Ask most people how long it takes to turn a promising lab discovery into an actual medicine, and they usually guess a year or two. The real answer is closer to ten or twelve years, and most of that time isn’t spent on dramatic breakthroughs. It’s spent on paperwork, repeated lab tests, and narrowing down thousands of possible molecules to the handful worth pursuing.

That’s exactly the part of the process Anthropic just showed its Claude models chipping away at. On October 27, 2026, the company published detailed results from deep research partnerships with six drug developers, plus an early look at a drug program it’s running itself. It’s one of the clearest real-world looks yet at what “AI for science” actually means once you get past the slogan.

What Anthropic Actually Announced

The partnerships involve BigHat Biosciences, Bristol Myers Squibb, Divergence Labs, Enveda, Generate Biomedicines, and The Column Group. Anthropic is careful to frame all of this as early and mostly preclinical work, not finished cures. But the specific numbers in each case study are worth slowing down for, because they show AI being used for genuinely technical science work, not just summarizing PDFs.

Designing a Smaller, Stronger Cancer Therapy

Generate Biomedicines is trying to make CAR T-cell therapy, which has mostly worked against blood cancers, effective against solid tumors too. Six of its scientists used Claude Code to redesign a key genetic component of the therapy. One of the resulting designs was about 70% shorter than the standard version. When tested in the lab, it let immune cells produce roughly ten times as many receptors, killed tumor cells more efficiently, and stayed active in the body longer. (You can read more about how researchers are approaching solid-tumor CAR T-cell therapy at the National Institutes of Health.)

Thousands of Antibody Designs in About a Month

Divergence Labs is working on food allergy treatments that physically detach the IgE antibody from immune cells, rather than just neutralizing it in the bloodstream. Claude turned the team’s scientific goals into a design plan, then largely on its own generated roughly 35,000 antibody designs over about a month. Out of those, researchers found three strong binders and twenty designs that could successfully dislodge IgE, with three of those twenty outperforming the standard allergy medication in early tests.

Catching What Human Reviewers Missed

Not every case study is about inventing new molecules. Enveda’s manufacturing chemists were spending up to 75% of their time on compliance paperwork instead of chemistry. After connecting their documents to Claude, it reviewed 1,061 pages, caught all eleven issues human reviewers had already found, and flagged seven more that had been missed. Review time dropped from over 25 hours to under three. Claude also drafted a regulatory document in four hours that would normally take about three months by hand.

Important tip: if you work in a field with heavy documentation (regulatory filings, compliance reports, research write-ups), this Enveda example is the more realistic near-term use of AI than “AI invents a cure.” Document review and drafting is where the time savings show up first, for almost any industry.

Anthropic Is Also Building Its Own Medicine

Maybe the most human part of the announcement is Mithril Medicine, a company Anthropic acquired that started as a one-person operation. Its founder, Cody Tranbarger, was working on treatments for two rare forms of muscular dystrophy and used Claude to organize contracts, logistics, and experiments across eleven external labs. A possible treatment for one form went from an idea to promising results in mice in under eighteen months. He’s now joined Anthropic, and if the early results hold up, a drug could be ready for human trials as soon as late 2028.

From my own experience working with websites, online tools, and automation projects, this pattern feels familiar even outside medicine: the AI isn’t doing the creative or judgment-heavy part by itself. It’s clearing out the slow, repetitive overhead (the paperwork, the first-pass analysis, the thousands of variations nobody has time to check by hand) so the human expert can spend their attention where it actually matters. I’ve also seen, through research into medical imaging and AI that explains its own reasoning to doctors, how much unglamorous groundwork has to happen before a model can be trusted with something this serious. These case studies read the same way: a lot of verification sitting underneath each headline number. If you want the background on how that kind of AI reasoning gets checked, our guide on explainable AI and how AI reads medical scans cover the fundamentals.

What This Means for You

You don’t need to work in a lab for this to matter. It’s a preview of how AI is likely to show up in most serious technical fields over the next few years: not as a replacement for experts, but as a tool that handles scale (thousands of designs, thousands of pages) while people make the final calls. If you’re a student in biology, chemistry, or data science, these partnerships are a real signal of where hands-on AI skills are becoming genuinely valuable, not just nice to have on a resume. Anthropic also recently opened an Anthropic Guest Investigator Program for outside researchers in the life sciences, and our guide on how AI can help with research and productivity has more ways to apply this in your own work.

Common Questions

Is AI actually discovering new drugs on its own?
Not yet, and Anthropic doesn’t claim that. Every case study pairs Claude with human scientists who design the experiments and verify the results in the lab.

How far along are these treatments?
Mostly preclinical, meaning they’ve been tested in lab settings or animal models, not yet in human clinical trials. The furthest along, Mithril Medicine’s muscular dystrophy candidate, is targeting human trials around late 2028 if results continue to hold up.

Why does this matter outside of medicine?
The same pattern (AI handling large-scale analysis and paperwork so humans can focus on judgment calls) applies to research, engineering, and plenty of other technical fields, which is why it’s worth understanding even if you’re not in life sciences.

Final Takeaway

This isn’t a story about AI replacing scientists. It’s a story about AI removing the parts of scientific work that were never the interesting part to begin with: the repetitive testing, the paperwork, the thousands of variations nobody could check manually. If that holds up outside these six partnerships, it’s one of the more genuinely useful applications of AI we’ve seen so far, and one worth watching as these programs move from lab results toward real patients. You can read Anthropic’s full case studies directly at its research page on early progress in drug development.