The next step.

Use AI to understand a complex paper — then design the experiment that comes next.

Read a recent Neuron paper on placebo analgesia with AI’s help, build your own explainer, and propose a meaningful follow-up experiment.
Neuron THE NEXT EXPERIMENT

Use AI to truly understand a complex, recent paper — then do what a good scientist does next: design the experiment that should come after it.

Set challenge · runs live 35 min teams of 3-5 Any chat AI (PDF-capable) · research-capable helps

The Goal Two things: (1) build your own explainer of a recent paper — clear enough that you could teach its experiments and findings to your lab — and (2) propose one well-reasoned follow-up experiment that tests an assumption, probes a limitation, or extends the work. AI does the fast reading and drafting; you supply the scientific judgment about what matters, what’s shaky, and what’s genuinely new.

Why it matters

Papers keep getting longer and more technique-dense, and no one is fluent in every method. Being able to rapidly metabolize an unfamiliar paper — and then push past it to “so what would I do next?” — is the core engine of research: journal clubs, grant aims, rotation projects, collaborations. This is also a clean test of AI for high-stakes thinking, where a confident-but-wrong explanation of a method, or a “novel” experiment that was actually published years ago, has real costs.

The paper

You’ll work from a recent paper on the circuit basis of placebo analgesia:

Livrizzi G, Chang-Weinberg J, Johnson DA, et al. Top-down control of the descending pain modulatory system drives multimodal placebo analgesia. Neuron (2026). doi:10.1016/j.neuron.2026.03.025

Get the paper 📄 Download the paper (open-access PDF)  ·  Published version in Neuron

The download is the open-access preprint of the same study (its title omits “multimodal”); cite the published Neuron version above. Paste the PDF or its text into your AI tool to begin.

Run of show

  • 0:00–0:05 · Challenge introduction (5 min)
  • 0:05–0:20 · Work in your group (15 min)
  • 0:20–0:22 · Post your best prompt (2 min)
  • 0:22–0:32 · Share & debrief (10 min)
  • 0:32–0:35 · Reset (3 min)

The challenge

This challenge has two parts.

Part 1 — Understand it. Use AI to do a rapid analysis of the paper and create your own summary of the study and its findings — in a format that lets you explain the experiments that were done and their major findings, not just restate the abstract. Think about what would actually be useful to you or your lab: a technique glossary? An experiment-by-experiment logic map? A one-slide model figure in words?

Part 2 — Extend it. Come up with one follow-up experiment that tests an assumption or finding in their work, or extends it in a meaningful way.

As you go, push the AI past surface answers:

  • What kind of summary would be genuinely useful beyond the existing abstract?
  • What limitations and caveats can AI help you uncover that you wouldn’t otherwise notice?
  • Can AI help you check whether your proposed experiment is new — or already published by someone else?
  • Can AI help you evaluate the feasibility and logic of your proposed experiment?

Bad prompt to better prompt

Weak prompt
Summarize this paper.

Why it disappoints: you get a polished paragraph that mirrors the abstract, glosses over the techniques, never explains why each experiment was run or what it rules out, and surfaces none of the assumptions you’d need in order to design what comes next.

Strong prompt
You are a systems neuroscientist helping me prepare to present this paper to my pain-research lab. I’ve pasted the full text below. Do four things, in labeled sections: 1. TECHNIQUE GLOSSARY: list every major method used, each with a one-sentence explanation a non-specialist could follow and what it lets the authors conclude. 2. EXPERIMENT MAP: for each experiment, give Question → Design → Key result → What it establishes (and what it does NOT establish). 3. THE MODEL: state the authors’ overall claim in 3 sentences, and list the 3 assumptions it most depends on. 4. WEAK POINTS: the 3 limitations or alternative explanations the authors most underplay. Then add “CHECK ME”: flag anything you are unsure you read correctly, and any claim I should verify against a figure before I repeat it.

Follow up with: “Propose two follow-up experiments that each test one of the assumptions in section 3. For each: hypothesis, design, predicted result, the main confound, and how I’d check whether something like it has already been published.” Then verify any cited prior work yourself before trusting it.

Debrief questions

  1. What summary format did your team build — and could you now explain the paper’s key experiment without re-reading the AI’s output?
  2. Where did the AI misdescribe a technique or overstate a finding? How did you catch it?
  3. What assumption or limitation did your follow-up experiment target — and why is it the interesting one?
  4. Did AI help you check whether your experiment was novel? Did it find prior work, or just claim there wasn’t any?
  5. How feasible is your proposed experiment, really? What did the AI miss about cost, time, or confounds?

← Challenges AI Toolkit →

Back to top