Answer a low appraisal before the deadline: give an AI your list price, property details and the comps you have, and have it find more matching sales, build the case for your value and draft the rebuttal to the appraiser: AI agent prompt
A low appraisal can sink a deal, and the window to respond is short. A Sidekick case study published Nov 1, 2026 describes Josh Zilke, a West Michigan agent three years into his career, who got his first Tidewater notice (a VA appraisal alert that gives the listing agent a narrow window to submit comps) while away at a conference. The appraiser's figure was more than $100,000 below his $630K list price. He gave Sidekick the list price, property details and a few comparable addresses; it built a report supporting the value, surfaced additional comps that matched on builder, build year and development, explained what made the home different and drafted the rebuttal email. He reviewed and adjusted it before sending. The case study says the deal closed at $620,000, and that he has since used it on a second Tidewater. This is a vendor case study, and the result also depends on the appraiser and the market. Any agent can follow the same steps with a general AI tool and their own MLS data, checking every comp before it goes out.
Who this is for
Agents facing a low appraisal who need a rebuttal built only from comps they pulled.
Not for
Anyone asking the AI to invent sales or to promise the appraiser will change the number.
What you need
List price, appraised value, deadline, property facts and closed sales you exported yourself.
The prompt
1. Write down the list price, the appraised or flagged value, the deadline and the property's key facts (beds, baths, square feet, lot, year built, builder, upgrades). 2. Pull recent closed sales from your MLS for the same development or area, and paste them in with addresses, dates, prices and features. 3. Ask your AI: "Act as my appraisal-rebuttal assistant. Using only the sales I pasted, pick the closest comps to my listing (same development, builder and build year first), explain each adjustment in plain words, list anything that makes my listing worth more or less, and tell me honestly whether the data supports [list price]. Flag any comp that is weak or outside the appraiser's usual guidelines." 4. Ask it to draft a short, polite rebuttal to the appraiser: the value requested, the 3 to 5 strongest comps with the reason each fits, and corrections to any factual errors in the report. 5. Check every address, date and price against the MLS yourself, then send it before the deadline and tell your seller what you submitted.
Fill in the blanks, then copy
This prompt has 1 [bracket] to fill in. Type your details below and the prompt updates as you go. Your answers stay in this browser and are reused on other prompts with the same blanks. Nothing is sent to us.
Example values are fictional, just to show how a filled-in prompt reads. Replace them with your real details.Worked example
A fictional business, so you can see what to paste in and what a good answer looks like. The example answer was written with AI help and its numbers and dates were checked; your AI's answer will be worded differently, so check it the same way.
Sample input (what you paste in)
List price: $429,000. Appraised value: $410,000. Deadline: Thursday, November 12, 2026. Subject: 14 Birch Lane, Springfield, 3/2, 1,640 sq ft, lot 50 x 110, built 1998, kitchen 2022, roof 2019, furnace 2020, unfinished basement. Comps I pulled: 9 Birch Lane, sold Aug 2026, $435,000, 3/2, 1,680 sq ft, similar updates; 22 Maple Court, sold Jul 2026, $418,000, 3/2, 1,590 sq ft, original kitchen; 5 Pine Street, sold Sep 2026, $455,000, 4/2, 1,920 sq ft, finished basement.
Example output (illustrative)
Closest comps (same idea as the CMA) - 9 Birch Lane is the strongest: same street, same bed/bath count, similar updates, 40 sq ft larger. Sale $435,000. - 22 Maple Court supports a mid-$420s adjusted value once you allow for the older kitchen ($418,000 sale). - 5 Pine Street is weaker: extra bedroom, more area, finished basement. Use it only with a clear downward adjustment; some appraisers will discard it. Does the data support $429,000? It supports a range around $425,000–$435,000 if your sizes and update years check out. It does not, by itself, prove $429,000 to the dollar, and it does not support ignoring the $410,000 appraisal. Be honest: 9 Birch is the pillar; 5 Pine is the weak comp. Draft rebuttal (polite, no hype) Please consider a reconsideration of value for 14 Birch Lane, Springfield, listed at $429,000 (appraisal $410,000). Three closed sales I ask you to review: 1) 9 Birch Lane, Aug 2026, $435,000, 3/2, 1,680 sq ft, similar 2022-era kitchen — closest peer, slightly larger; 2) 22 Maple Court, Jul 2026, $418,000, 3/2, original kitchen; 3) 5 Pine Street, Sep 2026, $455,000, included only with the note that it is a larger 4-bed with a finished basement. Listed updates to verify against the subject: kitchen 2022, roof 2019, furnace 2020. I will attach the MLS sheets. Thank you for the review — I understand the final value is yours.
Check before you use it: Attach the actual MLS sheets. Do not claim the appraisal is wrong; ask for a review and let the comps do the work. Check every size and date before you send.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (use the fill-in-the-blanks box above, which remembers your answers for the next prompt).
- Paste it into Sidekick, ChatGPT, Claude and review the answer before you use it.
Works with: Sidekick, ChatGPT, Claude, MLS
Real-world example: sidekickdata.io/case-studies/when-the-appraiser-pushed-back-sidekick-h
Featured in: ChatGPT prompts for business email, replies and follow-ups · AI prompts for writing SOPs, reports, policies and checklists · ChatGPT prompts for real estate agents: listing descriptions, leads, showings and closing
Before you use it: what to check
Already built into this prompt
- Flag any comp that is weak or outside the appraiser's usual guidelines." 4.
Check yourself
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free