What we learn running lab science with agents: protocols, plate data, agent design, and how we work. Founder essays live at Building Elnora; company announcements at News.
This is how to evaluate AI in drug discovery: by whether it changes which compounds a lab makes and tests, and whether those choices hold up in the lab's own assays. Elnora records each prediction before the round and scores it after.
A biotech can run multiple drug programs with a small team when an AI agent does the lab work for each one. Keep the programs in one shared record and Elnora plans each from what the others measured.
AI improves drug design first, toxicity prediction next and clinical efficacy last, so choosing which designed molecules to develop becomes the scarce skill. Elnora plans the screen to rank compounds by cytotoxicity and potency and keeps the results for the next round.
To set up an AI agent for your lab, start with your own scientists, who already decide which evidence counts and what cut-off makes a signal real. Elnora keeps those rules in the team's conventions and applies them to each analysis.
The largest gain AI offers science is an institute that keeps its failed runs and the reasons for its decisions, sees which projects depend on one result, and acts on it. Elnora traces what a finding rests on, each claim tied to its source.
This is how to optimize a lab protocol with AI: test a spread of conditions, fit a model to the readout and let it choose the next round. Elnora plans each round and writes the run, and a scientist approves it.
An AI agent raises a scientific model's score, mostly through routine engineering, and it inflates a score it holds itself. Keep the test data with a scientist, read the agent's record and give it a research routine.
AI narrows a panel of designed antibody candidates when it scores binding alongside expression and stability. The lab's own measurements, kept with the runs and protocols that produced them, are what make that ranking worth acting on.
AI for biotech lab documentation should make a lab learn each method once. How Elnora keeps the rules and methods one scientist works out, so a colleague's next analysis starts from them.
Computational design searches an enormous set of possible molecules and returns the few worth making. An assay development AI assistant plans the experiment that settles them, because prediction is strong on chemistry and ordinary on the disease biology.
An AI model proposes ideas from a published record skewed towards success. An AI agent for drug discovery lab work earns its place on the validation experiment: designed well, run at the bench and kept, negatives included.
AI does speed up scientific research, by close to seven hours a week on scientists' own count, so the slow step moves to the bench experiment and to checking the output, and hypotheses wait in a growing queue.
An AI assistant for wet lab scientists belongs on the searching and the drafting, and the anomaly stays with the scientist, because odd results are where the field's biggest discoveries started.
Roughly 950 AI agents searched public DNA databases for 21 hours and flagged an enzyme system in viruses that infect bacteria. The searching is what an AI agent that runs bioinformatics pipelines from public data does, and Elnora does it for a lab's questions.
World models learn how an environment behaves and predict what follows an action. A knowledge base for lab protocols and results is the version a lab already owns, and Elnora reads it, ranks explanations from it, rehearses each run and files what comes back.
An AI lab protocol generator turns a described experiment into a plate map, a materials list with resolvable catalogue numbers and a set of deck-specific instructions, while a scientist keeps deciding what the experiment should test.
Protein structure prediction, image analysis and AI-written research code are already real. A lab that wants to automate lab data analysis with an AI agent needs one that reads the files its own instruments write.
A scientist's job is a bundle of tasks that are changing at different speeds, and the labs that adopt now, while still teaching the underlying skill, are the ones that keep both the speed and the judgement.
Vendors who want a product named in a protocol have to give Elnora the same evidence a scientist would check: datasheets, application notes and the runs behind them, including the ones that failed.
How do scientists use AI agents in the lab? Increasingly to run computational biology, quality control and design of experiments work outside their formal training, as long as they still supply the judgement that decides whether the answer is right.
An answer key only covers the questions that have one. How to evaluate an AI agent for scientific work when two good scientists would disagree, by scoring provenance, negatives, and the judge itself.
Every list of the best AI tools for biology research is written from demos. The method we run on Elnora: synthetic data from a model you control, a withheld answer key, and defects you never mention.
Scientists open the CSV their machine wrote and prepare it with colour codes and tabs. Handing that to an AI tool to analyze plate reader data passes on the answer you already expected.
The loop behind every document at Elnora, a shared knowledge base, an agent that drafts from it, a review pass and the result filed back, is how Elnora works as an AI agent that drafts lab reports from your data.
