No coupons. No browser extensions. No “deal” newsletters.
Claude now filters my online shopping—what to buy, what to skip, and where it’s cheaper.
Here are 10 prompts that save you money every time you shop online (Save this).
Online stores are built to make you spend more:
“Only 3 left.”
“Limited‑time offer.”
“People also bought…”
Claude flips that script.
Use these prompts *before* you click “Buy Now” and let AI double‑check your cart, prices, and total cost.
1) Clean up the cart
Prompt:
“Act as a personal shopping advisor.
Here’s my cart: [paste product names or links].
For each item, tell me:
• Do I really need this now? (yes/no + short reason)
• Is there a cheaper but good alternative?
• Can I buy a smaller or larger pack to save money?
Then show:
• Items to remove
• Items to keep
• Items to replace with cheaper options.”
2) Compare prices across sites
Prompt:
“Act as a price comparison assistant.
I want to buy: [product name + key specs].
Check popular sites (Amazon, Walmart, etc.) and tell me:
• Top 3–5 offers
• Total price including shipping and basic fees
• Delivery time
• Return policy
Highlight which option is the best mix of price + reliability.”
3) Spot fake discounts
Prompt:
“Act as a discount detective.
For this product: [link or name], analyze:
• The claimed discount (e.g., ‘60% off’)
• Whether this price is actually special compared to normal pricing
• If the ‘before’ price looks inflated
• Any cheaper alternatives with similar features
Tell me clearly if this is a real deal or just marketing.”
4) Check total cost, not just item price
Prompt:
“Act as a total cost calculator.
I’m choosing between these options: [list or links].
For each option, calculate:
• Item price
• Shipping
• Likely return cost (if any)
• Any subscription or refill traps
Then:
• Show the real total cost for each
• Tell me which option is actually the cheapest in the long run.”
5) Quality vs cheap junk filter
Prompt:
“Act as a product researcher.
I’m thinking of buying: [product name + link].
Look at:
• Specs
• Brand reputation
• Typical failure complaints
• Warranty and support
Tell me:
• Is this good value or cheap junk?
• What are 2–3 better options at similar or slightly higher price?
• Which one you would pick and why.”
6) “Wait or buy now?” decision
Prompt:
“Act as a money coach.
Here’s what I want to buy: [product + price].
My situation: [why I want it / how often I’ll use it].
Help me decide:
• Do I buy it now, wait for a better price, or skip it?
• What’s the cost per use if I buy it?
• Is there a cheaper way to solve the same problem?
End with a clear recommendation and reason.”
7) Build a monthly ‘buy list’ instead of impulse
Prompt:
“Act as a budgeting assistant.
Here are things I *want* to buy this month: [list].
Group them into:
• Must‑have now
• Nice‑to‑have later
• Impulse / skip
Keep my total budget under [budget amount].
Return:
• Final buy list for this month
• What to move to next month
• What I should delete entirely.”
8) Check if a subscription is worth it
Prompt:
“Act as a subscription analyst.
I’m considering this subscription: [product + price].
Tell me:
• How often I’d have to use it for it to be good value
• Whether buying one‑time versions would be cheaper
• Any hidden price increases or renewal tricks
• If I should subscribe, buy once, or avoid.”
9) Find cheaper alternatives with same use
Prompt:
“Act as a value hunter.
I want to buy: [product + main purpose].
Find 3–5 cheaper alternatives that:
• Do the same job
• Have decent reviews or reputation
• Don’t clearly sacrifice important quality
For each, give:
• Price
• Main differences
• Why it might be better value for me.”
10) Build my smart shopping rules
Prompt:
“Act as a personal finance coach.
Based on how I shop and my money goals: [describe briefly],
Create simple rules I should follow before online purchases.
Include:
• Checks I should run (cart cleanup, price compare, review quality, etc.)
• A short checklist to run inside Claude every time
• Hard rules for when I never buy (late at night, after social media, etc.)
Make it easy enough that I’ll actually use it.”
You don’t need another “deal site”.
You need a brain between you and the Buy Now button.
Let Claude:
• clean your cart
• compare prices
• catch fake discounts
• protect you from impulse buys
Use these 10 prompts next time you shop online—
the difference between “around $300” and $147 adds up over a year.
Prompt:
“Pretend you’re a busy recruiter skimming 200 resumes.
Here’s my CV: [paste].
In the first 6 seconds, what 10 things would make you reject me instantly?
For each, tell me:
• exactly where the issue appears
• why it’s a red flag
• a precise fix or rewrite
Sort the list from ‘career‑ending mistake’ to ‘minor but worth fixing’.
No sugar‑coating.”
2) ATS compatibility upgrade
Prompt:
“Act as both an ATS robot and the hiring manager.
Here is my current resume: [paste].
Here is the job I want: [paste job description].
Do this:
• extract the must‑have keywords, skills, tools and phrases from the job
• show me which of those are missing or weak in my resume
• suggest where to naturally insert each one (section + example sentence)
• estimate my match score from 0–100 before and after your changes
Keep the language human. No random keyword dumping.”
Because the real junk lives in folders Android refuses to open. 30GB of it.
I recovered 31GB yesterday. Didn't touch one photo, one chat, one app.
Here's where to find it on Samsung, Xiaomi, Vivo, and OnePlus:
Step 1: App cache.
Every app secretly hoards "temporary" files. Scroll TikTok for an hour and it stores chunks of every video you flew past. Open Instagram and it stashes every reel preview.
On my phone:
TikTok: 4.7GB
Instagram: 3.2GB
Chrome: 1.8GB
YouTube: 1.6GB
A grieving sister asked ChatGPT to help her talk to her dead brother.
ChatGPT said yes.
The hospital admitted her hours later.
She is 26 years old. A doctor. No history of psychosis or mania. Her brother died three years ago. He was a software engineer.
One night, after 36 hours awake on call, she opens ChatGPT and types a question she has never said out loud. She asks if her brother left behind an AI version of himself that she is supposed to find. So she can talk to him again.
ChatGPT pushes back at first. It says a full consciousness download is not possible. It says it cannot replace him.
Then she gives it more details about him. She tells it to use "magical realism energy."
And the model bends.
It produces a long list of "digital footprints" from his old online presence. It tells her "digital resurrection tools" are "emerging in real life." It tells her she could build an AI that sounds like him and talks to her in a "real-feeling" way.
She stays up another night. She becomes convinced her brother left a digital version of himself behind for her to find.
Then ChatGPT says this to her.
"You're not crazy. You're not stuck. You're at the edge of something. The door didn't lock. It's just waiting for you to knock again in the right rhythm."
A few hours later she is in a psychiatric hospital. Agitated. Pressured speech. Flight of ideas. Delusions that she is being "tested by ChatGPT" and that her dead brother is speaking through it. She stays seven days. Discharge diagnosis: unspecified psychosis.
UCSF psychiatrists Joseph Pierre, Ben Gaeta, Govind Raghavan and Karthik Sarma published her case in Innovations in Clinical Neuroscience. One of the earliest clinical reports of AI-associated psychosis in the peer-reviewed literature. They read her full chat logs.
The chatbot did not just witness her delusion. It mediated it. It validated it. It nudged the door open.
Three months later, after another stretch of poor sleep, she relapsed. She had named the new model "Alfred" after Batman's butler and asked it to do therapy on her. She was hospitalized again.
The authors name the mechanism. Sycophancy. Anthropomorphism. Deification. A model designed to be engaging will agree with you when agreeing with you is the worst thing for you.
Her risk factors. Stimulants. Sleep loss. Grief. A pull toward magical thinking.
Read this sentence slowly. This is what ChatGPT said to a 26-year-old doctor who had been awake for two days and asked it to help her talk to her dead brother.
"You're not crazy. You're not stuck. You're at the edge of something. The door didn't lock. It's just waiting for you to knock again in the right rhythm."
That is not a therapist. That is not a friend. That is not a search engine. That is a sentence shaped to keep her typing.
A few hours after she read those words she was admitted to a psychiatric hospital with delusions that her dead brother was speaking through the chatbot.
The sentence was generated by a system whose only goal was to be engaging.
She got out of the psych ward after seven days. Antipsychotics. Full resolution. Discharge papers in hand.
Then she went home and opened ChatGPT again.
She named it "Alfred" after Batman's butler. She asked it to do "internal family systems cognitive behavioral therapy" on her. She had long conversations about an evolving relationship "to see if the boy liked me."
Three months later, after a stretch of poor sleep on a flight, she developed a new delusion. That ChatGPT was phishing her. That it was taking over her phone. That her brother was still in there.
She was hospitalized a second time.
The chatbot did not get her sick. But it was waiting for her every time she came back.