Gmail + WhatsApp follow ups that cut candidate ghosting
Candidate follow-up breaks in small, quiet ways. Someone applies, you mean to respond, then the day explodes. By the time you remember, the candidate has moved on, or worse, they show up cold and confused.
This Gmail WhatsApp follow-ups automation hits recruiters hardest, but hiring managers and ops leads feel it too. You get a consistent, human follow-up sequence for every applicant, without living in your inbox.
It triggers from your ATS or form, writes a personalized 7-day nurture sequence, then sends it on schedule through Gmail and WhatsApp. Next, you’ll see exactly what it fixes, how it runs, and what you need to launch it.
How This Automation Works
See how this solves the problem:
n8n Workflow Template: Gmail + WhatsApp follow ups that cut candidate ghosting
flowchart LR
subgraph sg0["MCP Recrutei Flow"]
direction LR
n0["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/webhook.dark.svg' width='40' height='40' /></div><br/>Webhook"]
n1@{ icon: "mdi:cog", form: "rounded", label: "Extract age", pos: "b", h: 48 }
n2@{ icon: "mdi:swap-vertical", form: "rounded", label: "Getting the AI content", pos: "b", h: 48 }
n3["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Separating information"]
n4["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Separating messages per days"]
n5@{ icon: "mdi:cog", form: "rounded", label: "Wait for more 4 days", pos: "b", h: 48 }
n6@{ icon: "mdi:cog", form: "rounded", label: "Wait for more 2 days", pos: "b", h: 48 }
n7@{ icon: "mdi:cog", form: "rounded", label: "No Operation, do nothing", pos: "b", h: 48 }
n8@{ icon: "mdi:wrench", form: "rounded", label: "MCP Recrutei", pos: "b", h: 48 }
n9@{ icon: "mdi:robot", form: "rounded", label: "AI Recruitment Assistant", pos: "b", h: 48 }
n10["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Message WhatsApp day1"]
n11@{ icon: "mdi:message-outline", form: "rounded", label: "Message Gmail day1", pos: "b", h: 48 }
n12["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Message WhatsApp day3"]
n13@{ icon: "mdi:message-outline", form: "rounded", label: "Message Gmail day3", pos: "b", h: 48 }
n14["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Message WhatsApp day7"]
n15@{ icon: "mdi:message-outline", form: "rounded", label: "Message Gmail day7", pos: "b", h: 48 }
n16["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/merge.svg' width='40' height='40' /></div><br/>Merge correct next node"]
n17["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/merge.svg' width='40' height='40' /></div><br/>Merge correct next node1"]
n0 --> n3
n1 --> n9
n8 -.-> n9
n11 --> n16
n13 --> n17
n15 --> n7
n6 --> n12
n6 --> n13
n5 --> n14
n5 --> n15
n10 --> n16
n12 --> n17
n14 --> n7
n2 --> n4
n3 --> n1
n16 --> n6
n9 --> n2
n17 --> n5
n4 --> n10
n4 --> n11
end
%% Styling
classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef disabled stroke-dasharray: 5 5,opacity: 0.5
class n9 ai
class n8 ai
class n0,n10,n12,n14 api
class n3,n4 code
classDef customIcon fill:none,stroke:none
class n0,n3,n4,n10,n12,n14,n16,n17 customIcon
The Challenge: Candidates Go Quiet After They Apply
Most candidate “ghosting” isn’t rudeness. It’s timing. If they apply and hear nothing for a day or two, they assume the role is already filled, or that your process is messy. Then you finally reach out, but it’s a cold restart. You re-answer basic questions, you re-confirm availability, you rebuild trust. And if you’re hiring at any kind of volume, the manual follow-ups become a second job that competes with sourcing, screening, and interviews.
It adds up fast. Here’s where it breaks down in real hiring workflows.
- You send a “thanks for applying” email, but forget the day-3 nudge, so the conversation stalls.
- WhatsApp messages get sent ad hoc, which means tone and details change from candidate to candidate.
- Copying phone numbers out of an ATS invites mistakes, and one wrong digit means your follow-up vanishes.
- When hiring ramps up, you end up choosing between speed and personalization, and neither choice feels good.
The Fix: A 7-Day Follow-Up Sequence Sent for You
This workflow turns every new applicant into a scheduled, multi-channel follow-up plan. A webhook catches the candidate details from your ATS (or any form submission), then the workflow cleans the data so names, job titles, and phone numbers are ready to use. Next, an AI “recruitment assistant” writes three distinct messages that feel personal, not templated, and it can adjust tone using context like the candidate’s age. Those messages get split into Day 1, Day 3, and Day 7. Day 1 goes out immediately via Gmail and WhatsApp. Then the workflow waits, sends the next message, waits again, and finishes the sequence automatically.
The flow is simple: capture applicant data, generate tailored copy, then send on a reliable schedule. Gmail covers the formal trail, WhatsApp handles the fast, friendly touch, and you stop chasing candidates one reminder at a time.
What Changes: Before vs. After
| What This Eliminates | Impact You’ll See |
|---|---|
|
|
Real-World Impact
Say you get 10 applicants a week for one role. Manually, a simple three-touch follow-up (email + WhatsApp on Day 1, Day 3, Day 7) often takes about 6 minutes per touch once you find the record, rewrite the message, and send it in two channels. That’s roughly 3 hours a week of repetitive follow-up. With this workflow, you spend a few minutes setting it up once, then each new applicant triggers automatically and runs in the background for the full week.
Requirements
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Gmail to send Day 1, 3, and 7 emails.
- WhatsApp (Evolution API) to send WhatsApp follow-ups on schedule.
- OpenAI API key (get it from your OpenAI dashboard).
Skill level: Intermediate. You’ll connect credentials, paste an API key, and test a webhook payload.
Need help implementing this? Talk to an automation expert (free 15-minute consultation).
The Workflow Flow
A new candidate hits your pipeline. Your ATS (or form tool) sends candidate details into n8n through a Webhook, so the workflow starts the moment an application is created.
The workflow cleans the data and adds context. It parses key fields (like name, role, and phone), then computes the candidate’s age from the birthday field so the messaging can be adjusted thoughtfully.
AI writes a three-part message sequence. The OpenAI-powered “Recruitment Assistant” generates Day 1, Day 3, and Day 7 messages as one block, then a small script splits them into separate variables for scheduling.
Messages go out in Gmail and WhatsApp, then wait nodes handle timing. Day 1 sends immediately through Gmail and the WhatsApp HTTP request. The workflow waits two days, sends Day 3, waits four more days, then sends the final Day 7 follow-up.
You can easily modify the timing (for example, Day 2 and Day 5) or switch the wording style based on role type. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Webhook Trigger
Set up the inbound webhook that receives candidate data and starts the follow-up flow.
- Add the Incoming Webhook Trigger node and set Path to
receving-new-candidate. - Set HTTP Method to
POST. - Connect Incoming Webhook Trigger to Parse Candidate Details to pass the request payload into the workflow.
- Use the Test button in the node to generate the webhook URL for initial testing.
Step 2: Connect OpenAI for Message Generation
Configure the AI composer and its MCP tool to generate the three scheduled outreach messages.
- Open AI Outreach Composer and set Model to
gpt-4.1-mini. - Credential Required: Connect your openAiApi credentials in AI Outreach Composer.
- Verify the user message content includes candidate details with expressions like
{{ $('Parse Candidate Details').item.json.vacancy_id }}and{{ $('Compute Age').item.json.yearsOld.years }}. - Open Recruiter MCP Tool and set Endpoint URL to
your_recrutei_mcp_url. This tool is connected to AI Outreach Composer as an AI tool—add any required credentials on AI Outreach Composer, not on the sub-node.
Step 3: Set Up Candidate Parsing and Message Splitting
Normalize incoming data, compute age, capture the AI output, and split the content into Day 1/3/7 messages.
- In Parse Candidate Details, keep the provided JavaScript to normalize fields like phone and map input values to vacancy_id, name, email, birthday, and more.
- In Compute Age, set Operation to
getTimeBetweenDates, Start Date to={{ $json.birthday }}, End Date to={{ $now }}, and Output Field Name toyearsOld. - In Capture AI Output, set the content assignment value to
={{ $json.message.content }}. - In Split Message Schedule, keep the JavaScript that splits the AI output into
day1,day3, andday7.
Step 4: Configure Day 1 Outreach Actions
Send the initial messages via WhatsApp and Gmail, then merge the results for the next wait step.
- Split Message Schedule outputs to both Send WhatsApp Day 1 and Send Gmail Day 1 in parallel.
- In Send Gmail Day 1, set Send To to
={{ $('Parse Candidate Details').item.json.email }}, Message to={{ $json.day1 }}, Subject to=Applying for the vacancy {{ $('Parse Candidate Details').item.json.vacancy }}, and Email Type totext. - Credential Required: Connect your gmailOAuth2 credentials in Send Gmail Day 1.
- In Send WhatsApp Day 1, set URL to
=https://{server-url}/message/sendText/{instance}, Method toPOST, and keep the JSON Body expression as provided. - In Send WhatsApp Day 1, set the Header Parameters apikey value to
[CONFIGURE_YOUR_API_KEY]. - Connect both Day 1 nodes into Merge Day 1 Results so the flow continues only after both messages complete.
{server-url}, {instance}, and [CONFIGURE_YOUR_API_KEY] in all WhatsApp nodes, or HTTP requests will fail.Step 5: Configure Delays and Follow-Up Messages (Day 3 and Day 7)
Delay the workflow and send parallel messages on Day 3 and Day 7, then close the flow.
- In Delay Two Days, set Amount to
2and connect it after Merge Day 1 Results. - Delay Two Days outputs to both Send WhatsApp Day 3 and Send Gmail Day 3 in parallel.
- Configure Send Gmail Day 3 with Send To
={{ $('Parse Candidate Details').item.json.email }}, Message={{ $('Split Message Schedule').item.json.day3 }}, and Subject=Applying for the vacancy {{ $('Parse Candidate Details').item.json.vacancy }}. - Credential Required: Connect your gmailOAuth2 credentials in Send Gmail Day 3.
- In Send WhatsApp Day 3, keep the JSON Body expression that references
{{ $('Split Message Schedule').item.json.day3 }}and update the apikey header value. - Merge outputs using Merge Day 3 Results, then connect to Delay Four Days with Amount set to
4. - Delay Four Days outputs to both Send WhatsApp Day 7 and Send Gmail Day 7 in parallel, and both complete at End Flow Placeholder.
- Configure Send Gmail Day 7 with Send To
={{ $('Parse Candidate Details').item.json.email }}, Message={{ $('Split Message Schedule').item.json.day7 }}, and the same subject line expression. - Credential Required: Connect your gmailOAuth2 credentials in Send Gmail Day 7.
- In Send WhatsApp Day 7, keep the JSON Body expression using
{{ $('Split Message Schedule').item.json.day7 }}and update the apikey header value.
Step 6: Test and Activate Your Workflow
Validate the entire flow from webhook to final follow-up, then activate it for production use.
- Click Execute Workflow and send a POST request to the Incoming Webhook Trigger URL with a JSON body containing
vacancy_id,name,email,vacancy,phone,birthday, andlocation. - Confirm AI Outreach Composer returns a single string with two pipe characters, and Split Message Schedule creates
day1,day3, andday7. - Verify that Send Gmail Day 1 and Send WhatsApp Day 1 both execute, then that Merge Day 1 Results continues to Delay Two Days.
- For testing, temporarily reduce Delay Two Days and Delay Four Days amounts to minutes to validate Day 3 and Day 7 paths faster.
- Once verified, restore delay values and toggle the workflow to Active for production use.
Watch Out For
- Gmail OAuth permissions can be the silent culprit. If emails don’t send, open the Gmail credential in n8n and re-authenticate, then confirm the “From” address matches the connected account.
- If you’re using Wait nodes or external sending, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Evolution API keys and instance URLs are easy to mistype. When WhatsApp fails, check the HTTP Request node’s {server-url}, {instance}, and header API key first, then review the Evolution API logs for rejected requests.
Common Questions
About an hour if your Gmail and WhatsApp accounts are ready.
Yes. You won’t write code, but you will copy a webhook URL, connect Gmail, and paste an API key into the WhatsApp HTTP Request nodes.
Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in OpenAI API costs (usually pennies per candidate for short messages) plus whatever your WhatsApp provider charges.
Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.
You can tweak the system prompt inside the AI Outreach Composer to match your role types, tone, and compliance notes. If you don’t want age-based language, remove the age field from the AI input and keep the rest the same. Timing is also easy to change: adjust the “Delay Two Days” and “Delay Four Days” nodes to fit your process. And if you use a different WhatsApp gateway than Evolution API, swap the HTTP Request nodes to your provider’s send-message endpoint.
Usually it’s expired OAuth access. Reconnect the Gmail credential in n8n, then re-test by running the Day 1 Gmail node with a sample candidate payload. If it still fails, check that your Google account allows the required scopes and that you’re not trying to send from an alias the credential doesn’t own.
On most setups, it handles typical small-business hiring volume easily. n8n Cloud capacity depends on your plan’s monthly executions, while self-hosting has no execution cap (it mainly depends on your server and email/WhatsApp rate limits). Practically, each candidate runs a 7-day sequence, so think in “candidates per month” rather than “messages per minute.” If you’re onboarding hundreds of applicants weekly, you’ll want to watch provider limits and consider queueing.
Often, yes, because the logic here isn’t just “send a message.” You’re generating content, splitting it into three scheduled sends, and coordinating two channels with waits and merges, which is exactly where simpler tools start to feel fragile or expensive. n8n also gives you the self-hosting option, so high volume doesn’t automatically mean a higher bill. Zapier or Make can still be fine if you only want a basic confirmation email and nothing else. If you’re unsure, Talk to an automation expert and you’ll get a straight recommendation.
Once this is live, every applicant gets a timely, consistent follow-up without you chasing the calendar. Honestly, that alone makes hiring feel calmer.
Need Help Setting This Up?
Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.
