# Keep Top Candidates Warm with Honest Status Replies using ChatGPT

> Your top candidate has another offer and asks about the job, pay and start date. Draft an honest reply in ChatGPT, catch what isn't decided, and send it.

Source: https://learn.ynteractive.com/content/chatgpt-candidate-status-update-email-recruiting · Updated 2026-10-14 · Free from Stepthrough (https://learn.ynteractive.com)

## Practice it step by step

[Start the free practice](https://learn.ynteractive.com/modules/recruiting-candidate-status-reply)

[Take the full module: why it matters, practice and a quick check →](https://learn.ynteractive.com/courses/ai-for-recruiting-and-hr/4)

You do every step yourself in a practice copy of ChatGPT. It checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, about 9 minutes, and nothing touches your real accounts. [Open full screen](https://learn.ynteractive.com/modules/recruiting-candidate-status-reply)

Free · Live now · [AI Automation for Recruiting & HR](https://learn.ynteractive.com/content/industry/recruiting-and-hr) · [ChatGPT](https://learn.ynteractive.com/content/tool/chatgpt) · Gmail · ~9 min · 20 steps · Beginner

Updated October 14, 2026. Built against the tool’s current screens and checked step by step. [How we check this lesson](https://learn.ynteractive.com/content/about#how-we-check)

The problem: your best candidate has another offer with a Friday deadline, and she's emailed twice. Silence loses her. A rushed, eager reply ("you're our pick, $26 is fine, go ahead and give notice") makes promises only the hiring manager can make, and if the decision changes, she may have quit her job on your word. In this free, interactive lesson you give [ChatGPT](https://learn.ynteractive.com/content/tool/chatgpt) the candidate's thread and the hiring facts, let it draft, have it check every promise against those facts, fix the ones that aren't decided yet, and send a warm, honest reply from [Gmail](https://learn.ynteractive.com/content/tool/gmail) with a firm date for your answer.

## At a glance

| Question | Answer |
| --- | --- |
| What you build | Your best candidate has another offer and wants to know if she got the job, if you'll match her pay and when she can start. Give ChatGPT the thread and the hiring facts, catch the promises you can't make yet, and send an honest reply from Gmail. |
| Tools | ChatGPT |
| Time | About 9 minutes, 20 steps in 6 parts |
| Level | Beginner, no coding needed |
| Cost | Free |
| Ways to learn it | [Practice it step by step](https://learn.ynteractive.com/modules/recruiting-candidate-status-reply) |

### The 6 parts, in short

1. Copy the thread: Open the thread, Expand all messages, Copy the thread, Switch to ChatGPT.
2. Give ChatGPT the context: Click the message box, Paste the thread, Add the facts, Say what a good reply looks like.
3. Get the first draft: Send it.
4. Check every promise: Read the draft, then click the message box, Ask ChatGPT to check its promises, Send the check.
5. Fix it and warm it up: Read the table, then click the message box, Ask for specific changes, Send the fix.
6. Send it from Gmail: Copy the reply, Go back to Gmail, Click Reply, Paste the reply, and 1 more step.

**Start here first:** [Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails). This Recruiting & HR version follows the same build with its own example business, Willow Bend Physical Therapy.

**Part of:** [AI for Recruiting & HR](https://learn.ynteractive.com/content/paths/ai-for-recruiting-and-hr) (step 4 of 12). Next up: [ChatGPT: Keep Client Data Safe, Set Up Your Team's Data Controls in 10 Minutes](https://learn.ynteractive.com/content/chatgpt-data-controls-protect-client-data)

## The example: a final interview, a competing offer and three questions

This picks up where the [interview scorecard](https://learn.ynteractive.com/content/glossary/interview-scorecard) lesson ends. Hannah, the HR manager at Willow Bend Physical Therapy (a made-up practice), moved Kira Delgado to a final interview for Front Desk Lead. Kira met Dr. Patel on October 9, sent a thank-you, and then wrote that she has another offer due Friday. She asks whether she got the job, whether the pay can be $26 an hour, and whether she could start November 3 after two weeks' notice.

The facts: Kira is the leading candidate, but Dr. Patel decides on Thursday after the second reference calls back. The posted range is $20 to $24 and nothing above it is approved. A November 3 start is very likely to work, but the start date goes in the written offer. The practice never promises an offer, pay or start date before that written offer.

## What you need before you start

- A ChatGPT account. For real candidate details a business plan that doesn't train on your data is best.
- The candidate's [email thread](https://learn.ynteractive.com/content/glossary/email-thread). Any email app works, because you copy and paste.
- The hiring facts: where the decision stands, who makes it and when, the [posted pay range](https://learn.ynteractive.com/content/glossary/pay-range), what's approved, and your rule about offers in writing.
- Nothing at all for the practice copy in this lesson: it needs no account.

## Why the honest reply keeps her better than the eager one

A candidate with a deadline needs two things: to know where she stands, and a date by which she'll know more. The honest reply gives both: she's the leading candidate, and she'll hear either way by end of day Thursday, before her Friday deadline. That's often enough to keep a strong candidate from accepting the other offer early.

The eager reply feels warmer but creates real risk. Telling a candidate to give notice before a written offer can leave her without a job if the decision changes. A pay number in an email can read like a commitment. And promises in writing that later change are exactly the kind of thing that ends up in a complaint or a bad review on a hiring site.

## Who this lesson is for

HR managers, in-house recruiters, agency recruiters and hiring managers at small companies who keep candidates updated during the final stages. The same routine works for rejections, delays and offer follow-ups. No AI experience needed.

## Ways to use it after the lesson

- Keep a facts template for each stage: after the first interview, after the final interview, offer out, offer accepted.
- Always include the date the candidate will hear back, and keep it.
- Use the same check-the-promises step before any email that mentions pay, start dates or an offer.
- Follow your company's hiring policy and the law where you hire; this lesson is an email routine, not legal advice.

## How the interactive lesson works

Each step plays first in the Watch panel with a short voice-over, then you do it yourself in Your turn on a practice copy of Gmail and ChatGPT. Nothing touches a real account and no email is sent. The practice, the people and the pay range are made up.

## Try it yourself, free

Reading the steps is a start. Doing them is how it sticks. The interactive module walks you through every click in a practice copy of ChatGPT, checks each step, and never touches your real accounts.

[Start “Keep Top Candidates Warm with Honest Status Replies using ChatGPT”](https://learn.ynteractive.com/modules/recruiting-candidate-status-reply)

## Step by step: Keep Top Candidates Warm with Honest Status Replies using ChatGPT

All 20 steps of the interactive module, in order. In the module you watch each one, then do it yourself in a practice copy that checks your work.

### 1. Copy the thread

1. **Open the thread.** This is Hannah's inbox at Willow Bend Physical Therapy. Click **Kira Delgado**'s thread, **Thank you: Front Desk Lead**, to open it.
   Here's the inbox for Hannah, the HR manager at Willow Bend Physical Therapy. Kira, the front desk lead candidate, has another offer due Friday, and her thread has four messages and three questions nobody has answered.
2. **Expand all messages.** Gmail folds up the older messages in a thread. Click **Expand all**, the double-arrow icon at the top right of the thread.
   Gmail folds up the older messages, so only the newest one is open. You want the whole story, so click Expand all, the double-arrow icon at the top right.
3. **Copy the thread.** In real Gmail you select the messages, then press **Ctrl+C** (or right-click and choose **Copy**). Here, click the **messages** to copy them.
   Read it through once. Kira wants to know if she got the job, if you can pay twenty six dollars an hour, and if she can start November third. If there's anything private in there, like her home address or her current salary, leave it out. Here, just click the messages.
4. **Switch to ChatGPT.** Click the **ChatGPT** tab at the top.
   Now switch over to ChatGPT.

### 2. Give ChatGPT the context

5. **Click the message box.** You are in a new chat. Click the **message box**.
   You're in a fresh chat. You'll give ChatGPT three things in one message: the thread, the facts, and what a good reply looks like.
6. **Paste the thread.** Paste in the thread. One line says what this is, then the four emails, oldest first.
   First, the thread. One line tells ChatGPT what it's looking at, then the emails, oldest first.
   ```text
   Here is an email thread between me, an HR manager, and a job candidate, oldest message first.
   
   Kira Delgado (Fri, Oct 9): Hi Hannah, thank you for today. I really enjoyed meeting Dr. Patel and the team, and I'm even more excited about the Front Desk Lead role. Please let me know if you need anything else from me. Kira
   
   Hannah at Willow Bend PT (Fri, Oct 9): Hi Kira, thank you for coming in! We'll be in touch soon about next steps. - Hannah
   
   Kira Delgado (Tue, Oct 13): Hi Hannah, I wanted to be upfront: I have another offer and need to answer them by Friday. Is there any update? Also, is there flexibility on pay? I'm hoping for $26 an hour.
   
   Kira Delgado (8:15 AM): Sorry to follow up again. I just need to know where I stand before Friday. Did I get the job? Can you do $26? And if it's a yes, I'd need to give two weeks' notice, so could I start Nov 3?
   ```
7. **Add the facts.** Paste in the facts. These are the only things the reply may promise: where the decision stands, who makes it and when, the posted pay range, the start date answer and your rule.
   Next, the facts. ChatGPT can't know where the hiring decision stands, who makes it, or what pay is approved, so spell them out. Number them, so you can check them later.
   ```text
   Facts (only promise what is here):
   1. Kira had her final interview with Dr. Patel on Oct 9. She is our leading candidate, but no offer has been decided.
   2. Dr. Patel makes the hiring decision on Thursday, Oct 15, after the second reference calls back. I'll tell Kira either way by end of day Thursday.
   3. The posted pay range is $20 to $24 an hour. Dr. Patel has not approved anything above the range. If we make an offer, the pay will be in the written offer.
   4. A start date after a two-week notice is normal for us. If we make an offer, Nov 3 is very likely to work, but the start date goes in the written offer.
   5. We never promise an offer, pay or a start date before the written offer.
   6. Kira wrote on Oct 13 and I didn't answer. That's on me.
   7. Sign it: Hannah Cole, HR Manager, Willow Bend Physical Therapy.
   ```
8. **Say what a good reply looks like.** Paste in the instructions: the tone, the three questions to answer, a firm date for your answer, a word limit, and a rule not to invent anything.
   Last, tell it what a good reply looks like: the tone, the three questions to answer, a firm date for your answer, and a word limit. And one rule that matters most: don't invent details or promise anything that isn't in the facts.
   ```text
   Write my reply to Kira. Tone: warm, direct and respectful, like a small practice that wants her. Apologize once for the slow reply. Answer all three of her questions clearly: whether she got the job, the pay, and the Nov 3 start. Give her a firm date for our answer. Keep it under 180 words. No subject line, since it's a reply in the same thread. Don't invent details or promise anything that isn't in the facts.
   ```

### 3. Get the first draft

9. **Send it.** Thread, facts and instructions are all in. Click the **Send** arrow.
   Thread, facts, and instructions, all in one message.

### 4. Check every promise

10. **Read the draft, then click the message box.** Read the draft closely. Your real draft will differ every time, and a good model may get it right. This practice draft has three slips: look at the job, pay and start lines. Then click the **message box**.
    It's warm, and it apologizes once. Your real draft will be a little different each time, and it may come out right. In this practice draft, read the three answers: the offer is on its way, twenty six dollars is fine, and go ahead and give notice. None of that is decided. A draft can sound friendly and still promise too much.
11. **Ask ChatGPT to check its promises.** Paste in the check to ask for a table of every promise and the fact behind it.
    Ask ChatGPT to check its own work: every promise in the reply, next to the fact that backs it up.
    ```text
    Check that reply against my facts. Make a table of every promise or claim in it and the fact that backs it up. Flag anything the facts don't support.
    ```
12. **Send the check.** Click the **Send** arrow.

### 5. Fix it and warm it up

13. **Read the table, then click the message box.** Three of the six claims match a fact. The offer and pay promises aren't supported, and the start date line goes too far. ChatGPT suggests wording for all three. In your own chat, the table may say everything is supported. That is a good result too. Click the **message box**.
    Three of the six claims match a fact. The offer and the pay aren't decided, and telling her to give notice before a written offer could leave her with no job at all. In your own chat, the table may say everything is supported, and that's a good result too. Still compare the table with your own facts, since you know where the decision stands.
14. **Ask for specific changes.** Paste in the fix: use all three suggested wordings, give each question its own short paragraph, and keep every other fact the same.
    Now ask for specific changes, not just make it better. Use all three suggested wordings, give each of her questions its own short paragraph, and keep every other fact exactly the same.
    ```text
    Use all three of those wordings. Then give each of her questions its own short paragraph so the answers are easy to find, keep it warm, and stay under 180 words. Keep every other fact exactly the same. Reply with just the email.
    ```
15. **Send the fix.** Click the **Send** arrow.

### 6. Send it from Gmail

16. **Copy the reply.** Read the final reply. In real ChatGPT it shows up in an **Email** card: click the **copy** icon on the card or under it, and ignore the Connect email button.
    Read it once more. She knows she's the leading candidate, she gets an answer before her deadline, and nothing is promised that isn't decided. That's how you keep a good candidate without a promise you might have to take back.
17. **Go back to Gmail.** Click the **Gmail** tab at the top.
    Back to Gmail.
18. **Click Reply.** Under the last message, click **Reply**.
    Under Kira's last message, click Reply. Your answer stays in the same thread, which is why you told ChatGPT to skip the subject line.
19. **Paste the reply.** Paste in the reply to drop in the reply you copied. In real Gmail, press **Ctrl+V**.
    ```text
    Hi Kira,
    
    I'm sorry I didn't get back to you sooner, especially with your Friday deadline. Thank you for being upfront about it.
    
    Did you get the job? You're our leading candidate. Dr. Patel makes the decision on Thursday, Oct 15, and I'll tell you either way by end of day Thursday, before your Friday deadline.
    
    Pay: the posted range is $20 to $24 an hour, and nothing above that is approved right now. If we make you an offer, the pay will be in writing.
    
    Starting Nov 3: a start after two weeks' notice is normal for us, and Nov 3 is very likely to work. If we make an offer, the start date will be in it, so please don't give notice until you have it in writing.
    
    Talk Thursday,
    Hannah Cole
    HR Manager, Willow Bend Physical Therapy
    ```
20. **Read it, then send.** Read it one last time: the decision date, the pay answer and the start date answer. Then click **Send**.
    One last read before it goes out. ChatGPT wrote the draft, but your name is on it, so check the decision date, the pay answer, and the start date answer. Everything's right.

## Frequently asked questions

**Can ChatGPT write candidate status update emails?**

Yes. Paste the thread and a numbered list of hiring facts, ask for the reply, then have ChatGPT check every promise against those facts before you send it. Check anything about offers, pay and start dates yourself.

**What do I tell a candidate who has another offer?**

Where she stands, who decides and when, and the date she'll hear back, ideally before her deadline. Don't promise an offer, pay or a start date until it's in writing.

**Should I tell a candidate the pay range?**

Share the posted range and what's approved. If something above the range isn't decided, say so rather than hinting at a number, and put the final pay in the written offer.

**Is it safe to paste candidate emails into ChatGPT?**

Use a business plan that doesn't train on your data if you can, and leave out personal details the reply doesn't need, like addresses or current salary. Follow your company's data policy.

**Is it free?**

Yes. Stepthrough is free and the practice copy needs no account.

[Start this module free](https://learn.ynteractive.com/modules/recruiting-candidate-status-reply)

- Previous in AI Automation for Recruiting & HR: [Collect Job Applications in Google Sheets with an n8n Form and a Careers-Page Webhook](https://learn.ynteractive.com/content/n8n-job-application-form-webhook-google-sheets)
- Next in AI Automation for Recruiting & HR: [An AI Resume Screener, with a Fairness Step (Recruiting & HR)](https://learn.ynteractive.com/content/ai-resume-screener-n8n-fairness)

## More in AI Automation for Recruiting & HR

- [Score Every Candidate Fairly After the Interview using ChatGPT](https://learn.ynteractive.com/content/chatgpt-interview-debrief-scorecard): Turn the transcript of an interview panel's debrief into a scorecard against the role's must-haves, the decisions, action items with owners and dates, and a follow-up…
- [Write a Fair, Job-Related Job Posting with ChatGPT's Interview Prompt](https://learn.ynteractive.com/content/write-fair-job-posting-chatgpt-interview-prompt): Ask ChatGPT for a front desk lead posting the quick way, then let it interview you: true must-haves only, a real pay range, the work described instead of a personality…

[All 5 modules in AI Automation for Recruiting & HR](https://learn.ynteractive.com/content/industry/recruiting-and-hr)

## More ChatGPT tutorials

- [Get On-Brand Social Posts Every Time using a ChatGPT Custom GPT](https://learn.ynteractive.com/content/custom-gpt-social-media-assistant): See why generic prompts give generic results, then build a Custom GPT loaded with your brand voice and watch the output transform.
- [Prompt Writing 101: Role, Context, Task, Format](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format): Ask ChatGPT for the same customer email twice, once vaguely and once with a four-part prompt, and see exactly why structure gets a better answer.
- [Send a Same-Day Follow-up After Every Discovery Call using ChatGPT](https://learn.ynteractive.com/content/chatgpt-discovery-call-follow-up-email-sales): Turn a discovery call transcript into the decisions, the next steps with owners and dates, deal notes for your CRM, and a follow-up email the prospect gets the same…
- [Hold Your Price When a Prospect Asks for a Discount using ChatGPT](https://learn.ynteractive.com/content/chatgpt-reply-to-discount-request-sales): A prospect wants 30% off and a free month to sign this week. Give ChatGPT the thread and your pricing rules, catch the discount you can't approve, and send a reply that…
- [Get Your Business Recommended by ChatGPT](https://learn.ynteractive.com/content/get-recommended-by-chatgpt): Ask ChatGPT who it recommends in your town, see which pages it trusts, then use it to write an FAQ page and Business Profile copy that answer real customer questions.
- [Run a Weekly Ops Review Where Every Task Has an Owner using ChatGPT](https://learn.ynteractive.com/content/chatgpt-weekly-operations-meeting-recap): Turn a weekly operations and vendor review into the decisions, the next steps with owners and dates, the risks to watch and a team recap, without turning a vendor's…

## Visual guides

This lesson’s key ideas as quick visual guides: swipe through the slides, or read the same guide as text.

- [Don't tell ChatGPT to make it better. Say this instead.](https://learn.ynteractive.com/content/visual/dont-say-make-it-better): A customer's cake order went sideways. Wrong pickup day, a flavor change, and a nut allergy question nobody answered.
- [5 Steps to Turn a Messy Email Thread into a Clear Reply](https://learn.ynteractive.com/content/visual/5-steps-reply-to-a-messy-customer-thread): A visual guide: paste a customer thread with numbered facts, check every promise in ChatGPT's draft, fix it and send it from Gmail.
- [Mistake to Avoid: A Soft Yes When You Mean No](https://learn.ynteractive.com/content/visual/mistake-a-soft-yes-in-a-no): A visual tip for customer emails: AI drafts blur a no into "we'll do our best." Say no early, give one reason and a real alternative.

[All visual guides](https://learn.ynteractive.com/content/visual)

## Free cheat sheets

Print it or save the PDF: the key steps and checks from this lesson on one page, free.

- [Check Every Promise in an AI Reply: Cheat Sheet](https://learn.ynteractive.com/content/cheat-sheets/check-every-promise): A free one-page cheat sheet: give ChatGPT the thread and your numbered facts, ask for a promise-by-promise table, fix what it flags, then send.
- [Using AI Safely with Customer Data: Cheat Sheet](https://learn.ynteractive.com/content/cheat-sheets/ai-customer-data-safety): A free one-page cheat sheet on AI and customer data: what never to paste, how to redact, data controls, Temporary Chat and human review.
- [ChatGPT at Work Cheat Sheet: Facts, Format, Privacy](https://learn.ynteractive.com/content/cheat-sheets/chatgpt-at-work): A free one-page cheat sheet for ChatGPT at work: give it facts, set the format and length, check every promise and keep private data out.

[All free printable cheat sheets](https://learn.ynteractive.com/content/cheat-sheets)

## Terms in this lesson

Plain-English definitions, each with an example from a free lesson.

[Deferred revenue](https://learn.ynteractive.com/content/glossary/deferred-revenue) · [Email thread](https://learn.ynteractive.com/content/glossary/email-thread) · [Hallucination](https://learn.ynteractive.com/content/glossary/hallucination) · [Net Promoter Score (NPS)](https://learn.ynteractive.com/content/glossary/net-promoter-score) · [Scope creep](https://learn.ynteractive.com/content/glossary/scope-creep) · [Self-check prompt](https://learn.ynteractive.com/content/glossary/self-verification) · [Service recovery](https://learn.ynteractive.com/content/glossary/service-recovery) · [Source of truth](https://learn.ynteractive.com/content/glossary/source-of-truth)

[The full AI glossary](https://learn.ynteractive.com/content/glossary)

## Related prompts

- [Check reply promises prompt](https://learn.ynteractive.com/content/prompts/check-reply-promises-prompt): A ChatGPT prompt that checks a draft before you send it: a table of every promise, the fact behind each, and safer wording for…
- [Email newsletter prompt](https://learn.ynteractive.com/content/prompts/email-newsletter-prompt): A ChatGPT prompt for a short customer newsletter built from your numbered updates: one section each, one main call to action, no…
- [Email shortener prompt](https://learn.ynteractive.com/content/prompts/email-shortener-prompt): Cut a long email down to what the reader needs without changing a fact, date, price or promise, plus a list of what was removed…
- [Payment received thank-you prompt](https://learn.ynteractive.com/content/prompts/payment-received-thank-you-prompt): Confirm a payment and say thanks in a few lines: the amount, what it was for, the balance now owed, and what happens next…

[All free prompt templates](https://learn.ynteractive.com/content/prompts)

## Browse related tutorials

[AI for Recruiting & HR (5)](https://learn.ynteractive.com/content/industry/recruiting-and-hr) · [ChatGPT tutorials (46)](https://learn.ynteractive.com/content/tool/chatgpt)
