Skip to Content
Research with AIUsing AI for research

Using AI for research

Principles

  1. AI suggests; you verify — Treat every factual claim as untrusted until it matches a primary or high-quality secondary source.
  2. Ask for sources — Prefer tools that expose links (Perplexity) or your uploaded files (NotebookLM).
  3. Separate “ideas” from “facts” — Brainstorming and summarizing your own notes are lower risk than medical, legal, or financial claims.
  4. Save the trail — Bookmarks, quotes with URLs, and dates — future-you needs auditability.

Suggested workflow

StepWhat to do
1. Frame the questionOne sentence goal + audience (e.g. “Options for hosting a Next.js app for a solo dev”).
2. Broad passUse search+citation tool or manual search; collect 5–10 candidate sources.
3. Read primariesOfficial docs, standards bodies, vendor status pages — not only blog summaries.
4. SynthesizeUse AI to compress what you already read — paste excerpts, not blind trust.
5. Check conflictsIf two sources disagree, note the disagreement; don’t average into false certainty.

Prompt patterns that help

  • “List assumptions and unknowns after you answer.”
  • “Quote short excerpts I should verify; don’t invent citations.”
  • “What would change your answer if it were wrong?”

Last reviewed: April 2026.

Last updated on