Get one misclassified blood-panel charge reversed on a live insurer call with ChatGPT's help
- Posted
- by Kevin Darbelnet (LinkedIn)
- Last checked
- Method:
- How we verify
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
PartialThe source says it only partly worked, or had a significant problem a person had to deal with.
What went wrong: One of the two charges was reversed during the call; the appeal on the second was still pending.
Context: The poster is an AI strategy consultant, and the post ends with a pitch for that work.
Outcome
Billed for a standard blood panel from a routine preventive visit that had been misclassified, Kevin Darbelnet kept ChatGPT open during a call with UnitedHealthcare. It decoded the diagnosis and CPT codes, fed Darbelnet questions to ask the provider and insurer in real time, drafted a formal appeal letter and helped assemble EOBs, provider statements and claim history. One charge was reversed during the call; an appeal on the second was submitted within an hour and was still pending at the time of posting.
Agent
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Let's work this out together. I'll tell you what I know, you suggest options and ask what you need, and we'll narrow it down step by step. Nothing gets booked, bought or sent until I say so. Goal: Help me challenge a charge I think was billed under the wrong code, before and during my call with the insurer. What I'll share as we go: - The bill and EOB (codes, dates, amounts; I'll hide my ID numbers) - What the visit was for (e.g. a routine preventive check-up) - What the provider and insurer have told me so far This is admin help, not medical advice. Don't diagnose or suggest treatments. If anything I mention sounds urgent, tell me to contact a doctor or emergency services first. Rules: - Explain each code on the bill in plain words and say why it might have been billed as non-preventive. - Give me short questions to ask the provider's billing office and the insurer, in order. - During the call, keep answers to a line or two so I can read them out. - Draft an appeal letter only from facts in my documents and list the attachments it needs. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. Output: A one-page call script, a list of documents to gather, and a draft appeal letter. You'll know it worked when: the right code is confirmed or corrected, and anything left is in a written appeal with proof attached.
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Let's work this out together. I'll tell you what I know, you suggest options and ask what you need, and we'll narrow it down step by step. Nothing gets booked, bought or sent until I say so. Goal: Help me challenge a charge I think was billed under the wrong code, before and during my call with the insurer. What I'll share as we go: - The bill and EOB (codes, dates, amounts; I'll hide my ID numbers) - What the visit was for (e.g. a routine preventive check-up) - What the provider and insurer have told me so far This is admin help, not medical advice. Don't diagnose or suggest treatments. If anything I mention sounds urgent, tell me to contact a doctor or emergency services first. Rules: - Explain each code on the bill in plain words and say why it might have been billed as non-preventive. - Give me short questions to ask the provider's billing office and the insurer, in order. - During the call, keep answers to a line or two so I can read them out. - Draft an appeal letter only from facts in my documents and list the attachments it needs. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. - Keep a running log of who I spoke to, when, and any reference numbers. Output: A one-page call script, a list of documents to gather, and a draft appeal letter. You'll know it worked when: the right code is confirmed or corrected, and anything left is in a written appeal with proof attached. Before you finish: re-read my goal and constraints, check your answer against each one, and list anything you assumed or couldn't confirm.
Source
Related cases
After weeks of getting the runaround from both her doctor's office and her insurer, a poster put all the bill information into Grok. She says it found the coding issue and told her how to press it with her doctor, and she avoided a huge medical bill.
Grok · Personal · Source date:
After a new dentist's visit left her owing $1,201.80 on top of the $2,111.29 she'd already paid, Jamie Phillis gave ChatGPT her call transcripts, receipt, explanation of benefits and her insurer's appeal instructions. It wrote a formatted appeal letter in under a minute and flagged duplicate evaluations and a charge at seven times the allowed rate. The first appeal was denied; ChatGPT then drafted a second-level appeal and a complaint to the Arizona Department of Insurance. She says the case was never formally resolved, but the office never sent her a bill for the uncovered balance and she never paid the $1,200.
Poster says:$1,201.80 balance never billed after appeals
ChatGPT · Personal · Source date:
- Appeal a denied cardiac test using studies found with ChatGPT Deep ResearchRecreated promptEvidence: Described by poster
When insurance denied the poster's husband's cardiologist-ordered nuclear stress test as 'experimental' (a $1,500 out-of-pocket cost), the poster used ChatGPT Deep Research to find peer-reviewed studies on the test's effectiveness: five studies in ten minutes. Five minutes later they had a draft appeal letter for the cardiologist to review and send. The poster says a week later the insurer reversed its decision and covered the test.
ChatGPT · Personal · Source date: