Google Sheets + Telegram: instant resume shortlists
Your inbox fills up with resumes, and somehow the “quick review” turns into a messy, multi-day backlog. By the time you get aligned on who looks good, strong candidates have already moved on.
This resume shortlist automation hits HR managers first, but founders hiring their first team and recruiters supporting multiple roles feel the same drag. You want consistent screening, less admin work, and a shortlist your team actually trusts.
This n8n workflow logs every applicant to Google Sheets, scores resumes with an AI screening agent, then pings Telegram only when someone is worth a real look. You’ll see how it works, what you need, and what to tweak so it matches your roles.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Google Sheets + Telegram: instant resume shortlists
flowchart LR
subgraph sg0["Application form 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/form.svg' width='40' height='40' /></div><br/>Application form"]
n1@{ icon: "mdi:cog", form: "rounded", label: "Extract profile", pos: "b", h: 48 }
n2@{ icon: "mdi:brain", form: "rounded", label: "gpt4-1 model", pos: "b", h: 48 }
n3@{ icon: "mdi:cog", form: "rounded", label: "Upload to Google Drive", pos: "b", h: 48 }
n4@{ icon: "mdi:robot", form: "rounded", label: "Structured Output Parser1", pos: "b", h: 48 }
n5@{ icon: "mdi:database", form: "rounded", label: "Open_Positions", pos: "b", h: 48 }
n6@{ icon: "mdi:database", form: "rounded", label: "Update_HR_Application_System", pos: "b", h: 48 }
n7@{ icon: "mdi:robot", form: "rounded", label: "HR_RTS_Agent", pos: "b", h: 48 }
n8@{ icon: "mdi:swap-horizontal", form: "rounded", label: "If", pos: "b", h: 48 }
n9@{ icon: "mdi:database", form: "rounded", label: "Update_HR_Application_System1", 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/telegram.svg' width='40' height='40' /></div><br/>Send a text to HR Team"]
n11@{ icon: "mdi:robot", form: "rounded", label: "Dynamic Question Generator A..", pos: "b", h: 48 }
n8 --> n11
n7 --> n6
n2 -.-> n7
n2 -.-> n11
n5 -.-> n7
n5 -.-> n11
n1 --> n7
n0 --> n3
n0 --> n1
n4 -.-> n7
n6 --> n8
n9 --> n10
n11 --> n9
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 n0 trigger
class n4,n7,n11 ai
class n2 aiModel
class n8 decision
class n5,n6,n9 database
classDef customIcon fill:none,stroke:none
class n0,n10 customIcon
The Problem: Resume screening turns into a bottleneck
Resume screening feels simple until you’re doing it under pressure. One person scans PDFs, another checks the job requirements, someone else tries to keep a tracker updated, and the hiring manager wants “just the top five” before lunch. Meanwhile, candidates apply through a form, email, referrals, and random DMs, so your “source of truth” becomes a patchwork. The real cost is not only time. It’s inconsistency. Two reviewers read the same CV and come to different conclusions, then you spend another meeting arguing about gut feel instead of evidence.
It adds up fast. And it usually breaks in the same places.
- Resumes sit unread for a day or two because reviewing them requires uninterrupted focus time.
- Your tracker falls behind, so nobody trusts it and you end up re-checking candidates repeatedly.
- Shortlisting depends on whoever is available, which means criteria quietly shift from week to week.
- Hiring teams miss strong applicants because there’s no immediate “this one looks good” alert at the moment it matters.
The Solution: AI screening to Google Sheets, shortlists to Telegram
This workflow turns your application intake into a repeatable pipeline. A candidate submits a form (with their CV attached), the file is saved to Google Drive for clean record-keeping, and the resume text is extracted automatically. From there, an AI screening agent reads the resume and compares it to the role requirements stored in Google Sheets, so the evaluation is anchored to your job criteria instead of vibes. The workflow writes the candidate’s name, score, and shortlist decision into your “Applications” tracker, then checks a simple condition: shortlisted or not. If they qualify, a second AI agent generates three tailored interview questions and updates the same row. Finally, your team gets a Telegram alert so the best applicants get reviewed while they’re still fresh.
The workflow starts with a form submission and ends with an actionable Telegram message. In between, it standardizes screening against the role requirements in Google Sheets, logs every decision, and only escalates the people who pass your bar.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you get 20 applications a week for one role. Manually, you might spend about 10 minutes opening the PDF, scanning for fit, and then updating your tracker, which is roughly 3 hours of admin before you even talk to anyone. With this workflow, the “work” is basically submitting the form (candidates do that) and glancing at Telegram when a shortlist alert appears. Even if you spend 2 minutes reviewing each shortlisted profile in the sheet, you’re usually down to about 30 minutes of real effort, plus the background processing time you don’t have to sit through.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Google Sheets to store roles, applicants, and decisions.
- Google Drive for storing uploaded CV files.
- Telegram to alert the hiring team in real time.
- OpenAI API key (get it from your OpenAI platform dashboard).
Skill level: Beginner. You’ll connect accounts, paste an API key, and edit a few prompts to match your role requirements.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A candidate submits an application through your form. The n8n Form Trigger collects basics like name and email, plus a CV file upload and the selected job role.
The CV is stored and converted into readable text. Google Drive receives the uploaded file in a designated folder, then the workflow extracts the resume text so the AI can evaluate it reliably.
AI screens the resume against your job criteria. The screening agent uses your Open Roles data in Google Sheets, produces a structured score and shortlist decision, and writes that result into your Applications sheet.
Shortlisted candidates get interview questions and a Telegram alert. If the applicant qualifies, a second agent generates three role-relevant questions, updates the same Google Sheets row, and sends Telegram to your team so review happens quickly.
You can easily modify the shortlist threshold and the interview question style based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Form Trigger
Start by setting up the intake form that kicks off the workflow and captures applicant submissions.
- Add and open Candidate Intake Form to define your form fields for applicant data and file upload.
- Ensure the form is saved and copy the generated form URL for your public-facing intake page.
Step 2: Connect File Handling and Storage
When the form is submitted, the workflow branches in parallel to store files and extract applicant data.
- Confirm Candidate Intake Form outputs to both Drive File Upload and Parse Applicant Profile in parallel.
- In Drive File Upload, configure the destination Drive folder where applicant files should be saved.
- In Parse Applicant Profile, map the uploaded file field from the form to the file input for extraction.
Step 3: Set Up AI Screening and Role Matching
Configure the AI stack that reads the parsed profile, screens the applicant, and builds follow-up questions.
- Open GPT-4 Chat Model and connect it as the language model for both HR Screening Agent and Question Builder Agent.
- Verify Structured Parser is connected to HR Screening Agent as the output parser for structured screening results.
- Ensure Open Roles Sheet is connected as a tool to both HR Screening Agent and Question Builder Agent for role lookup.
- Confirm Parse Applicant Profile outputs to HR Screening Agent so the agent receives parsed data.
Step 4: Configure Evaluation and Tracking
Save screening results and determine whether to generate follow-up questions.
- In Update HR Tracker, map fields from HR Screening Agent into your HR tracking sheet.
- Set up Branch Evaluation to evaluate the screening outcome and send approved candidates to Question Builder Agent.
Step 5: Configure Follow-Up Updates and Notifications
Write follow-up actions to the tracker and notify HR.
- Configure Update HR Tracker Followup to add question sets or follow-up steps generated by Question Builder Agent.
- In Notify HR via Telegram, craft the message content and destination chat/channel for HR notifications.
Step 6: Test and Activate Your Workflow
Run a full test to validate data flow, AI outputs, and notifications before going live.
- Click Execute Workflow and submit a test entry through Candidate Intake Form.
- Verify that Drive File Upload stores the file, Parse Applicant Profile extracts data, and HR Screening Agent produces structured results.
- Confirm the sheet updates occur in both Update HR Tracker and Update HR Tracker Followup, and that Notify HR via Telegram delivers the alert.
- When everything looks correct, toggle the workflow to Active for production use.
Common Gotchas
- Google Sheets credentials can expire or need specific permissions. If things break, check the connected Google account access in n8n credentials first, then confirm the sheet is shared with that account.
- If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.
Frequently Asked Questions
About 15 minutes if your Google and Telegram accounts are ready.
No. You will mostly connect accounts and edit the screening prompts. If you can manage Google Sheets, you can handle this.
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, which are usually a few cents per resume depending on length.
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.
Yes, and you should. You can update the role requirements in the “Open Roles” Google Sheet, then adjust the screening agent prompt to reflect what “qualified” means for each role. Common customizations include setting a higher score threshold for senior roles, adding disqualifiers (like missing a required certification), and changing the interview question style to match your interview loop.
Most of the time it’s a bot token issue or the bot hasn’t been added to the correct chat. Regenerate the Telegram bot token if needed, confirm the chat ID is correct, and make sure the bot has permission to post messages in that group. If it works in tests but fails under load, rate limits can also show up when you shortlist many candidates at once.
A lot.
Often, yes, especially when you want AI screening plus structured outputs. n8n handles branching logic and multi-step AI flows cleanly, and self-hosting means you can run high volume without paying per task. Zapier and Make can be simpler for basic “form to sheet” syncing, but they get awkward when you need two AI agents, a parser, conditional shortlisting, and record updates in the same run. Cost is another factor: frequent runs can get expensive fast on per-task pricing. If you want a quick recommendation based on your volume and tools, Talk to an automation expert.
Once this is running, your team stops babysitting the tracker and starts reviewing the right people at the right time. 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.
