in fewer runs than the one-factor-at-a-time habit ever could. Here is a working scientist's guide to factors, designs, and a worked example you can take to the bench.
From Question to Experiment in Minutes: Rethinking Research Workflows with AI
The time between "I have a question" and "I have a protocol I can run tomorrow" is the most underestimated number in research. AI is about to change it dramatically.
Why We Built Shadow AI: A Scientist's Story
I spent a decade in biopharma labs. The problem wasn't the science. It was everything around the science. Here's the story of how that frustration became Shadow AI.
Using AI in the Lab: A Practical Guide for Bench Scientists
Not every lab task benefits from AI, and some tasks benefit enormously. A practical breakdown of where AI is worth adopting, where it isn't, and how to start without disrupting your team.
How AI Is Reshaping the Scientific Method
The scientific method isn't disappearing. Every step - hypothesis, design, execution, analysis, communication - is being reshaped by AI. Here's what's actually changing and what stays the same.
Why Experiment Design Is the Silent Bottleneck in Biopharma Research
Most experiments don't fail at the bench - they fail on the whiteboard. A look at why experiment design is the most under-invested step in biopharma research, and what happens when we finally give it the tools it deserves.