Compare · Research · Research notes

AI research tools — scored

Research tools fail when you cite a summary you did not open. Score verified reading time, not chat fluency.

Last reviewed: 2026-08-15. Re-run the protocol after major model or pricing changes.

How do you test AI research tools in 15 minutes?

  1. Write a question you already know one good paper or page for.
  2. Ask two tools. Open every citation.
  3. Mark invented titles, wrong years, and missing counter-evidence.
  4. Stop when you can defend inclusion/exclusion.

What is the scoring rubric?

CriterionWeightHow to score
Cites openGateFail dead or invented sources.
Known paper found1–5Did it surface a source you already trust?
OverclaimingPass/FailFail if it treats a blog as a trial.
Time to a usable map1–5Include verification time.

Which research tool should I start with?

ToolBest fitBest jobWatch-outNote
PerplexityOpen-web mapFast linked answersNot a bibliographyOpen the links.
ElicitPaper workflowsQuestion-driven papersStill read methodsStrong for literature screening.
ResearchRabbitCitation graphsRelated-paper mapsCan miss key papersStart from 3–5 seeds you trust.
NotebookLMYour sourcesQ&A over uploadsNot open-web researchKeep it in the source-notes lane.

Learn the craft, not just the tool

Practice the transferable habit in AI for research, then Citation checker, Deep research blog.

FAQ

Is Perplexity better than ChatGPT for research?

Usually for sourced web maps. ChatGPT can draft; it is weaker as a citation engine unless you browse and verify.

Can I cite an AI summary?

Cite the primary source you opened. The summary is a map.