Step-by-step
🔍 Gemini
Google
📘 Step-by-step 📘 Google · Gemini↗ Gemini · Official sitebeginner 🔄 Life & Business

How to Fact-Check a Viral News Story With Gemini Before You Share It

A simple three-step check that helps you spot misleading claims before you forward a story to family or group chats.

6 min read·September 23, 2026

This guide was written by AI. It passed automated fact and quality checks, and our editor spot-checks published guides every day.

See AI World HQ first on GoogleAdd us as a preferred source and our stories show up higher in Google’s Top Stories.Add on Google

Viral stories travel fast. By the time you see one in your family group chat, it has usually already been shared hundreds of times, sometimes with a photo, a dramatic quote, or a link that looks real but isn't. This guide walks you through a simple way to slow down, sanity-check the claim with Gemini, and decide whether it's worth passing along. You don't need to be a journalist — you just need ten quiet minutes and a willingness to ask "is this actually true?"

💡 Tip: tap a step’s number when you finish it — a green tick appears and your browser remembers how far you got.

✅ Before you start
  • A Google account (the same one you use for Gmail or YouTube).
  • Access to Gemini in a browser, or the Gemini app on your phone. Free is fine; some advanced features may sit behind a paid plan.
  • The headline, link, or screenshot of the story you want to check — copy it to your clipboard before you start.
  • About 10 minutes of focused time. Rushing is what makes viral misinformation spread in the first place.
1
Step 1 of 3

Open Gemini and paste the exact claim

Open gemini.google.com in a browser, or tap the Gemini app on your phone. You'll land on a clean chat screen with a text box at the bottom and a blinking cursor. If you've used Gemini before, your old chats sit on the left side; if it's your first time, the screen is mostly empty.

Click or tap inside the text box and paste the headline or short claim exactly as you saw it. Don't rewrite it yet — you want Gemini to react to the same words that hooked you. After you paste, you'll see your text appear inside a rounded message bubble, with a small send icon (usually a paper airplane ✈️ or an arrow) on the right side of the box.

Tap that send icon. Within a few seconds, Gemini starts typing a response. You'll see words appearing one at a time, the way a person would type. If nothing happens, look for a button labeled "Send" instead, or press Enter on a keyboard.

💬 Examplepaste this — `Headline: "Government to ban all cash payments above $200 starting next month, officials confirm." Is this a real, verified news story? Where did it originate?`
✅ You'll know it worked when

you see a written reply appear below your pasted headline, usually within 5–15 seconds.

Next step ↓
Geminigemini.google.…
✏️ Sketch — your screen may look a little different
2
Step 2 of 3

Ask Gemini to question the source and the evidence

Now you ask the follow-up that does the real fact-checking work. In the same chat box (your conversation is still open — you don't start over), type a question that pushes Gemini to look behind the claim. Plain language is fine; you don't need fancy words. Hit send the same way as before.

What you want to see is a thoughtful reply that names which outlets are reporting this, whether the claim has been confirmed by official sources, and what's missing from the original story — quotes, dates, names, places. If Gemini says it can't find any reliable source, that's actually useful information; it means the claim may have started on social media without ever being verified.

💬 Exampletype this — `Can you find at least three reputable news outlets (not random blogs or social posts) that confirm this story? Also, does any official government source or press release back it up? If you can't confirm it, say so clearly.`

Both are fine — read the links, don't just trust the summary.

Either answer is a real result — silence or vague waffle is the warning sign.

✅ You'll know it worked when

the reply either (a) names specific outlets you can independently check, or (b) honestly tells you it can't verify the story.

🔄 If it looks different

**** on your screen: some versions of Gemini respond with a long list of links and short summaries; others give a single paragraph.

Next step ↓
GeminiCan you find atleast threereputable news…
✏️ Sketch — your screen may look a little different
3
Step 3 of 3

Ask for the counter-evidence, then check it yourself

One more prompt, same chat box. This time you're asking Gemini to play devil's advocate (the person who argues the opposite side, just to test the idea). Specifically, ask what would have to be true for this story to be false, and whether any trusted source is saying the opposite.

What you should see is a reply that lists reasons to be skeptical — older stories that contradict it, fact-check articles, or simply an honest "I don't see any counter-evidence, but here are the gaps in the original story." This is the moment where you stop letting Gemini think for you and start doing your own quick check.

Now open a second tab (or another browser window) and visit one of the outlets Gemini named — or type the headline into Google Search yourself inside quotation marks, like "government to ban cash above $200". The quotation marks tell Google to find that exact phrase. Look for coverage from outlets you already trust, not from sites you've never heard of.

💬 Exampletype this — `Play devil's advocate. What reasons are there to doubt this story? Has any fact-checker (like Snopes, PolitiFact, Reuters Fact Check, or AP Fact Check) looked at it? List the strongest counter-arguments or gaps in the evidence.`

If you can't find one, treat the story as unverified — and that's a perfectly fine answer.

✅ You'll know it worked when

you have at least one named, clickable source from a real newsroom or fact-checking organization, and you've personally visited that source yourself.

🔄 If it looks different

**** on a phone, you may need to switch between the Gemini app and your browser by swiping up from the bottom of the screen — that's normal.

Geminisecond tab
✏️ Sketch — your screen may look a little different
⚠️ Common mistakes
  • Trusting the first reply without reading it. Gemini can sound confident even when it's guessing. Always read the actual links it gives you, not just the summary text.
  • Asking Gemini to "just tell me if it's true." That's too vague. Always ask it to show you the sources and the counter-evidence. The showing matters more than the verdict.
  • Stopping after one prompt. A single question rarely tells the whole story. The three-step check — claim, sources, counter-evidence — is what protects you. Skipping a step is how misinformation gets through.
  • Sharing a story because a chatbot "said it looked real." Gemini is a starting point, not a court of law. If you can't find a trusted human-run outlet confirming the claim, don't forward it.
🚀 Try it now

Pick the last surprising headline you almost shared. Open Gemini, paste it in, and run all three prompts in order. Don't share anything until you've done the full check — and notice how different the story looks after ten focused minutes.

🎯 Next guideHow to Use Gemini to Keep One Project's Notes and Chats Together in One PlaceGive each project its own Gemini workspace so your files, notes and chats stay in one spot you can return to.

❓ Quick questions

How long does this take?

About 6 minutes — the guide has 3 steps, and you can tick each one off as you go.

Which tool do I need?

This guide uses Google Gemini — but the approach works very similarly in other AI assistants.

Do I need to prepare anything?
  • A Google account (the same one you use for Gmail or YouTube).
  • Access to Gemini in a browser, or the Gemini app on your phone. Free is fine; some advanced features may sit behind a paid plan.
  • The headline, link, or screenshot of the story you want to check — copy it to your clipboard before you start.
  • About 10 minutes of focused time. Rushing is what makes viral misinformation spread in the first place.
What mistakes should I avoid?
  • Trusting the first reply without reading it. Gemini can sound confident even when it's guessing. Always read the actual links it gives you, not just the summary text.
  • Asking Gemini to "just tell me if it's true." That's too vague. Always ask it to show you the sources and the counter-evidence. The showing matters more than the verdict.
  • Stopping after one prompt. A single question rarely tells the whole story. The three-step check — claim, sources, counter-evidence — is what protects you. Skipping a step is how misinformation gets through.
  • Sharing a story because a chatbot "said it looked real." Gemini is a starting point, not a court of law. If you can't find a trusted human-run outlet confirming the claim, don't forward it.

Keep reading

📘 How to Fact-Check a Viral Claim or Breaking News Story with Perplexity Use Perplexity's source-cited answers to see who said what, where, and when — all in about ten minutes. 📘 Fact-Check Online Claims with Perplexity's Sources Learn to use Perplexity to quickly trace the origins of social media claims and evaluate their reliability before you share them. 📘 How to Fact-Check a Suspicious Text or Link Before Forwarding It Use any AI assistant to spot warning signs, build a reusable checklist, and decide what to share with family, in about ten minutes. 📘 Fact-check a viral claim with Perplexity before you share it Run a shocking headline through Perplexity to see what the actual sources say — in 60 seconds. 📘 How to quickly fact‑check any AI answer in under one minute Learn a simple, step‑by‑step method to verify AI‑generated information fast, using source requests and quick cross‑checks so you can spot mistakes before you act. 📘 How to Use Gemini to Keep One Project's Notes and Chats Together in One Place Give each project its own Gemini workspace so your files, notes and chats stay in one spot you can return to.

📬 The week’s AI, in your inbox

One friendly email every Sunday — the 5 stories that mattered, in plain English. No spam, unsubscribe anytime.

Was this helpful?

✦ Generated by AI in AI World HQ's automated newsroom, written in plain language. Checked by automated fact and quality gates, and our editor spot-checks published guides every day. Spot a mistake? Use the buttons above.

📘 Prefer it in one file? Understand Anything: The AI Pack (20 guides, free printable PDF)

← Back to all stories