Telegram to Google Sheets, job briefs sorted fast
Copying a job brief into a doc, guessing keywords, searching, opening ten tabs, then trying to remember what looked promising. It’s not hard work. It’s just endless work.
Telegram Sheets automation helps when you’re moving fast and your “system” is basically screenshots and browser history. Recruiters feel it first, but freelancers pitching projects and ops folks supporting hiring get stuck in the same loop. You want a shortlist you can trust, without the manual scavenger hunt.
This workflow takes a pasted job brief, extracts five useful search terms, finds relevant n8n templates, then saves the best matches into a Google Sheet with clean URLs. You’ll see exactly how it works and what you need to run it.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Telegram to Google Sheets, job briefs sorted fast
flowchart LR
subgraph sg0["Incoming Chat Flow"]
direction LR
n0@{ icon: "mdi:play-circle", form: "rounded", label: "Incoming Chat Trigger", pos: "b", h: 48 }
n1@{ icon: "mdi:robot", form: "rounded", label: "Keyword Extraction Agent", pos: "b", h: 48 }
n2@{ icon: "mdi:brain", form: "rounded", label: "OpenAI Dialogue Model", 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/>Decode Keyword JSON"]
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/>Build Keyword Array"]
n5@{ icon: "mdi:swap-vertical", form: "rounded", label: "Iterate Keyword Batch", pos: "b", h: 48 }
n6["<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/>Template Search Request"]
n7@{ icon: "mdi:swap-vertical", form: "rounded", label: "Separate Results", pos: "b", h: 48 }
n8@{ icon: "mdi:database", form: "rounded", label: "Append Sheet Row", pos: "b", h: 48 }
n9@{ icon: "mdi:database", form: "rounded", label: "Retrieve Sheet Rows", pos: "b", h: 48 }
n10@{ icon: "mdi:swap-vertical", form: "rounded", label: "Assign URL Field", pos: "b", h: 48 }
n11@{ icon: "mdi:database", form: "rounded", label: "Modify Sheet Row", pos: "b", h: 48 }
n1 --> n3
n7 --> n8
n10 --> n11
n3 --> n4
n5 --> n7
n5 --> n6
n6 --> n5
n2 -.-> n1
n4 --> n5
n9 --> n10
n8 --> n9
n0 --> n1
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 n1 ai
class n2 aiModel
class n8,n9,n11 database
class n6 api
class n3,n4 code
classDef customIcon fill:none,stroke:none
class n3,n4,n6 customIcon
The Problem: Turning messy job briefs into a clear shortlist
Job briefs are rarely written for search. They’re written by stressed hiring managers, copied from old roles, and loaded with vague phrases like “must be a self-starter.” So you end up translating that brief into keywords yourself, then searching template libraries in a way that’s half intuition, half luck. Do it once and it’s annoying. Do it five times a day and it becomes a quiet time leak that also kills your focus. Worse, you can’t easily show your work later because nothing is saved in one place.
It adds up fast. And the friction compounds the moment you need consistency across a team.
- Most people spend about 20 minutes per brief just trying different search terms and re-opening results they already saw.
- Good matches get lost because they live in tabs, DMs, or someone’s memory.
- Keyword quality is inconsistent, which means your shortlist is inconsistent too.
- Without a structured sheet, you can’t track what you recommended, clicked, or used later.
The Solution: Paste a brief, get template matches in Sheets
This n8n workflow starts where you already work: a simple Telegram message containing a job brief. An AI agent reads the text and pulls out exactly five concise search keywords, returned in structured JSON so the rest of the workflow stays predictable. Then n8n searches the n8n template library for each keyword via HTTP request, collects the results, and writes them into a Google Sheet as individual rows. Finally, it builds a canonical public URL for each template from the template ID and slug, so your sheet isn’t just “notes.” It’s clickable, review-ready output you can share.
The workflow begins with a Telegram chat trigger. From there, OpenAI generates five search terms and n8n queries the templates API for each term. Results are appended to Google Sheets, then updated with a clean URL field so everything is easy to review later.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you review 5 job briefs in a busy day. Manually, you might spend about 20 minutes per brief searching, opening results, and copying links, which is roughly 100 minutes total. With this workflow, you paste each brief into Telegram (about 1 minute), then wait a couple minutes for searches and the Google Sheet updates. You get back about an hour and a half, and your shortlist is already organized with URLs.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Telegram to paste in job briefs quickly
- Google Sheets to store and review the shortlist
- OpenAI API key (get it from the OpenAI API dashboard)
Skill level: Beginner. You’ll connect accounts, create a sheet with the right columns, and paste a few config values.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A Telegram message triggers the run. You paste a job brief into Telegram, and the Incoming Chat Trigger starts the workflow immediately.
The brief is turned into five search terms. The Keyword Extraction Agent uses the OpenAI Chat Model to return five concise keywords as JSON, which keeps the output consistent even when the brief is messy.
n8n searches the template library for each keyword. A small bit of code builds an array, then Split in Batches iterates keyword-by-keyword and calls the templates API using an HTTP request. Results are split into individual items so they can be saved cleanly.
Google Sheets becomes your shortlist. Each matched template is appended as a new row (Template ID, Name, User, Description), then the workflow retrieves the row and assigns a canonical URL field before updating it.
You can easily modify the keyword rules to focus on certain categories (like CRM, AI, or lead gen) based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Chat Trigger
Set up the incoming chat trigger that starts the workflow when a chat message arrives.
- Add the Incoming Chat Trigger node to your workflow.
- Leave Options empty unless you need custom chat settings (the workflow uses the default trigger behavior).
- Connect Incoming Chat Trigger to Keyword Extraction Agent.
Step 2: Connect Google Sheets
Connect and configure Google Sheets to store and update template results.
- Open Append Sheet Row and select the target spreadsheet by setting Document ID to
[YOUR_ID]and Sheet Name togid=0. - Set Operation to
appendand map columns with expressions: id →{{ $json.id }}, Name →{{ $json.name }}, User →{{ $json.user }}, Description →{{ $json.description }}. - Open Retrieve Sheet Rows and set the same Document ID
[YOUR_ID]and Sheet Namegid=0. Configure filters with lookupColumnid+ lookupValue{{ $json.id }}and lookupColumnName+ lookupValue{{ $json.Name }}. - Open Modify Sheet Row, set Operation to
update, and map row_number to{{ $('Retrieve Sheet Rows').item.json.row_number }}and id to{{ $json.URL }}. - Credential Required: Connect your googleSheetsOAuth2Api credentials in Append Sheet Row, Retrieve Sheet Rows, and Modify Sheet Row.
Step 3: Set Up the AI Keyword Extraction
Configure the agent and language model to extract five search keywords from the incoming chat message.
- Open Keyword Extraction Agent and set System Message to the provided prompt (ensure it outputs JSON keys
keyword1throughkeyword5). - Open OpenAI Dialogue Model and select Model
gpt-4.1-mini. - Connect OpenAI Dialogue Model to Keyword Extraction Agent as the language model.
- Credential Required: Connect your openAiApi credentials in OpenAI Dialogue Model. This model powers Keyword Extraction Agent.
Step 4: Configure Processing, Search, and URL Enrichment
Parse the AI output, build keyword batches, query the template API, and update the sheet with generated URLs.
- In Decode Keyword JSON, set JavaScript Code to
const items = $input.all(); const updatedItems = items.map((item) => { const output = JSON.parse(item?.json?.output); return output; }); return updatedItems;. - In Build Keyword Array, set JavaScript Code to
const input = $json; return [ { json: { keyword: input.keyword1 } }, { json: { keyword: input.keyword2 } }, { json: { keyword: input.keyword3 } }, { json: { keyword: input.keyword4 } }, { json: { keyword: input.keyword5 } }, ];. - Connect Build Keyword Array → Iterate Keyword Batch to loop through keywords in batches.
- Configure Template Search Request with URL
https://api.n8n.io/templates/search, enable Send Query and Send Headers, and set the query parameter name to=searchwith value{{ $json.keyword }}. - Connect Iterate Keyword Batch to Template Search Request (loop) and to Separate Results (split the results array).
- In Separate Results, set Field to Split Out to
workflows, then connect to Append Sheet Row. - In Assign URL Field, set URL to
=https://n8n.io/workflows/{{$json.id}}-{{$json.Name.toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/(^-|-$)/g, "")}}, then connect to Modify Sheet Row.
Step 5: Test and Activate Your Workflow
Run a manual test and then activate the workflow for production use.
- Click Execute Workflow and send a sample chat message through Incoming Chat Trigger.
- Verify that Keyword Extraction Agent outputs JSON with five keywords and that Decode Keyword JSON produces clean fields.
- Confirm Append Sheet Row adds rows with id, Name, User, and Description, and Modify Sheet Row updates the URL field using the row number from Retrieve Sheet Rows.
- When satisfied, toggle the workflow to Active to start processing incoming chat messages automatically.
Common Gotchas
- Google Sheets credentials can expire or need specific permissions. If things break, check the Google connection in n8n’s Credentials section first.
- 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 30 minutes if your accounts are already connected.
No. You’ll mostly paste config values and connect Telegram, OpenAI, and Google Sheets.
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 usage, which is usually only a few cents per brief.
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, but you’ll swap the Google Sheets nodes (Append Sheet Row, Retrieve Sheet Rows, Modify Sheet Row) for Airtable or Notion equivalents and keep the same fields. Common tweaks include changing the system prompt to extract different keywords, adding a filter to only keep certain template categories, and writing results to a different table per role type.
Usually it’s expired OAuth access or the wrong Google account connected. Reconnect Google Sheets in n8n Credentials, then confirm the sheet name and document ID match what you set in the Config node. If the sheet is shared from another account, make sure the connected account has edit access. Also check if your organization blocks third-party app access, because that can look like a “random” failure.
Plenty for a small team: most setups can handle dozens per day without any drama, and self-hosted n8n can scale based on your server.
Often, yes, because this flow benefits from loops (searching once per keyword), data shaping, and updating rows after the fact. n8n handles that kind of logic cleanly, and you can self-host if you want to avoid execution limits. Zapier and Make can still do it, but you may end up paying more as volume grows or simplifying the workflow in ways that reduce match quality. If your priority is “set it up in 10 minutes and forget it,” they can feel easier at first. Talk to an automation expert if you want help choosing.
Once this is running, job briefs stop being a time sink and start becoming a repeatable input. The workflow handles the busywork so you can focus on judgment calls.
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.
