Lesson 265 of 1455
The Three-Source Rule
Smart researchers don't trust any single source. They cross-check claims across at least three independent sources before treating something as fact.
Builders · Research & Analysis · ~11 min read
Why one source is never enough
If only one source claims something, you don't know if it's a careful finding or a mistake. If three independent sources arrive at the same conclusion separately, you have real confidence.
This is called triangulation. Real journalists, scientists, and historians all use this approach.
A simple workflow
- 1Find your first source — note the specific claim
- 2Search for the same claim from a different organization
- 3Find a third — ideally from a different country or era
- 4If all three agree, you can trust the claim
- 5If they disagree, dig deeper into why
AI and the three-source rule
Asking three different AI models the same question doesn't count as three sources — they may all be trained on similar data and inherit the same errors. AI is one source. Always pair it with two human-written sources.
Key terms in this lesson
The big idea: real research isn't about finding one source — it's about finding three that all point to the same truth, independently.
End-of-lesson quiz
Check what stuck
8 questions · Score saves to your progress.
Lesson help
Questions are best handled with a grown-up here.
For this age range, Tendril keeps freeform AI chat paused until parent/guardian consent and child-safe moderation are fully verified. Use the quiz, notes, and related lessons below, or ask a parent, guardian, teacher, or librarian to work through the question with you.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Builders · 15 min
The Publication Date Check
AI gives you confident answers about facts that may have changed. The publication date of any source is the first thing to check — including AI's training cutoff.
Builders · 15 min
Asking AI for Sources (and Verifying Them)
When AI mentions a study, book, or article, your job is to verify the source actually exists — not just trust AI's summary of it.
Builders · 18 min
Spotting Fake Citations Made by AI
Fabricated citations are AI's most dangerous failure mode for research. Knowing the signs saves you from accidentally citing something that doesn't exist.