January 22, 2026

LinkedIn to Telegram, only high fit job alerts

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

You open LinkedIn for “a quick check,” and suddenly you’ve read 40 job posts that were never a match. Wrong seniority. Wrong language. “Hybrid” that actually means a two-hour commute. It’s exhausting.

This LinkedIn Telegram alerts automation hits job seekers first, obviously. But recruiters running targeted searches and career coaches helping clients feel the same drag. The outcome is simple: fewer distractions, and a short list of roles that actually fit.

Below you’ll see how the workflow finds LinkedIn roles, filters them with your rules (language, level, commute), scores them against your CV, and then pings you in Telegram only when it’s worth your attention.

How This Automation Works

The full n8n workflow, from trigger to final output:

n8n Workflow Template: LinkedIn to Telegram, only high fit job alerts

Click to explore

flowchart LR

    subgraph sg0["Schedule Flow"]
        direction LR
        n0@{ icon: "mdi:swap-vertical", form: "rounded", label: "Config", pos: "b", h: 48 }
        n1["<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/>Scrape LinkenIn Jobs"]
        n2@{ icon: "mdi:cog", form: "rounded", label: "Done!", pos: "b", h: 48 }
        n3@{ icon: "mdi:robot", form: "rounded", label: "Structured Output Parser", pos: "b", h: 48 }
        n4@{ icon: "mdi:swap-horizontal", form: "rounded", label: "If Seniority Match", pos: "b", h: 48 }
        n5@{ icon: "mdi:robot", form: "rounded", label: "Deconstruct Job Data", pos: "b", h: 48 }
        n6@{ icon: "mdi:swap-horizontal", form: "rounded", label: "If Language Match", pos: "b", h: 48 }
        n7@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini", pos: "b", h: 48 }
        n8@{ icon: "mdi:swap-horizontal", form: "rounded", label: "If is not Remote", pos: "b", h: 48 }
        n9["<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/>Get Commute Time"]
        n10@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Is Commute Acceptable", pos: "b", h: 48 }
        n11@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini Deep Analysis", pos: "b", h: 48 }
        n12@{ icon: "mdi:robot", form: "rounded", label: "Structured Output Parser Dee..", pos: "b", h: 48 }
        n13["<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/supabase.svg' width='40' height='40' /></div><br/>Save Data"]
        n14@{ icon: "mdi:swap-horizontal", form: "rounded", label: "If Has High Match Score", pos: "b", h: 48 }
        n15@{ icon: "mdi:robot", form: "rounded", label: "AI Deep Analysis", pos: "b", h: 48 }
        n16@{ icon: "mdi:swap-vertical", form: "rounded", label: "Items Loop", pos: "b", h: 48 }
        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/telegram.svg' width='40' height='40' /></div><br/>Send a Notification"]
        n18@{ icon: "mdi:play-circle", form: "rounded", label: "Schedule Trigger", pos: "b", h: 48 }
        n19@{ icon: "mdi:play-circle", form: "rounded", label: "Manual Executing", pos: "b", h: 48 }
        n20@{ icon: "mdi:cog", form: "rounded", label: "To The Next", pos: "b", h: 48 }
        n0 --> n1
        n13 --> n14
        n16 --> n2
        n16 --> n5
        n20 --> n16
        n7 -.-> n5
        n15 --> n13
        n9 --> n10
        n8 --> n9
        n8 --> n15
        n19 --> n0
        n18 --> n0
        n6 --> n8
        n6 --> n16
        n4 --> n6
        n4 --> n16
        n17 --> n20
        n5 --> n4
        n1 --> n16
        n10 --> n15
        n10 --> n16
        n14 --> n17
        n14 --> n20
        n3 -.-> n5
        n11 -.-> n15
        n12 -.-> n15
    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 n18,n19 trigger
    class n3,n5,n12,n15 ai
    class n7,n11 aiModel
    class n4,n6,n8,n10,n14 decision
    class n1,n9 api
    classDef customIcon fill:none,stroke:none
    class n1,n9,n13,n17 customIcon

The Problem: Job Search Busywork Hides the Good Roles

Most job searches don’t fail because you’re unqualified. They fail because the funnel is noisy, and you burn your best energy at the top. You end up reading full descriptions just to discover the role is in German, the level is “Senior” dressed up as “Associate,” or the office is technically commutable if you enjoy losing your mornings. Then there’s the worst part: you still have to decide if you match, which usually means cross-checking your CV line-by-line while your motivation quietly leaves the room.

It adds up fast. Here’s where it breaks down in real life.

You spend about 1–2 hours a day scanning listings, and maybe 10 minutes of that was useful.
Hybrid and on-site roles look fine until you map the commute, which you usually do too late.
“Requirements” are written to be vague, so you second-guess yourself and hesitate on good roles.
You lose track of what you’ve reviewed, which leads to duplicates, missed follow-ups, and messy notes.

The Solution: An AI Filter That Only Sends High-Fit Roles

This n8n workflow acts like a personal screening assistant for LinkedIn roles. It runs on a schedule (or manually), pulls new job listings from LinkedIn via an HTTP request (using an Apify scrape behind the scenes), and then reads each full job description with AI. First, it extracts the basics that usually waste your time: language, seniority level, and whether the role is remote, hybrid, or on-site. Next, it applies your rules, so mismatches get discarded early. For the jobs that survive, it calculates commute time from your home location for hybrid/on-site roles, then does a deeper CV-to-job comparison to generate a match score and a clean summary you can act on.

The workflow starts with your keywords and preferences in one “Config” area. AI triage filters out obvious mismatches, the commute check removes “technically possible” roles, and a deeper AI pass scores fit against your CV. Finally, everything is logged, while only high-score roles trigger a Telegram alert.

What You Get: Automation vs. Results

What This Workflow Automates

Results You’ll Get

Scrapes LinkedIn listings for the keywords you choose on a schedule.
Reads each job description and extracts language, seniority, and work model.
Checks commute time for hybrid or on-site roles using your home location.
Compares the job requirements against your pasted CV and assigns a match score.

Get back about 5–7 hours per week you’d normally spend on low-fit scanning.
See fewer “maybe” roles, so you apply faster when something is truly right.
Stop getting tricked by hybrid listings with painful commutes.
Keep a searchable log of qualified roles for follow-ups and tracking.
Open Telegram to decisions, not distractions.

Example: What This Looks Like

Say you scrape 50 LinkedIn jobs each morning from 3 keywords. Manually, even a quick skim is maybe 2 minutes per job, plus another 10 minutes each for the handful you open fully, which lands around 2 hours on an average day. With this workflow, you spend about 10 minutes once setting your CV and filters, then the daily run happens in the background. You only review the 3–7 Telegram alerts that clear your match score and commute rules, which is usually 10–15 minutes total.

What You’ll Need

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Apify to scrape LinkedIn job listings
Google Cloud (Gemini + Maps) for AI reading and commute time
Supabase to store every qualified job record
Telegram to receive high-fit alerts
Apify API Token (get it from your Apify account settings)

Skill level: Intermediate. You’ll paste your CV, set filters, and connect a few APIs with keys.

Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).

How It Works

A scheduled run (or manual start) kicks it off. You can run it daily, twice a day, or whenever new roles tend to appear in your niche. The workflow loads your saved preferences from the setup variables node.

LinkedIn listings get collected, then handled one-by-one. An HTTP request pulls a batch of roles (via Apify), and n8n iterates through them in manageable chunks so the workflow stays stable even when you scrape more jobs.

AI triage filters out obvious mismatches. A Gemini model reads the description and extracts structured fields like language, work model, and seniority. Then a few simple checks remove anything that doesn’t match your target language and experience level.

Commute and CV fit decide what’s worth your time. If the role is hybrid or on-site, the workflow calls the Google Maps API to calculate commute duration from your home location, then drops anything over your limit. For the remaining roles, a deeper AI analysis compares job requirements to your CV text and generates a match score plus a practical summary.

Everything gets logged, and only the best roles ping you. Qualified job records are saved to Supabase for tracking. If the match score clears your threshold, you get a detailed Telegram alert and can move quickly.

You can easily modify the match score threshold to be stricter (or looser) based on your needs. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Scheduled Run Trigger and Manual Start Trigger

Set up the workflow entry points so you can run the job screening either on a schedule or manually for testing.

Open Scheduled Run Trigger and set the rule interval to trigger at 9 (hour) to match the configured schedule.
Keep Manual Start Trigger as-is so you can execute the workflow on demand during setup and debugging.
Confirm both Scheduled Run Trigger and Manual Start Trigger connect to Setup Variables.

Step 2: Connect LinkedIn Listings

Define your search inputs and connect the Apify-based LinkedIn data source.

In Setup Variables, set MyCV to YOUR FULL TEXT CV HERE!.
Set JobKeywords to AI Integration, ExperienceLevel to mid_senior, and JobsToScrape to 20.
Set HomeLocation to Breda, Netherlands, MaxCommuteMinutes to 75, and TargetLanguage to English.
Set Under10Applicants to false and ActorId to [YOUR_ID].
In Fetch LinkedIn Listings, set URL to =https://api.apify.com/v2/acts/{{ $json.ActorId }}/run-sync-get-dataset-items and Method to POST.
Set JSON Body to ={"date_posted":"day","experienceLevel": {{ $json.ExperienceLevel.toJsonString() }},"keywords": {{ $json.JobKeywords.toJsonString() }},"limit": {{ $json.JobsToScrape }},"under_10_applicants": {{ $json.Under10Applicants.toJsonString() }},"sort":"relevant","location":"91000000","page_number": 1}.
Credential Required: Connect your httpBearerAuth credentials in Fetch LinkedIn Listings.

⚠️ Common Pitfall: Replace [YOUR_ID] in Setup Variables before testing, or the Apify request in Fetch LinkedIn Listings will fail.

Step 3: Set Up AI Screening and Filters

Configure the loop over listings, AI language checks, and filtering logic before deep resume matching.

Ensure Fetch LinkedIn Listings connects to Iterate Listings to loop over each job.
In Analyze Job Details, keep the prompt text as-is and confirm hasOutputParser is enabled.
Structured Parser is connected as the output parser for Analyze Job Details — ensure credentials are added to Gemini Chat Model (not the parser).
Credential Required: Connect your googlePalmApi credentials in Gemini Chat Model.
In Seniority Check, confirm the condition uses ={{ $json.output.confirmed_seniority }} equals ={{ $('Setup Variables').item.json.ExperienceLevel }}.
In Language Filter, confirm the boolean expression uses ={{ $('Setup Variables').item.json.TargetLanguage.toLowerCase().split(', ').includes($('Analyze Job Details').item.json.output.jobLanguage.toLowerCase()) }}.
In Remote Status Check, confirm the condition checks ={{ $('Iterate Listings').first().json.work_type.toLowerCase() }} not equals remote.
In Retrieve Commute Duration, set URL to =https://maps.googleapis.com/maps/api/directions/json and query parameters: origin ={{ $('Setup Variables').item.json.HomeLocation }}, destination ={{ $('Iterate Listings').first().json.location }}.
Credential Required: Connect your httpQueryAuth credentials in Retrieve Commute Duration.
In Commute Threshold Check, verify ={{ $json.routes[0].legs[0].duration.value }} is less than or equal to ={{ $('Setup Variables').item.json.MaxCommuteMinutes * 60 }}.
Confirm the loop back via Next Item Hop → Iterate Listings to continue processing remaining jobs.

Tip: If commute checks fail unexpectedly, validate that the job location from Iterate Listings is a geocodable string for Google Directions.

Step 4: Configure Output and Notifications

Set up deep resume matching, store results, and notify when a high-match job is found.

In Resume Match Analysis, keep the prompt text and system message as-is and ensure hasOutputParser is enabled.
Deep Output Parser is connected as the output parser for Resume Match Analysis — ensure credentials are added to Gemini Deep Model (not the parser).
Credential Required: Connect your googlePalmApi credentials in Gemini Deep Model.
In Store Records, set Table to job_tracker and keep field mappings such as jobTitle ={{ $('Iterate Listings').first().json.job_title }} and matchScore ={{ $json.output.match_score }}.
Credential Required: Connect your supabaseApi credentials in Store Records.
In High Score Gate, confirm the condition is ={{ $('Resume Match Analysis').item.json.output.match_score }} greater than or equal to 8.
In Send Telegram Alert, set Chat ID to [YOUR_ID] and keep the HTML-formatted Text expression as provided.
Credential Required: Connect your telegramApi credentials in Send Telegram Alert.

⚠️ Common Pitfall: Replace [YOUR_ID] in Send Telegram Alert or messages will not deliver.

Step 5: Test and Activate Your Workflow

Validate each stage and then enable scheduled execution.

Click Execute Workflow and use Manual Start Trigger to run a test cycle.
Verify jobs are fetched in Fetch LinkedIn Listings and looped by Iterate Listings.
Confirm AI outputs appear in Analyze Job Details and Resume Match Analysis, and that Store Records writes to the job_tracker table.
Check that Send Telegram Alert posts only when High Score Gate passes.
When satisfied, activate the workflow so Scheduled Run Trigger runs automatically.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Common Gotchas

Google Cloud credentials can expire or be missing API access. If commute checks fail, look in your Google Cloud Console to confirm the Maps API is enabled and billing is active.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Apify runs can silently return fewer results if your actor settings, token permissions, or LinkedIn scraping limits change. Check the Apify run logs first before blaming n8n.

Frequently Asked Questions

How long does it take to set up this LinkedIn Telegram alerts automation?

About 45 minutes if you already have the API keys.

Do I need coding skills to automate LinkedIn Telegram alerts?

No. You’ll connect services, paste keys, and adjust plain-English settings in the Config node.

Is n8n free to use for this LinkedIn Telegram alerts workflow?

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 Google Cloud usage for Gemini and Maps, plus Apify runs and your Supabase plan.

Where can I host n8n to run this automation?

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.

Can I customize this LinkedIn Telegram alerts workflow for different job boards instead of LinkedIn?

Yes, but plan to swap the data source. Replace the “Fetch LinkedIn Listings” HTTP Request step with a different Apify actor, an RSS feed reader, or another job-board API, then keep the same AI triage and scoring steps. Common customizations include changing the keyword list, tightening the commute limit, and raising the match-score gate so you only see near-perfect fits.

Why is my Telegram connection failing in this workflow?

Most of the time it’s the bot token or chat ID being wrong, or the bot not being added to the target channel. Regenerate the Telegram Bot Token if needed, then confirm the chat ID matches the exact destination where you expect alerts. Also check if your Telegram node is pointed at the right credential in n8n. If your workflow runs but sends nothing, make sure jobs are actually passing the High Score Gate.

How many jobs can this LinkedIn Telegram alerts automation handle?

Practically, it depends on your scrape size and API limits. On n8n Cloud Starter you can run a healthy number of executions per month for a personal search, and Pro handles more volume. If you self-host, there’s no hard execution cap, but your server resources and the Apify/Google rate limits become the bottleneck. For most personal setups, scraping 50–200 jobs per run is comfortable.

Is this LinkedIn Telegram alerts automation better than using Zapier or Make?

Often, yes. This workflow uses multiple decision points (language, seniority, remote status, commute, match score) and it loops through batches, which is where n8n tends to be more flexible and cost-effective. Self-hosting is also a big deal if you want to run frequent scans without worrying about task pricing. Zapier or Make can be fine for a simple “new item → send message” setup, but they get awkward when you add deep AI analysis and filtering logic. Talk to an automation expert if you want help choosing.

Once this is running, your “job search time” stops being endless scrolling and starts being quick decisions. Honestly, that’s the whole win.

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.

Lisa Granqvist

Workflow Automation Expert

Expert in workflow automation and no-code tools.

{
"id": "",
"name": "Automated Job Screening Pipeline",
"versionId": "",
"meta": {
"instanceId": "558f481744ac274d989dd6b20ae6d6a6baad48059b62e527face5d26a43ece9e",
"templateCredsSetupCompleted": null
},
"nodes": [
{
"id": "flowpast-topbar-8539",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
20
],
"parameters": {
"color": 7,
"width": 1705,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "0d1ee8d1-e28c-47e6-9d60-185de0d0dcc2",
"name": "Setup Variables",
"type": "n8n-nodes-base.set",
"position": [
1280,
310
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "171ff4c5-b238-4b4c-8a27-a5a9564bd673",
"name": "MyCV",
"type": "string",
"value": "YOUR FULL TEXT CV HERE!"
},
{
"id": "2be3ae0b-02f0-40c7-955f-e71b7a2881bc",
"name": "JobKeywords",
"type": "string",
"value": "AI Integration"
},
{
"id": "b062eed9-9fbd-4f45-9117-0ccd4b5d53db",
"name": "ExperienceLevel",
"type": "string",
"value": "mid_senior"
},
{
"id": "5808ab43-3551-42a0-b677-535b29bebf6c",
"name": "JobsToScrape",
"type": "number",
"value": 20
},
{
"id": "9076e2c5-2e23-41f5-bb73-04ab4534b960",
"name": "HomeLocation",
"type": "string",
"value": "Breda, Netherlands"
},
{
"id": "12b91df8-f52d-41b8-b18d-5d378942281f",
"name": "MaxCommuteMinutes",
"type": "number",
"value": 75
},
{
"id": "5d06b164-8c25-4e3d-8739-1900d9a4c7db",
"name": "TargetLanguage",
"type": "string",
"value": "English"
},
{
"id": "934fbe29-f5f0-4ca1-97ad-4e2c28e46b92",
"name": "Under10Applicants",
"type": "string",
"value": false
},
{
"id": "3f789658-2cfd-4c3e-9d7c-749d9e79fa65",
"name": "ActorId",
"type": "string",
"value": "[YOUR_ID]"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "671cf8fb-b319-4e82-99ae-181f89aa936b",
"name": "Fetch LinkedIn Listings",
"type": "n8n-nodes-base.httpRequest",
"position": [
1045,
295
],
"parameters": {
"url": "=https://api.apify.com/v2/acts/{{ $json.ActorId }}/run-sync-get-dataset-items",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"date_posted\": \"day\",\n  \"experienceLevel\": {{ $json.ExperienceLevel.toJsonString() }},\n  \"keywords\": {{ $json.JobKeywords.toJsonString() }},\n  \"limit\": {{ $json.JobsToScrape }},\n  \"under_10_applicants\": {{ $json.Under10Applicants.toJsonString() }},\n  \"sort\": \"relevant\",\n  \"location\": \"91000000\",\n  \"page_number\": 1\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpBearerAuth"
},
"credentials": {
"httpBearerAuth": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "47daec05-16be-4502-a183-a444b534bada",
"name": "Complete Step",
"type": "n8n-nodes-base.noOp",
"position": [
820,
120
],
"parameters": [],
"typeVersion": 1
},
{
"id": "f09488e4-11b0-456c-92f2-e6804b64ea75",
"name": "Structured Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
820,
170
],
"parameters": {
"jsonSchemaExample": "{\n\"jobLanguage\": \"English\",\n\"confirmed_seniority\": \"mid_senior\",\n\"is_match\": true\n}"
},
"typeVersion": 1.3
},
{
"id": "62f689ec-b638-4feb-8ada-74ff30cddf13",
"name": "Seniority Check",
"type": "n8n-nodes-base.if",
"position": [
340,
290
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "d1f7b9b9-4fd1-44d2-b799-5fae8bcee7be",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.confirmed_seniority }}",
"rightValue": "={{ $('Setup Variables').item.json.ExperienceLevel }}"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "3ec3aea3-2639-4afb-a261-f81eaf0c13af",
"name": "Analyze Job Details",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
570,
310
],
"parameters": {
"text": "=You are an expert HR data analyst. Your task is to validate the seniority level of a job posting based on its full description.\n\nThe job was originally tagged with the seniority level: \"{{ $('Setup Variables').item.json.ExperienceLevel }}\"\n\nAnalyze the full job description below and determine if this tag is accurate.\n\nReturn ONLY a valid JSON object with these fields:\n- \"jobLanguage\": The primary language of the text.\n- \"confirmed_seniority\": The most accurate seniority level based on your analysis of the text. You MUST choose one from: [\"internship\", \"entry\", \"associate\", \"mid_senior\", \"director\", \"executive\"].\n- \"is_match\": A boolean (true/false) indicating if your confirmed_seniority matches the original tag.\n\nJob Description:\n\"\"\"\n{{ $('Iterate Listings').first().json.description }}\n\"\"\"",
"options": [],
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2.2
},
{
"id": "78600425-b859-4c2b-b416-669bd7f6f4ce",
"name": "Language Filter",
"type": "n8n-nodes-base.if",
"position": [
120,
310
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "09fadd6c-b339-4173-84f4-aa0b50e3706c",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $('Setup Variables').item.json.TargetLanguage.toLowerCase().split(', ').includes($('Analyze Job Details').item.json.output.jobLanguage.toLowerCase()) }}",
"rightValue": "={{ $json.output.jobLanguage.toLowerCase() }}"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "1c49665e-3444-4528-85e2-5fa2f6f1547a",
"name": "Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
600,
180
],
"parameters": {
"options": []
},
"credentials": {
"googlePalmApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "fd7deb25-14f0-42dc-bb6f-c02a5dcd9314",
"name": "Remote Status Check",
"type": "n8n-nodes-base.if",
"position": [
0,
300
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "95ad2f86-418a-4e1d-99df-75ef6037b072",
"operator": {
"type": "string",
"operation": "notEquals"
},
"leftValue": "={{ $('Iterate Listings').first().json.work_type.toLowerCase() }}",
"rightValue": "remote"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "9500741a-7fff-41ec-ba2c-3d3690b3e779",
"name": "Retrieve Commute Duration",
"type": "n8n-nodes-base.httpRequest",
"position": [
140,
530
],
"parameters": {
"url": "=https://maps.googleapis.com/maps/api/directions/json",
"options": [],
"sendQuery": true,
"authentication": "genericCredentialType",
"genericAuthType": "httpQueryAuth",
"queryParameters": {
"parameters": [
{
"name": "origin",
"value": "={{ $('Setup Variables').item.json.HomeLocation }}"
},
{
"name": "destination",
"value": "={{ $('Iterate Listings').first().json.location }}"
}
]
}
},
"credentials": {
"httpQueryAuth": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "d8b75d80-fbd0-4a4a-b4ac-35843bbc5e48",
"name": "Commute Threshold Check",
"type": "n8n-nodes-base.if",
"position": [
370,
550
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "6717790e-4c69-434c-afcc-d33cbe362789",
"operator": {
"type": "number",
"operation": "lte"
},
"leftValue": "={{ $json.routes[0].legs[0].duration.value }}",
"rightValue": "={{ $('Setup Variables').item.json.MaxCommuteMinutes * 60 }}"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "c2b71945-4bf2-48b4-be34-104bbf7e8208",
"name": "Gemini Deep Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
840,
640
],
"parameters": {
"options": []
},
"credentials": {
"googlePalmApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "a09b3dc1-a6d2-402d-be2e-1dcd2c7d05a1",
"name": "Deep Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1070,
640
],
"parameters": {
"jsonSchemaExample": "{\n  \"summary\": \"A 2-bullet point summary.\",\n  \"key_skills\": [\"skill1\",\"skill2\"],\n  \"match_score\": 5,\n  \"salaryInfo\": \"The extracted salary range\",\n  \"reasoning\": \"A one-sentence explanation for the score.\"\n}"
},
"typeVersion": 1.3
},
{
"id": "b114ccb2-6d92-4e70-bd6b-dbf96379974b",
"name": "Store Records",
"type": "n8n-nodes-base.supabase",
"position": [
820,
510
],
"parameters": {
"tableId": "job_tracker",
"fieldsUi": {
"fieldValues": [
{
"fieldId": "jobTitle",
"fieldValue": "={{ $('Iterate Listings').first().json.job_title }}"
},
{
"fieldId": "companyName",
"fieldValue": "={{ $('Iterate Listings').first().json.company }}"
},
{
"fieldId": "matchScore",
"fieldValue": "={{ $json.output.match_score }}"
},
{
"fieldId": "aiSummary",
"fieldValue": "={{ $json.output.summary }}"
},
{
"fieldId": "jobURL",
"fieldValue": "={{ $('Iterate Listings').first().json.job_url }}"
},
{
"fieldId": "salaryInfo",
"fieldValue": "={{ $json.output.salaryInfo }}"
},
{
"fieldId": "aiReasoning",
"fieldValue": "={{ $json.output.reasoning }}"
},
{
"fieldId": "applyURL",
"fieldValue": "={{ $('Iterate Listings').first().json.apply_url }}"
}
]
}
},
"credentials": {
"supabaseApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "7f9b8050-305b-4bf0-a587-3816d7d11723",
"name": "High Score Gate",
"type": "n8n-nodes-base.if",
"position": [
1045,
530
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "64d17e00-bada-41e9-918c-f507a1e59df9",
"operator": {
"type": "number",
"operation": "gte"
},
"leftValue": "={{ $('Resume Match Analysis').item.json.output.match_score }}",
"rightValue": 8
}
]
}
},
"typeVersion": 2.2
},
{
"id": "96b8e300-cb29-4ded-ad55-8b6c4cedacae",
"name": "Resume Match Analysis",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
600,
530
],
"parameters": {
"text": "=Here is the candidate's resume and the job description. Please perform your analysis.\n---\n**Candidate's Resume:**\n\"\"\"\n{{ $('Setup Variables').first().json.MyCV }}\n\"\"\"\n---\n**Job Description:**\n\"\"\"\n{{ $('Iterate Listings').first().json.description }}\n\"\"\"",
"options": {
"systemMessage": "=You are an expert career coach and HR specialist. Your task is to analyze a candidate's resume against a job description and provide a detailed, structured analysis.\n\nReturn ONLY a valid JSON object with the following structure:\n{\n  \"summary\": \"A 2-bullet point summary of the role's main responsibilities.\",\n  \"key_skills\": [\"An array of the top 5 most important skills required for this job.\"],\n  \"match_score\": \"An integer from 1 to 10 of how well the resume matches the job requirements.\",\n  \"salaryInfo\": \"The extracted salary range or the string 'Not specified' if no salary is mentioned.\",\n  \"reasoning\": \"A one-sentence explanation for the score, highlighting a key strength or a potential gap in the resume.\"\n}"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2.2
},
{
"id": "ad6f8535-342b-4db8-b0d9-9b761c56ed62",
"name": "Iterate Listings",
"type": "n8n-nodes-base.splitInBatches",
"position": [
795,
320
],
"parameters": {
"options": []
},
"typeVersion": 3
},
{
"id": "b6beecb9-3cee-4647-9995-942cedc77b42",
"name": "Send Telegram Alert",
"type": "n8n-nodes-base.telegram",
"position": [
1265,
515
],
"webhookId": "57ac8c41-a3bc-4b4e-8e22-adab496b2df0",
"parameters": {
"text": "=\ud83d\udd25 <b>High-Match Job Found! ({{ $('Resume Match Analysis').item.json.output.match_score }}/10)</b>\n\n<b>{{ $('Iterate Listings').item.json.job_title }}</b> at <b>{{ $('Iterate Listings').item.json.company }}</b>\n\n<b>AI Reasoning:</b>\n<i>{{ $('Resume Match Analysis').item.json.output.reasoning }}</i>\n\n<b>Key Skills:</b>\n<code>{{ $('Resume Match Analysis').item.json.output.key_skills.join(', ') }}</code>\n\n<b>Salary:</b> <code>{{ $('Resume Match Analysis').item.json.output.salaryInfo }}</code>\n\n<a href=\"{{ $('Iterate Listings').item.json.apply_url }}\">Apply Here</a> | <a href=\"{{ $('Iterate Listings').item.json.job_url }}\">View Job Description</a>",
"chatId": "[YOUR_ID]",
"additionalFields": {
"parse_mode": "HTML",
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "191a6567-4fda-46c1-aeb8-9a1d75742a39",
"name": "Scheduled Run Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
1600,
240
],
"parameters": {
"rule": {
"interval": [
{
"triggerAtHour": 9
}
]
}
},
"typeVersion": 1.2
},
{
"id": "15d4435b-5cd8-4081-af0b-0159d70ba342",
"name": "Manual Start Trigger",
"type": "n8n-nodes-base.manualTrigger",
"position": [
1605,
360
],
"parameters": [],
"typeVersion": 1
},
{
"id": "d3b4a1c4-7f39-4d9f-95c9-381d91ed9e68",
"name": "Next Item Hop",
"type": "n8n-nodes-base.noOp",
"position": [
1495,
530
],
"parameters": [],
"typeVersion": 1
}
],
"pinData": [],
"connections": {
"Setup Variables": {
"main": [
[
{
"node": "Fetch LinkedIn Listings",
"type": "main",
"index": 0
}
]
]
},
"Store Records": {
"main": [
[
{
"node": "High Score Gate",
"type": "main",
"index": 0
}
]
]
},
"Iterate Listings": {
"main": [
[
{
"node": "Complete Step",
"type": "main",
"index": 0
}
],
[
{
"node": "Analyze Job Details",
"type": "main",
"index": 0
}
]
]
},
"Next Item Hop": {
"main": [
[
{
"node": "Iterate Listings",
"type": "main",
"index": 0
}
]
]
},
"Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Analyze Job Details",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Resume Match Analysis": {
"main": [
[
{
"node": "Store Records",
"type": "main",
"index": 0
}
]
]
},
"Retrieve Commute Duration": {
"main": [
[
{
"node": "Commute Threshold Check",
"type": "main",
"index": 0
}
]
]
},
"Remote Status Check": {
"main": [
[
{
"node": "Retrieve Commute Duration",
"type": "main",
"index": 0
}
],
[
{
"node": "Resume Match Analysis",
"type": "main",
"index": 0
}
]
]
},
"Manual Start Trigger": {
"main": [
[
{
"node": "Setup Variables",
"type": "main",
"index": 0
}
]
]
},
"Scheduled Run Trigger": {
"main": [
[
{
"node": "Setup Variables",
"type": "main",
"index": 0
}
]
]
},
"Language Filter": {
"main": [
[
{
"node": "Remote Status Check",
"type": "main",
"index": 0
}
],
[
{
"node": "Iterate Listings",
"type": "main",
"index": 0
}
]
]
},
"Seniority Check": {
"main": [
[
{
"node": "Language Filter",
"type": "main",
"index": 0
}
],
[
{
"node": "Iterate Listings",
"type": "main",
"index": 0
}
]
]
},
"Send Telegram Alert": {
"main": [
[
{
"node": "Next Item Hop",
"type": "main",
"index": 0
}
]
]
},
"Analyze Job Details": {
"main": [
[
{
"node": "Seniority Check",
"type": "main",
"index": 0
}
]
]
},
"Fetch LinkedIn Listings": {
"main": [
[
{
"node": "Iterate Listings",
"type": "main",
"index": 0
}
]
]
},
"Commute Threshold Check": {
"main": [
[
{
"node": "Resume Match Analysis",
"type": "main",
"index": 0
}
],
[
{
"node": "Iterate Listings",
"type": "main",
"index": 0
}
]
]
},
"High Score Gate": {
"main": [
[
{
"node": "Send Telegram Alert",
"type": "main",
"index": 0
}
],
[
{
"node": "Next Item Hop",
"type": "main",
"index": 0
}
]
]
},
"Structured Parser": {
"ai_outputParser": [
[
{
"node": "Analyze Job Details",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Gemini Deep Model": {
"ai_languageModel": [
[
{
"node": "Resume Match Analysis",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Deep Output Parser": {
"ai_outputParser": [
[
{
"node": "Resume Match Analysis",
"type": "ai_outputParser",
"index": 0
}
]
]
}
}
}