Medicinal chemistry runs on judgement.

Not the vague kind. The sharp, hard-earned kind that shows up as a throwaway comment in a design meeting. You know the ones: “That substitution will spike clearance.” “This looks like a P-gp magnet.” “We’re about to grow a rotatable bond tax.” Or simply, “This series is going to fall apart on solubility.”

Most software discards that signal. Blaise treats it as first-class data.

The key idea: feedback is an asset, not an annotation

In a real program, the scarce resource isn’t compute. It’s experienced attention.

Chemists see nuance instantly because they’ve internalised series-specific structure–property trade-offs, project history, and those unspoken constraints—synthesis, IP, tox, developability—that never make it into the initial prompt.

If your system can’t capture that, it will keep repeating the same mistakes with better typography.

What “first-class” means in practice

In Blaise, comments and critique aren’t sticky notes. They are structured signals that plug back into the design loop.

When you critique a molecule, that feedback links to the exact series it refers to. The system learns what a given team calls “good” or “bad” in context, and the scoring and proposal logic adapts immediately. That closes a loop most “AI for chemistry” products leave wide open.

Why this beats static scoring functions

Static property predictors are brittle. They miss project-specific constraints, over-generalise across chemical space, and ignore the fact that optimisation is implicitly multi-objective.

Chemist feedback is the missing term in that equation. Capture it, and the system stops being a demo and starts becoming a colleague.

The compounding effect

The first time you capture critique, you get a better next suggestion. The hundredth time, you’ve built something more important: a project memory.

You end up with an auditable design trail and a reusable set of “house rules” grounded in actual outcomes. This is how you make AI useful in drug discovery—not by pretending models are omniscient, but by wiring expert judgement directly into the loop.