# Luma blog

Plain answers about AI, medical evidence and how to check a claim against published research.

- [How medical writers can use AI without risking fabricated references](/blog/medical-writers-ai-fabricated-references): Medical writers can use AI to draft but never as a source: verify every reference in PubMed, keep a verification log, and learn the red flags of fabrication.
- [What is claim-level verification?](/blog/what-is-claim-level-verification): Claim-level verification splits an answer into its factual claims and checks each against evidence, so one wrong claim cannot hide in a mostly right answer.
- [What is the hierarchy of evidence?](/blog/hierarchy-of-evidence): The hierarchy of evidence ranks study designs by how well they guard against bias, from systematic reviews and trials down to case reports and expert opinion.
- [What is a fabricated citation, and why do AI tools produce them?](/blog/what-is-a-fabricated-citation): A fabricated citation points to a paper that does not exist, and AI tools produce them by generating plausible text from patterns instead of looking sources up.
- [How to check if a PubMed citation is real](/blog/how-to-check-if-a-pubmed-citation-is-real): Search the PMID, title and authors on PubMed, confirm the journal, year and volume match the record, then read the abstract to see if it supports the claim.
- [Can you trust the sources in an AI medical answer?](/blog/can-you-trust-sources-in-ai-medical-answers): Not automatically: AI medical answers can cite papers that do not exist or real papers that say something else, so every source needs a check before you use it.