by admin | Nov 18, 2026 | Research & Productivity
Imagine handing a computer a single strand of DNA and asking it two different questions: “What happens inside a heart cell?” and “What happens inside a brain cell?” and getting two different, useful answers. That is roughly what Google DeepMind just built, and it is called AlphaGenome 2.
If you have ever wondered how AI is quietly changing medical research, this is a good example to understand. You do not need a biology degree to follow it. You just need to know what problem it solves and why that problem matters.
What Is AlphaGenome 2?
AlphaGenome 2 is a new AI model from Google DeepMind, announced on November 11, 2026. Its job is to predict how a piece of DNA, or a change in that DNA (called a variant), affects a specific type of human cell.
That last part, “a specific type of cell,” is the key upgrade. DNA is the same in almost every cell of your body, but cells read it differently. A skin cell and a liver cell share the same genetic instructions, yet they behave in completely different ways because they switch different parts of those instructions on and off.
The original AlphaGenome, released in 2025, tried to predict effects across many tissues at once from a long DNA sequence. DeepMind found this spread the model’s attention too thin, making it harder to tell closely related cell types apart. AlphaGenome 2 fixes that by taking the DNA sequence and a specific condition (a tissue, a cell type, or a cell state) together, then predicting what happens in that one condition. Scientists can even point it at their own single-cell lab data instead of a preset list.
What Can It Actually Predict?
According to DeepMind, AlphaGenome 2 was trained on more than 100 million individual cell profiles across 68 tissues, combining human and mouse data. With that training, it predicts:
- Gene expression (whether a gene is switched on or off, and how strongly)
- Chromatin accessibility (how “open” or “closed” a stretch of DNA is for reading)
- Histone modifications (chemical tags that influence gene activity)
- DNA methylation, a newly added readout that researchers had been asking for
On a public dataset covering 28 types of immune cells, AlphaGenome 2 correctly identified the DNA variant actually causing a measured effect about 30% of the time, compared to 16% for the previous best approach. That is nearly double.
Why This Is More Than a Lab Curiosity
DeepMind shared two real examples that make this easier to picture.
In inflammatory bowel disease, the model reproduced a known finding where a distant stretch of DNA overactivates a gene called ETS2 in gut immune cells, and it correctly flagged which exact variant was responsible.
In COVID-19 research, using single-cell data the model had never seen before, it told apart “activated” and “resting” T cells (a type of immune cell), and showed that a variant linked to severe COVID-19 disrupts gene activity more strongly once those cells are activated. That kind of detail matters because a drug or treatment that works in one cell state might do nothing, or even cause harm, in another.
Important: AlphaGenome 2 is a research tool, not a diagnostic one. DeepMind is explicit that it has not been validated for clinical or diagnostic use. It is meant to help scientists form better hypotheses and prioritize experiments, not to replace a doctor or a lab test.
From my own experience working with websites, online tools, and digital projects, I have seen how much trust depends on understanding why a system made a decision, not just what it decided. That is exactly the gap models like this try to close in medicine: fewer black-box guesses, more traceable reasoning that a researcher can actually check against known biology. It is the same reason tools like explainable AI are becoming such a big deal across healthcare AI generally, not just genomics.
How Can Researchers Use It?
AlphaGenome 2 is available now, for free, for non-commercial research through DeepMind’s AlphaGenome API, with ready-made Colab tutorials so scientists do not have to start from scratch. Commercial research access is in private preview through Google Cloud. DeepMind is also inviting researchers to submit real use cases by November 30, 2026, with a shot at extra compute credits. You can read more background on the original model in DeepMind’s first AlphaGenome announcement.
This fits a pattern we have covered before on BrightMindAI: major AI labs opening up serious research tools for free or low cost, the same spirit behind Anthropic’s guest investigator program for life sciences researchers and the broader trend of AI helping scientists discover new drugs faster. If you want the bigger picture on how AI reads health-related data in general, our guide on how AI reads medical scans is a good next read.
Common Questions
Is AlphaGenome 2 the same as a genetic test?
No. It is a research model used by scientists to study DNA and disease. It does not diagnose conditions in individual patients.
Does it replace doctors or genetic counselors?
No. DeepMind says clearly that it is for research, not clinical decisions.
Can anyone use it, or only big labs?
Non-commercial researchers can access it now through the AlphaGenome API, free of charge. You do need some background in biology or bioinformatics to use it meaningfully.
Why does “cell-specific” prediction matter so much?
Because the same DNA change can be harmless in one cell type and harmful in another. A model that ignores that difference misses a lot of real biology, which is exactly what the original AlphaGenome struggled with.
Final Takeaway
AlphaGenome 2 will not change your day-to-day life tomorrow. But it is a solid example of where useful AI progress is actually happening in 2026: not just bigger chatbots, but tools that help scientists ask sharper questions about disease, cell by cell. If you follow how AI is being used in medicine and research, this is one worth bookmarking, and it is a good reminder that some of the most meaningful AI work right now is happening quietly, far from the headlines about chatbots.
by admin | Nov 5, 2026 | Research & Productivity
If you’ve ever tried to use ChatGPT for a literature review, you’ve probably run into the same problem every researcher does. It sounds confident even when it’s wrong, and tracking down whether a citation is actually real can take almost as long as just reading the paper yourself.
That trust gap is exactly what Elsevier, the publisher behind journals like The Lancet and Cell, built its AI tool LeapSpace to close. It has been rolling out through 2026, and by September it had grown into something genuinely different from the general purpose chatbots most people reach for when they are trying to find or understand academic research.
What LeapSpace Actually Does
LeapSpace is not trying to be a chatbot for everything. It is built specifically for research tasks: finding relevant papers, summarizing findings, spotting contradictions between studies, and pulling together a literature review you could actually show your advisor. Ask it a question and it shows the steps it took to reach the answer, not just the answer itself, so you can check its work instead of taking it on faith.
Every claim it makes links back to a traceable source. Elsevier calls these “Trust Cards,” short explanations of why a particular source was cited and whether it contradicts something else in the results. That single feature addresses the thing that makes most researchers wary of AI tools in the first place: you usually cannot tell when they have made something up.
Built On Published Research, Not the Open Web
Where general chatbots pull from whatever is on the open web, LeapSpace is built on Elsevier’s own library plus licensing deals with other publishers. As of September 2026 it draws on more than 23 million full peer reviewed articles and books, on top of 2.6 billion cited references from Scopus covering work from over 7,000 publishers. Elsevier has also signed licensing agreements with BMJ Group, JAMA Network, Emerald Publishing, Sage, and IOP Publishing, among others, so the tool is not limited to Elsevier’s own journals.
That matters more than it sounds. Elsevier’s own research found that only 22% of researchers trust existing AI tools, mostly because general models are trained on a mix of sources with no clear way to tell what is reliable. Full text access instead of just abstracts means LeapSpace can actually read a paper’s methodology section, not just guess at it from a summary.
Who Can Use It, and What It Costs
Institutions and companies can already buy LeapSpace, and individual plans for academics and students became available earlier in 2026, including a free access tier. If you are a student working through a literature review or a researcher trying to clear a backlog of papers, it is worth checking whether your university library already has it. A lot of institutional subscriptions quietly include tools like this without anyone announcing it loudly.
Quick tip: before you adopt any new research tool, ask whether it shows its sources clearly enough that you could defend a citation in front of your advisor. If it cannot, you are still doing the fact checking work yourself, just with extra steps.
Why This Fits a Bigger Pattern
From my own experience working with online tools and research adjacent projects, the tools that stick around tend to be the ones that make their limits visible instead of hiding them. An independent five person advisory board, including researchers from RWTH Aachen and the University of Wisconsin-Madison, now reviews how LeapSpace ranks sources and flags bias, which is a step most AI tools skip entirely.
If you are already using other AI research tools, LeapSpace is worth comparing on exactly this point: not how fluent the answers sound, but how easy it is to verify the ones that matter. Our guide on how to fact-check AI research answers walks through a simple process for that, and if you are weighing LeapSpace against something built more for speed than rigor, our Elicit vs Gemini Notebook comparison covers that tradeoff. If you want the bigger picture on using AI for coursework or your own research, our guide to AI for research and productivity is a good starting point, and our piece on Google Scholar Labs covers a free alternative worth knowing about too.
Common Questions
Is LeapSpace free?
Individual academics and students get access to a free tier, though fuller paid plans unlock more. Institutions and companies pay for broader access.
Does LeapSpace replace Google Scholar?
Not really. Google Scholar is a search engine for finding papers. LeapSpace is built to read, summarize, and cross-check papers once you have found them. Many researchers will likely end up using both.
Can I actually trust what LeapSpace tells me?
More than a general purpose chatbot, since every answer links to a specific source and flags contradictions. But “more trustworthy” is not the same as “always right,” so checking the underlying paper is still worth the extra minute.
Final Takeaway
AI research tools are multiplying fast, and most of them are optimized to sound helpful rather than to be checkable. LeapSpace is a useful reminder that the second one matters more. If you do any kind of literature review work, even occasionally, it is worth five minutes to see whether your institution already has access.
by admin | Oct 29, 2026 | Research & Productivity
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.
by admin | Oct 23, 2026 | Research & Productivity
Picture a small research group studying a rare disease. They have a promising idea, but not the budget for a big AI lab’s compute, and not the time to become machine learning experts just to test one hypothesis. That gap, between a good research question and the resources to chase it, is exactly what Anthropic’s newest program is trying to close.
On October 22, 2026, Anthropic opened applications for a Guest Investigator Program aimed squarely at life sciences researchers. It is a small, practical idea: pair outside scientists directly with Anthropic’s own research team for a few months, give them free use of Claude, and publish whatever comes out of it together. If you follow AI in research at all, this one is worth knowing about.
What the Guest Investigator Program Actually Offers
According to Anthropic’s own announcement, this goes further than a simple API discount. Selected research groups work directly with Anthropic researchers on a problem the group chooses, and Anthropic runs its models and research harnesses for the project at no cost. The company says it will publish the outputs jointly with each group and open source the data and code that come out of it.
- Who can apply: principal investigators and their research groups at academic institutions, nonprofits, or government labs.
- What counts as eligible research: causal human biology, structural and computational molecular biology, medicinal chemistry, drug discovery, and clinical science.
- How long it lasts: collaborations run 8 to 12 weeks, with some extended if the work is going well.
- Timeline: applications stay open for about 14 days after the announcement, and selected groups hear back roughly 14 days after applications close.
One detail stands out if you have ever been wary of handing research data to a big AI company: Anthropic says it does not ask for data, either in the application or during the collaboration, and applications should only contain publicly available information. Investigators keep the rights to their data the whole way through, plus the rights to any follow-on research that comes later.
Why This Is Different From a Normal Research Grant
Most research funding gives you money and leaves the rest up to you. This program gives you something harder to buy: time with the people who actually built the model you are trying to use well. That matters more than it sounds. A lot of scientists know roughly what they want an AI tool to do, but not the fastest way to get there, which prompts work, which parts of a workflow should stay manual, where a model is likely to be wrong. Working alongside the team that built the tool shortens that learning curve considerably.
This also builds on two things Anthropic already had running. Its AI for Science program, launched back in 2025, gives qualifying researchers free API credits for high-impact projects, decided case by case based on scientific merit and how much AI could genuinely speed the work up. There is also a separate Life Sciences Verification Program that gives vetted scientists direct access to Anthropic’s most capable publicly available models for biology work. The Guest Investigator Program sits a level above both of those: instead of credits or model access alone, you get a defined, hands-on collaboration with a deadline and a shared publication at the end.
Why AI Labs Are Courting Scientists Right Now
This is part of a bigger pattern. OpenAI has its own Rosalind academic plan giving university labs free seats and gated access to a life-sciences focused model, which we covered in our guide to the Rosalind academic plan. Anthropic has separately been investing heavily in trust and safety work through programs like independent model evaluation, which we explained in our piece on who actually checks whether AI models are safe. Put together, the race among big labs has shifted. Building bigger models used to be the whole story. Now proving those models are useful, and safe enough to trust, for research that actually changes people’s lives matters just as much.
From my own experience helping people set up websites and online tools, I have noticed the same shift happening one level down, outside of elite research labs. Everyday small business owners and students are being handed free or cheap access to tools that used to require a specialist. The scale is different for a cancer researcher versus someone automating their invoicing, but the underlying idea is the same: AI companies have realized that giving real experts hands-on access, instead of just a generic chat window, is where the genuinely useful results come from.
Important tip: if you or someone you know runs a research group and this sounds relevant, read the eligibility list closely before applying. Anthropic is specific about the five research areas it wants (causal human biology, molecular biology, medicinal chemistry, drug discovery, and clinical science), and a strong application explains clearly how direct access to Anthropic’s researchers, beyond the model itself, would change what the project could achieve in 8 to 12 weeks.
What This Could Mean for Medical and Health Research
A program like this is especially interesting for anyone following AI in medicine, where the hardest problem usually is not “can the model get the right answer,” it is “can a doctor or researcher trust why it got that answer.” Explainability matters enormously in clinical science and drug discovery, where a wrong or unexplained result can waste months of lab work. Getting direct time with the people building these systems, rather than treating the model as a black box, is a meaningfully different way to close that trust gap than simply publishing a bigger benchmark score.
Common Questions
Do I need to already be famous in my field to apply? No. Anthropic says it is looking at the potential impact of the proposed project and how much AI could realistically accelerate it, rather than a researcher’s existing reputation alone.
Will Anthropic own my data or results? No. The announcement states that guest investigators keep the rights to their data throughout the project and to any independent follow-on research, and Anthropic does not request data as part of the application.
Is this the same as the Rosalind academic plan or the Life Sciences Verification Program? No, those are separate initiatives from OpenAI and Anthropic respectively that mainly provide model access or credits. This program adds direct, hands-on collaboration with Anthropic’s own researchers for a fixed period.
Final Takeaway
Free AI credits are nice, but a few months of direct help from the people who built the tool is a different kind of offer, and it is a sign of how seriously the big AI labs now take real scientific research, well beyond chatbots and coding assistants. If you are in life sciences research and have a question that keeps stalling for lack of the right tools, this is a short window worth looking into before it closes.
by admin | Oct 16, 2026 | Research & Productivity
If you have ever watched a university lab wait weeks for a bigger cloud-computing budget just to run one more experiment, you already know the real bottleneck in science is rarely a shortage of ideas. It is access. On October 15, 2026, OpenAI tried to chip away at that problem for a specific group of researchers with a new program called the Rosalind Academic Plan.
If you work in a lab, teach at a university, or just follow how AI is changing research, here is what the plan actually offers, who qualifies, and why it is worth paying attention to even if you will never apply for it yourself.
What Is the Rosalind Academic Plan?
The Rosalind Academic Plan is a new OpenAI program that gives eligible U.S. university labs free access to its commercial AI models, paired with GPT-Rosalind, OpenAI’s specialized model for life sciences, plus a workspace called Rosalind Workbench. Until now, GPT-Rosalind access had mostly gone to large companies and select government partners, so opening a path for academic labs is a genuine shift.
Each approved lab can activate up to 30 named seats at no charge, for up to 12 months, with usage limits attached. The offer covers subscription-style seats only. It does not include API access, so labs cannot wire the models directly into their own custom research software.
What Is GPT-Rosalind, and Why Isn’t It Automatic?
GPT-Rosalind launched back in April 2026 as the first model in a new OpenAI series built for scientific work. It is named after Rosalind Franklin, whose X-ray images were central to discovering the structure of DNA. OpenAI designed it to reason about molecules, proteins, genes, pathways, and disease biology, and to handle multi-step research tasks like literature review, experiment planning, and data analysis using scientific tools and databases. Early partners applying it to real workflows reportedly include Amgen, Moderna, the Allen Institute, and Thermo Fisher Scientific.
Here is the part that trips people up: getting a seat under the Rosalind Academic Plan does not automatically unlock GPT-Rosalind itself. That model needs a separate trusted-access review, on top of the lab’s approval for the plan. OpenAI is clearly treating a biology-tuned reasoning model as higher-stakes than a general chatbot, which tracks with how cautious the field has been about models that touch drug discovery and pathogen-adjacent research.
Who Can Actually Apply
Eligibility is reviewed at the lab level, not the individual level. OpenAI looks at:
- The lab lead’s identity, university appointment, and authority to oversee access
- The lab’s university affiliation and current research activities
- The intended use of the models and data
Labs at universities that already have an OpenAI Enterprise agreement apply through their institution. Labs at universities without one go through OpenAI’s own trusted-access route instead. OpenAI also states that research data shared through the plan is not used to train its models by default, which matters a lot if your work involves anything sensitive or unpublished.
Tip: before you plug any real experimental or patient-derived data into a new research AI tool, read the data-use and training policy yourself rather than trusting a headline summary of it. Policies like this get updated, and “not used to train by default” can still mean something different from “never touches our servers.”
The Bigger Pattern Behind the Headline
From my own experience working around websites, online tools, and digital projects, I have noticed that AI research access is splitting into two very different tracks right now. Broad discovery tools are opening up fast and wide, the way Google Scholar Labs expanded its AI research features to more users this year. But specialized, higher-stakes models like GPT-Rosalind are moving the opposite direction: more gated, more reviewed, more careful about who gets in.
That split makes sense once you think about what is at stake. A general research assistant that helps you summarize papers is a very different risk profile from a model fine-tuned to reason about disease pathways and drug design. If you are comparing everyday research tools rather than specialist lab software, our recent look at Elicit vs Gemini Notebook is a useful next read.
It is also a reminder that whatever AI tool you are using for research, the output still needs your judgment on top. That applies just as much to a specialized biology model as it does to a general chatbot summarizing a journal article. We covered the practical side of that in how to fact-check AI research answers before you cite them, and it is worth revisiting before any serious project, academic or otherwise.
What This Means for You
If you are not affiliated with a U.S. university lab, this specific program will not reach you directly. But it is still a useful signal: AI companies are increasingly willing to subsidize serious research use cases while keeping tighter control over who touches their most specialized models. If you are a student or early-career researcher, it is worth asking your supervisor or department whether your institution already has an OpenAI Enterprise agreement, since that changes which door you knock on.
Common Questions
Is the Rosalind Academic Plan free forever?
No. Approved labs get up to 30 seats free for up to 12 months, with usage limits. OpenAI has not said what happens after that period.
Does my university need an existing deal with OpenAI first?
Not necessarily. Universities with an OpenAI Enterprise agreement apply through their institution. Universities without one can apply through OpenAI’s separate trusted-access route.
Can an approved lab use GPT-Rosalind right away?
No. A seat under the plan covers OpenAI’s general commercial models. GPT-Rosalind itself needs an additional, separate trusted-access review.
Does the plan include API access for custom tools?
No. It covers subscription seats only, not API access, so labs cannot connect the models directly into their own research software through this plan.
Final Takeaway
The Rosalind Academic Plan is a narrow program on paper, limited to U.S. university labs, capped seats, and a one-year clock. But it says something broader about where AI in research is heading: more free access for people doing real scientific work, and more scrutiny over who gets the most powerful, specialized tools. Whether you are in a biology lab or just reading a paper with an AI assistant open in another tab, the same habit still applies: use the tool, then check its work yourself.
by admin | Oct 15, 2026 | Research & Productivity
You open twelve browser tabs, a stack of PDFs, and a half-finished spreadsheet, and you still cannot answer a simple question: what does the research actually say? If that sounds familiar, you have probably already tried an AI research tool to speed things up. Two of the most talked-about options right now are Elicit and Gemini Notebook, the tool most people still know by its old name, NotebookLM.
Both tools use AI to help you work through research faster, but they are built for different jobs. Picking the wrong one wastes time you were trying to save. Here is a plain-English look at what each one actually does, where it falls short, and which one fits your situation.
What Elicit Is Really Good At
Elicit is built for people doing serious literature work: students writing a thesis, researchers running a systematic review, or anyone who needs to find and summarize academic papers quickly. It searches across more than 138 million papers and over 500,000 clinical trials using semantic search, so you do not need to guess the exact keywords a paper might use.
- A Research Agent that gathers evidence from journals, clinical trials, and your own uploaded documents, then builds cited reports, tables, and even slides
- Systematic review support that automates screening and data extraction, with Elicit’s own figures suggesting researchers can save a large share of the time that step normally takes
- A Library to store and reuse sources across projects, plus Routines that keep you updated when new relevant research is published
- Sentence-level citations on AI-generated claims, so you can trace every summary back to its source
Elicit has a free Basic plan for casual searching and reading, with paid tiers that unlock exports, larger systematic reviews, and API access for heavier workloads. If your work involves citing sources properly, our guide on how to fact-check AI research answers before you cite them is worth reading alongside any tool you choose, Elicit included.
What Gemini Notebook (Formerly NotebookLM) Does Differently
Google renamed NotebookLM to Gemini Notebook in July 2026, though plenty of people still search for it by the old name, so we will use both here. The core idea has not changed: you upload your own sources, PDFs, notes, slides, websites, and Gemini Notebook answers questions strictly grounded in what you gave it, with citations pointing back to the exact passage.
- Source-grounded chat that will not wander off into made-up answers outside your uploaded material
- Audio and video overviews that turn your notes into a spoken discussion or a short explainer video
- Mind maps, flashcards, quizzes, and slide decks generated automatically from your sources
- A secure code execution environment per notebook, useful for data analysis grounded in the files you uploaded
- Syncing between the Gemini app and the standalone Gemini Notebook experience
Where Elicit goes out and searches the wider body of academic literature for you, Gemini Notebook stays inside the walls of whatever you feed it. That difference decides which tool actually helps you.
Quick tip: if you are not sure which job you are doing, ask yourself this: am I trying to find research I have not read yet (use Elicit), or am I trying to understand and organize research I already have (use Gemini Notebook)? That one question settles most of the confusion.
Elicit vs Gemini Notebook: Practical Scenarios
- Writing a literature review from scratch and need to discover relevant papers: Elicit
- You already have a folder of PDFs, lecture slides, or meeting notes and want a study companion: Gemini Notebook
- Running a formal systematic review that needs PRISMA-style screening: Elicit
- Turning dense research into an audio summary you can listen to on a commute: Gemini Notebook
- Extracting data into a table across dozens of papers: Elicit
- Building a quiz or mind map from your own course material to revise for exams: Gemini Notebook
From my own experience working with online tools and digital projects, the tools that save real time are the ones matched to the job in front of you, not the ones with the longest feature list. Match the tool to the task first, then worry about which one looks nicer.
Which One Should You Actually Pick?
If you are starting a research project and do not yet know what has already been published, start with Elicit. It will surface papers you would never have found by scrolling through Google Scholar manually, and the citation trail keeps your work honest. For deeper background on how these grounded-answer systems work under the hood, see our explainer on what RAG in AI actually means, since both tools lean on similar retrieval techniques.
If you already have the material, your own PDFs, lecture notes, or a pile of saved articles, and you want to understand, organize, and revise it faster, Gemini Notebook is the better fit. Our guide on how to chat with a PDF using AI covers a similar workflow if you want more free and low-cost options in the same space.
Plenty of students and researchers end up using both: Elicit to find and screen the literature, then Gemini Notebook to turn the papers they have collected into something they can actually study from. If you want a wider view of how AI fits into a research workflow beyond these two tools, our piece on how AI can help with research and productivity is a good next read.
Common Questions
Is Elicit free to use? Yes, Elicit has a free Basic plan with unlimited search across its paper database and limited use of its Research Agent and Reports features. Paid plans add exports, larger systematic reviews, and higher usage limits.
Did NotebookLM really change its name? Yes. Google announced the rename to Gemini Notebook in July 2026. It is the same underlying product, now more tightly connected to the Gemini app and Google Search.
Can I trust the citations these tools give me? Both tools link claims back to source text, which is a good starting point, but you should still open the original source before citing it in your own work. Our guide on fact-checking AI research answers walks through exactly how to do that.
Final Takeaway
Elicit and Gemini Notebook are not really competitors, they solve two different problems. Elicit helps you find research you have not seen yet. Gemini Notebook helps you make sense of research you already have. Figure out which problem you are facing today, pick the matching tool, and you will get more done in the next hour than an afternoon of random tab-switching ever managed.