Minimal line drawing of a person standing on top of oversized sheets of paper with scientific drawings on them

Chats for scientists

Medical researchers at top U.S. institutions shared chats they use in their research and day-to-day practice. Tap a chat to get started.

Create content for a clinical research study

I’m generating a word list recall for a memory test. Create a list of 10 words in American English at a sixth-grade reading level, each with a moderate level of word frequency.

Brainstorm next-generation treatments

You are a world‐leading expert in HIV, immunology, and therapeutic development. Your goal is to map out 10 clear paths that, if pursued rigorously, could finally solve the HIV cure/vaccine challenge. Develop and describe 10 distinct, high‐impact approaches—ranging from novel immunogens and delivery platforms to cell- and gene-based therapies—that could realistically lead to either a functional cure or an effective vaccine. For each approach, include: • A concise name or concept title • Underlying biological rationale • Key technological or methodological innovation • Anticipated mechanism of action • Major technical or safety challenges and how to address them • A rough timeline or next‐step experiment to validate feasibility Be bold, interdisciplinary, and specific.

Get up to speed quickly on a condition

Tell me everything you know about retinitis pigmentosa.

Analyze a large dataset

I am looking for genes that may cause urogenital disorders. I need help studying a large proteomic dataset on patient urine. Based on the attached file, do any of these cases have urine proteomic values that seem unique or drastically different from the others? If so, what is different about them?

Identify potential drug candidates

I used machine learning to identify ~50 potential treatments for POEMS syndrome. Will you assess and validate these treatments? For each treatment, let me know the biological rationale for why it may work and why it may not. Then re-rank them based on existing evidence.

Generate personalized pictures for test stimuli

Create an image for a cognitive assessment that is culturally appropriate and clear for people to describe based on the following guidance: A clean, horizontal digital artwork of an indoor community space in soft, semi-stylized illustration style (not realistic). The scene includes exactly 12 unique content units: 4 people, each performing a completely different activity (e.g., reading, painting, stretching, watering a plant) and 8 distinct inanimate objects (e.g., potted plant, wall art, rug, bookshelf, window, chair, table with supplies, floor lamp). Each person and object must be fully visible and clearly different — no repetitions in action, object, or appearance. Distribute the content evenly across the image with exactly 3 content points in each quadrant (upper left, upper right, lower left, lower right). Use soft colors, clear separation between elements, and a warm, family-friendly tone. The image should be free of text and easy to interpret visually, especially on a mobile screen.

Translate your research into layman’s language

Read this paper very carefully, reason about it, then write a report in layman’s language that captures all the important points and why this research is significant or impactful to the field. Explain what this means for therapeutics and diagnosis for ME/CFS.

Create a reading list

Make a list of the top literature from 2024 on AI and healthcare. “Top” can mean anything from an exciting topic to an extremely useful method to a dataset that enables new and important research. With the list, please include the reason the paper was chosen.

Make connections across scientific literature

You are a domain-expert researcher. I’m attaching several academic papers — each presenting distinct theories, datasets, or methodologies. Please: • Summarize each paper’s key findings in one or two sentences. • Identify and explain at least three non-obvious connections or thematic overlaps across the papers. • Propose at least three novel hypotheses or research ideas that emerge only when these works are considered together. For each proposed idea, outline: • a concise title • why it follows logically from the combined literature • one possible experimental or computational approach to test it Present your answer in a structured report with clearly labeled sections (Summary, Connections, New Ideas, Next Steps)