Alec Newcomb
May 28, 2025 • Reading Time: 4 minutes
In partnership with
Your quick win of the week - what to do when your AI’s lying to you.
A Serious Problem: AI is confidently stating "73% of marketers prefer email over social" – but we ran it back, and this statistic doesn't exist ANYWHERE.
Step 1: ADD Source-Demanding Prompt Step
Add this to key content generation prompts:
CRITICAL: For every statistic, claim, or fact you include, you MUST either:
- State "This requires verification"
- Provide the specific source and date
-Mark uncertain information with [VERIFY]
Step 2: Content Verification Tracker
👉🏼 Google Sheet Content Verification Tracker 👈🏼
Use this FREE template that I build for my upcoming UNH class so your team has a clear process to replace AI Fibs before they become problems.
Step 3: Measure Your Brands Error Rate
Track this KPI: AI Accuracy Score = (Verified Claims ÷ Total Claims) × 100
Target: 99%+ accuracy
Baseline: Check your last 10 AI pieces
Do quarterly audits of published content
Fact to verify: [CLAIM or use linked above Google Sheet as a PDF]
Searched: [Google, industry reports, company sites, Wikipedia]
Result: [VERIFIED/DEBUNKED/MODIFIED]
Replacement Fact: [ACCURATE VERSION with source url]
Note:[DATE]
KeepCart: Coupon Protection partners with DTC brands like Quince, Blueland, Vessi and more to protect your checkout from plug-ins like Honey, CapitalOne, RetailMeNot, and more to boost your DTC margins
Overpaid commissions to affiliates and influencers add up fast – Get rid of the headache and revenue losses with KeepCart.
After months of using KeepCart, Mando says “It has paid for itself multiple times over.”
Now it’s your turn to see how much more profit you can keep.
👀 Your Next Step: Run your next AI campaign through this 3-step process and track the error rate improvement.
What's the worst AI hallucination you've caught before publication? |
Cheers,
Alec
P.S. If your team is struggling with AI accuracy in marketing (hello, hallucinations), join my next UNH course. We tackle the real challenges of AI not just the hype.
