How does Perplexity AI source information about companies and people?

Perplexity is the cleanest example of a retrieval-first AI engine, which is why it is often the easiest engine to influence in the short term. Each query triggers a live web search, the system ranks the returned pages using its own retrieval logic (weighted heavily toward recency, domain authority, topical relevance, and citation patterns), the model synthesizes an answer from the top-ranked pages, and the cited sources appear inline so users can verify each claim. The practical consequence: a strong new authoritative article on a topic, or a meaningfully improved Wikipedia paragraph, can shift Perplexity’s answer within days. The same intervention will take longer to show up in engines that weight their training-data baseline more heavily, but Perplexity is the early indicator that source-layer work is having an effect.