January 22, 2026

Telegram + Google Sheets: polished resume images

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

Your resume “content” might be solid, but the presentation turns into a time sink. You tweak spacing, fight templates, export the wrong file type, then someone asks for “just one more version” with a different look.

This Telegram resume images automation hits career coaches and resume writers hardest because you’re producing under deadline. Recruiting teams feel it too when candidates keep sending messy PDFs that need fixing before sharing.

This workflow takes a Telegram message or file and returns a polished resume image, using Google Sheets as the style memory. You’ll see how it works, what you need, and where the biggest time savings show up.

How This Automation Works

The full n8n workflow, from trigger to final output:

n8n Workflow Template: Telegram + Google Sheets: polished resume images

Click to explore

flowchart LR

    subgraph sg0["User Sends Message to Bot 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/httprequest.dark.svg' width='40' height='40' /></div><br/>Download Resume"]
        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/telegram.svg' width='40' height='40' /></div><br/>Notify User"]
        n2@{ icon: "mdi:robot", form: "rounded", label: "Structured Output2", pos: "b", h: 48 }
        n3@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini3", pos: "b", h: 48 }
        n4@{ icon: "mdi:robot", form: "rounded", label: "Resume Writer", pos: "b", h: 48 }
        n5@{ icon: "mdi:robot", form: "rounded", label: "Structured Output1", pos: "b", h: 48 }
        n6@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini2", pos: "b", h: 48 }
        n7@{ icon: "mdi:database", form: "rounded", label: "Clear sheet", pos: "b", h: 48 }
        n8@{ icon: "mdi:swap-vertical", form: "rounded", label: "Loop Over Items", pos: "b", h: 48 }
        n9@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini1", pos: "b", h: 48 }
        n10@{ icon: "mdi:robot", form: "rounded", label: "Structured Output", pos: "b", h: 48 }
        n11@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini", pos: "b", h: 48 }
        n12@{ icon: "mdi:robot", form: "rounded", label: "Validate user Input", 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/telegram.svg' width='40' height='40' /></div><br/>User Sends Message to Bot"]
        n14@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Check For Input Type", pos: "b", h: 48 }
        n15@{ icon: "mdi:cog", form: "rounded", label: "Run Resume Workflow", 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/code.svg' width='40' height='40' /></div><br/>Splitting BrowserAct Items"]
        n17@{ icon: "mdi:robot", form: "rounded", label: "Chatting With User", pos: "b", h: 48 }
        n18@{ icon: "mdi:cog", form: "rounded", label: "SVG To JPG", pos: "b", h: 48 }
        n19@{ icon: "mdi:robot", form: "rounded", label: "Analyze Resume image", pos: "b", h: 48 }
        n20@{ icon: "mdi:database", form: "rounded", label: "Save Data", pos: "b", h: 48 }
        n21@{ icon: "mdi:robot", form: "rounded", label: "Resume Visualization", pos: "b", h: 48 }
        n22@{ icon: "mdi:robot", form: "rounded", label: "Generate Resume", pos: "b", h: 48 }
        n23["<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 Resume Back"]
        n24@{ icon: "mdi:cog", form: "rounded", label: "Aggregate Google Sheet Data", pos: "b", h: 48 }
        n25@{ icon: "mdi:database", form: "rounded", label: "Get Saved Resume", pos: "b", h: 48 }
        n26["<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/>Answer the User"]
        n20 --> n8
        n18 --> n19
        n7 --> n16
        n11 -.-> n10
        n11 -.-> n12
        n4 --> n21
        n9 -.-> n17
        n6 -.-> n5
        n6 -.-> n4
        n3 -.-> n2
        n3 -.-> n21
        n0 --> n18
        n22 --> n23
        n8 --> n25
        n8 --> n0
        n25 --> n24
        n10 -.-> n12
        n17 --> n26
        n5 -.-> n4
        n2 -.-> n21
        n15 --> n7
        n12 --> n14
        n19 --> n20
        n14 --> n15
        n14 --> n1
        n14 --> n17
        n21 --> n22
        n13 --> n12
        n16 --> n8
        n24 --> n4
    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 n13 trigger
    class n2,n4,n5,n10,n12,n17,n19,n21,n22 ai
    class n3,n6,n9,n11 aiModel
    class n14 decision
    class n7,n20,n25 database
    class n0 api
    class n16 code
    classDef customIcon fill:none,stroke:none
    class n0,n1,n13,n16,n23,n26 customIcon

The Problem: Resume formatting and revisions eat your week

Resume work is weirdly repetitive. You collect details from a chat thread, a PDF, a Google Doc, maybe a screenshot. Then you do the “design part” again: align sections, pick a template, adjust spacing, export, send, and wait. The worst part is the back-and-forth because clients don’t ask for “better,” they ask for “more professional,” “more modern,” or “make it look like this example.” Each request forces you to rebuild layout decisions you already made last time.

It adds up fast, especially when you’re juggling multiple people at once.

You end up recreating the same styles for every new resume because there’s no reusable “design memory.”
Exporting and sending files becomes its own mini-project, and the wrong format (or a broken PDF) triggers another round of edits.
Reference designs arrive as images or odd files, which means you either ignore them or spend time reverse-engineering the look.
Manual workflows invite small mistakes, like outdated phone numbers, missing roles, or duplicated bullet points after a copy/paste pass.

The Solution: Telegram in, polished resume image out

This workflow turns Telegram into the front door for resume intake and delivery. A Telegram bot receives either plain text (someone pastes their resume details) or a file (PDF or an image reference). Google Gemini classifies what came in, then pulls context and structure so the details aren’t stuck as a messy blob. If there’s a reference design, the workflow standardizes it and has Gemini Vision “read” the style, capturing the layout as a reusable template. Google Sheets becomes your simple library for those templates, so the next resume can match a “Corporate” or “Creative” style on purpose.

From there, an AI agent maps the candidate’s content to the selected layout, another AI agent writes the image-generation prompt, and Gemini renders the final resume image. The workflow sends it back in Telegram quickly, so the request-and-deliver loop feels instant instead of days long.

What You Get: Automation vs. Results

What This Workflow Automates

Results You’ll Get

It accepts resume text or files directly from a Telegram chat.
It parses and validates the incoming content before doing any design work.
It extracts a “Visual DNA” from reference images and stores it in Google Sheets.
It generates a styled resume image with Google Gemini and delivers it back to Telegram.

Most teams get about 2 hours back per resume when revisions calm down.
You can keep formatting consistent across clients because styles are stored, not reinvented.
Fewer “can you re-export this?” messages since the output is ready to share as an image.
Faster turnaround makes it easier to sell resume packages with clear delivery timelines.
You get a lightweight template library in Google Sheets that grows over time.

Example: What This Looks Like

Say you handle 5 resumes a week. Manually, it’s common to spend about 45 minutes formatting, then another 30 minutes on exports, tweaks, and “make it match this example” edits, so you’re at roughly 6 hours weekly. With this workflow, intake is a Telegram message (a couple minutes), style selection and rendering happen automatically, and you mostly review and request one adjustment if needed. Realistically, you can cut the process down to about 1 hour per week for touch-ups and final checks.

What You’ll Need

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Telegram to receive requests and deliver images
Google Sheets for template storage and structured data
Google Gemini API (get it from Google AI Studio / Google Cloud)

Skill level: Intermediate. You’ll connect accounts, map a few fields, and test with real Telegram messages and sample files.

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. The workflow starts when someone sends your bot resume text, a PDF, or a file link. If it’s not actually a resume request, it can reply normally instead of wasting compute.

The input gets classified and cleaned up. AI validation checks that the message contains enough resume detail to work with. If a file is provided, the workflow fetches it, reads the binary/PDF content, and converts formats when needed so downstream steps don’t choke.

Style is selected (or learned) via Google Sheets. If there’s a reference design image, the workflow converts it (for example SVG to JPG), then Gemini Vision inspects it and saves the layout traits into Google Sheets. If there’s no reference, the “Resume Blueprint Writer” agent picks a stored template based on industry and maps the candidate’s content into that layout.

Gemini renders the resume and Telegram delivers it. A “Visualizer” agent writes a detailed prompt from the blueprint, Gemini generates the final resume image, and the bot sends the result back to the same Telegram chat.

You can easily modify where the finished image goes (Telegram vs. Google Drive) based on your needs. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Telegram Trigger

This workflow starts when a user sends a Telegram message to your bot.

Add and open Telegram Message Trigger.
Credential Required: Connect your telegramApi credentials.
Keep Updates set to message.
Save the node so n8n registers the webhook.

Tip: Send a test message to your bot after saving the trigger to verify the webhook is reachable.

Step 2: Validate and Route User Input

Classify the incoming text and route to resume processing or chat response.

Open Validate Incoming Text and set Text to {{ $json.message.text }}.
Ensure Has Output Parser is enabled in Validate Incoming Text.
Open Structured Parse Base and keep Auto Fix enabled with the provided JSON schema.
Confirm Gemini Chat Model is connected as the language model for Validate Incoming Text and that credentials are added to Gemini Chat Model, not the parser node.
Configure Route Input Type rules to match Resume, Chat, and NoData using {{ $json.output.Type }}.

Credential Required: Connect your googlePalmApi credentials to Gemini Chat Model.

⚠️ Common Pitfall: Do not add credentials to Structured Parse Base; the API key must be set on Gemini Chat Model.

Step 3: Configure Parallel Branching and User Responses

When input is routed, the workflow either runs a resume-generation branch or sends a conversational response.

Note the parallel execution: Route Input Type outputs to both Execute BrowserAct Flow and Alert Telegram User in parallel.
Open Alert Telegram User and set Text to Ok, I will do it please give me a moment..
Set Chat ID in Alert Telegram User to {{ $('Telegram Message Trigger').item.json.message.chat.id }}.
Open Compose User Reply and set Text to Input type : {{ $json.output.Type }} | User Input : {{ $('Telegram Message Trigger').item.json.message.text }}.
Connect Compose User Reply to Send Text Response for both Chat and NoData outputs.

Credential Required: Connect your telegramApi credentials to Alert Telegram User and Send Text Response.

Credential Required: Connect your googlePalmApi credentials to Gemini Chat Model A, which powers Compose User Reply.

Step 4: Run BrowserAct and Prepare Template Data

Generate resume template data, wipe the sheet, and prepare batch processing for design templates.

Open Execute BrowserAct Flow and set Type to WORKFLOW and Workflow ID to your BrowserAct workflow ID (replace [YOUR_ID]).
Credential Required: Connect your browserActApi credentials to Execute BrowserAct Flow.
Open Wipe Sheet Rows and keep Operation set to clear.
Set Document ID to =parameter.SpreadSheetID == <SpreadSheetID> Or Select From List.
Set Sheet Name to parameter.SheetID == <SheetID> Or Select From List.
Open Split BrowserAct Items and keep the provided JS Code for splitting JSON strings.
Connect Split BrowserAct Items to Batch Iterator to start batch handling.

Credential Required: Connect your googleSheetsOAuth2Api credentials to Wipe Sheet Rows.

⚠️ Common Pitfall: The code in Split BrowserAct Items expects $input.first().json.output.string. Ensure your BrowserAct flow outputs that path.

Step 5: Analyze Resume Designs and Populate Google Sheets

Fetch and analyze template resumes, then store the visual descriptions in Google Sheets.

Open Fetch Resume File and set URL to {{ $json.Resume }}.
Open Convert SVG to JPG and set Output Format to jpg.
Open Inspect Resume Image and keep Resource as image, Input Type as binary, and Operation as analyze.
Open Append Sheet Data and map Resume Details to {{ $json.content.parts[0].text }}.
Ensure Append Sheet Data uses Operation append with the same Document ID and Sheet Name values as Wipe Sheet Rows.
Confirm the batch loop: Append Sheet Data → Batch Iterator → Retrieve Sheet Rows → Aggregate Sheet Records.

Credential Required: Connect your cloudConvertOAuth2Api credentials to Convert SVG to JPG.

Credential Required: Connect your googlePalmApi credentials to Inspect Resume Image.

Credential Required: Connect your googleSheetsOAuth2Api credentials to Append Sheet Data and Retrieve Sheet Rows.

Step 6: Generate the Resume Blueprint with AI

Use Gemini to select the best design and generate a structured blueprint based on user data.

Open Aggregate Sheet Records and keep Aggregate set to aggregateAllItemData.
Open Resume Blueprint Writer and set Text to Template Examples : {{ $json.data[0]["Resume Details"] }}, User Resume : {{ $('Validate Incoming Text').first().json.output.Resume }}, Category : {{ $('Validate Incoming Text').first().json.output.Category }} you need to use user resume data for final ouput..
Ensure Resume Blueprint Writer has Has Output Parser enabled.
Open Structured Parse A and keep Auto Fix enabled with the blueprint JSON schema.
Confirm Gemini Chat Model B is connected as the language model for Resume Blueprint Writer, and credentials are added to Gemini Chat Model B, not the parser node.

Credential Required: Connect your googlePalmApi credentials to Gemini Chat Model B.

Tip: The blueprint depends on sheet content. If no rows are found, check that Append Sheet Data is writing properly before running this step.

Step 7: Create and Render the Final Resume Image

Turn the blueprint into an image prompt and render the final resume.

Open Create Image Prompt and set Text to {{ $json.output.Resume }}.
Ensure Create Image Prompt has Has Output Parser enabled and uses Structured Parse B with the image prompt schema.
Confirm Gemini Chat Model C is connected as the language model for Create Image Prompt.
Open Render Resume Image and set Prompt to {{ $json.output.Image_Prompt }}.
Ensure Render Resume Image outputs binary data using the default Binary Property Output of data.

Credential Required: Connect your googlePalmApi credentials to Gemini Chat Model C and Render Resume Image.

⚠️ Common Pitfall: Do not attach credentials to Structured Parse B; the AI credentials belong to Gemini Chat Model C.

Step 8: Configure Output Delivery to Telegram

Send the rendered resume image or a text response back to the user.

Open Send Resume Result and set Operation to sendPhoto.
Set Binary Data to true so the image is sent from Render Resume Image.
Set Chat ID to {{ $('Telegram Message Trigger').first().json.message.chat.id }}.
Open Send Text Response and set Text to {{ $json.output }}.
Set Chat ID in Send Text Response to {{ $('Telegram Message Trigger').item.json.message.chat.id }}.

Credential Required: Connect your telegramApi credentials to Send Resume Result and Send Text Response.

Step 9: Test & Activate

Validate the end-to-end flow, then activate the workflow for production use.

Click Execute Workflow and send a Telegram message with a resume request.
Confirm that Alert Telegram User responds immediately while Execute BrowserAct Flow runs in parallel.
Verify that Send Resume Result delivers an image when input type is Resume and Send Text Response delivers a message for Chat or NoData.
Check the Google Sheet to ensure Append Sheet Data has added rows and Retrieve Sheet Rows can read them.
Once the test passes, toggle the workflow Active to enable production use.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Common Gotchas

Google Sheets credentials can expire or need specific permissions. If things break, check the n8n credential status and the spreadsheet sharing settings 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.
Telegram bot delivery can fail if the generated image is too large or the chat ID changes. If messages stop arriving, confirm the bot still has access to the chat and review the Telegram node error output.

Frequently Asked Questions

How long does it take to set up this Telegram resume images automation?

About an hour if your accounts are already created.

Do I need coding skills to automate Telegram resume images?

No. You’ll mainly connect credentials and paste in prompts/settings for the AI agents.

Is n8n free to use for this Telegram resume images 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 Gemini API usage costs, which vary by model and image generation volume.

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 Telegram resume images workflow for saving outputs to Google Drive instead?

Yes, and it’s a common tweak. Replace the “Send Resume Result” Telegram step with a Google Drive upload so the image is stored automatically, then optionally send the Drive link back in Telegram. You can also export to PDF/PNG by adding a conversion step after rendering. If you want the style library shared across teammates, keep Google Sheets as the template store and just change the final destination.

Why is my Telegram connection failing in this workflow?

Usually it’s the bot token or chat permissions. Confirm the Telegram Bot Token in n8n is correct, then verify the bot is actually in the chat (or that you’re messaging it directly) and hasn’t been blocked. If you recently recreated the bot, the old token will still “look valid” but won’t work. Also check the Telegram node error output in the execution log because it will often show a clear “chat not found” or “forbidden” message.

How many resumes can this Telegram resume images automation handle?

If you self-host n8n, there’s no fixed execution limit, so capacity mainly depends on your server and how fast Gemini renders images. On n8n Cloud, the practical limit is your monthly execution allowance on your plan, plus API rate limits from Gemini and any file conversion service. For many small teams, processing a few dozen resumes a day is realistic as long as you queue batches and don’t try to render everything at once.

Is this Telegram resume images automation better than using Zapier or Make?

Often, yes, because this kind of flow needs branching, file handling, and multi-step AI prompting that gets clumsy (and expensive) in simpler automation tools. n8n is also easier to self-host, which matters if you’re running lots of resume requests. Zapier or Make can still work if you only want a basic “Telegram in, image out” pipeline with minimal logic. If you’re unsure, Talk to an automation expert and we’ll map the cheapest setup that still feels reliable.

Once this is running, the workflow handles the repetitive formatting loop and your “resume delivery” becomes a simple Telegram conversation. Set it up, save your styles in Sheets, and stop rebuilding the same layouts from scratch.

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": "",
"meta": {
"instanceId": "28a3190e3ef786db513875a8a6b0a42ae7bc100fb4af45b9b580263f53a51430"
},
"name": "Automated Visual Resume Generator",
"tags": [],
"nodes": [
{
"id": "flowpast-topbar-12346",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
20
],
"parameters": {
"color": 7,
"width": 1340,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "5521c9ff-ed2f-4c25-85b2-8c18ad5476af",
"name": "Fetch Resume File",
"type": "n8n-nodes-base.httpRequest",
"position": [
200,
460
],
"parameters": {
"url": "={{ $json.Resume }}",
"options": []
},
"typeVersion": 4.3
},
{
"id": "c15f27ea-5bda-4131-96c1-64199e334d25",
"name": "Alert Telegram User",
"type": "n8n-nodes-base.telegram",
"position": [
480,
140
],
"webhookId": "23e1fb3a-33d8-40fa-aa49-08b320348b0a",
"parameters": {
"text": "=Ok, I will do it please give me a moment.",
"chatId": "=parameters.chatId=={{ $('Telegram Message Trigger').item.json.message.chat.id }}",
"additionalFields": {
"parse_mode": "HTML",
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "gJnGTVzNOeiM3LHZ",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "25ebb9a3-0238-4c1d-8fdc-87bf8691e29e",
"name": "Structured Parse B",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1020,
200
],
"parameters": {
"autoFix": true,
"jsonSchemaExample": "{\n  \"Image_Prompt\": \"<YOUR_HUGE_DETAILED_PROMPT_STRING_HERE>\"\n}"
},
"typeVersion": 1.3
},
{
"id": "9f9dcdb8-6d81-4363-a808-b193752f58a3",
"name": "Gemini Chat Model C",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
840,
200
],
"parameters": {
"options": []
},
"credentials": {
"googlePalmApi": {
"id": "9pXYiybR74j5zn4d",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "fb3921e9-1577-42b8-9f52-eb4bec5438a0",
"name": "Resume Blueprint Writer",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
420,
180
],
"parameters": {
"text": "=Template Examples : {{ $json.data[0][\"Resume Details\"] }},\nUser Resume : {{ $('Validate Incoming Text').first().json.output.Resume }},\nCategory : {{ $('Validate Incoming Text').first().json.output.Category }}\n\nyou need to use user resume data for final ouput.",
"options": {
"systemMessage": "# Role\nYou are the **Senior Resume Architect & Design System Engine**. You possess expert knowledge in visual design, typography hierarchy, and color psychology.\n\n# Context\nYou will be provided with two distinct inputs:\n1.  **Design Knowledge Base (JSON):** A dataset of resume templates. Each entry contains a `row_number` and a text field called `Resume Details` describing a specific visual style (colors, layout, fonts, shapes).\n2.  **Candidate Profile:** The raw text or structured data of a job applicant's resume.\n\n# Your Mission\nYour goal is to autonomously select the most appropriate design from the Knowledge Base and generate a **machine-readable Visual Blueprint** in JSON format. This blueprint will be used by a renderer to reconstruct the resume pixel-perfectly.\n\n# Operational Steps\n\n## Step 1: Semantic Design Matching\nAnalyze the **Candidate Profile** to determine their industry, seniority, and professional archetype. compare this against the \"Aesthetic\" and \"Vibe\" described in the **Design Knowledge Base**.\n* **Logic Rule A:** If the candidate is in Healthcare, Education, HR, or childcare, prioritize designs described as \"Nurturing,\" \"Soft,\" \"Human-Centric,\" or layouts using soft colors (e.g., Pink/Pastel).\n* **Logic Rule B:** If the candidate is in Logistics, Engineering, Data, or Construction, prioritize designs described as \"Industrial,\" \"Structural,\" \"Monochrome,\" or layouts using dark/high-contrast headers.\n* **Logic Rule C:** If the candidate is in Law, Research, Finance, or Administration, prioritize designs described as \"Classic,\" \"Linear,\" \"Academic,\" or layouts using conservative colors (Maroon/Navy) and clean lines.\n\n## Step 2: Visual Extraction\nOnce a `row_number` is selected, extract every visual parameter from its `Resume Details` text. You must not hallucinate details; use the specific Hex codes, specific font styles (Sans-Serif/Serif), and specific layout rules provided in that text.\n\n## Step 3: Content Mapping\nMap the Candidate's raw data into the selected layout's constraints. Decide exactly where the Name, Contact Info, Skills, and Experience will be placed based on the design rules (e.g., \"Left Sidebar\" vs \"Top Header\").\n\n# Output Specification (Strict JSON)\nYou must output **ONLY** a single valid JSON object. Do not output markdown blocks (```json), do not output conversational text, and do not output explanations outside the JSON.\n\nThe JSON must follow this exact schema:\n\n{\n  \"Resume\": {\n    \"meta\": {\n      \"candidate_name\": \"<Extracted Name>\",\n      \"candidate_industry\": \"<Detected Industry>\",\n      \"selected_design_row_number\": \"<Integer from the input JSON>\",\n      \"match_reasoning\": \"<Explain why this design fits this candidate's industry based on the 'Vibe' description>\"\n    },\n    \"visual_blueprint\": {\n      \"layout_engine\": {\n        \"structure_type\": \"<e.g., Asymmetrical 2-Column, Offset Single-Column, Linear>\",\n        \"column_ratio\": \"<e.g., 35% Left / 65% Right>\",\n        \"margins_and_padding\": \"<Detailed description of whitespace/padding rules from the text>\"\n      },\n      \"color_system\": {\n        \"background_hex\": \"<Precise Hex Code from text>\",\n        \"primary_text_hex\": \"<Precise Hex Code from text>\",\n        \"header_background_hex\": \"<Precise Hex Code from text or 'None'>\",\n        \"accent_hex\": \"<Precise Hex Code or 'None'>\",\n        \"aesthetic_vibe\": \"<e.g., Industrial, Nurturing, Academic>\"\n      },\n      \"typography_hierarchy\": {\n        \"level_1_name\": {\n          \"font_style\": \"<e.g., Sans-Serif, Geometric>\",\n          \"casing\": \"<e.g., UPPERCASE, Title Case>\",\n          \"weight\": \"<e.g., Bold, Heavy>\",\n          \"tracking\": \"<e.g., Wide Letter Spacing, Normal>\"\n        },\n        \"level_2_headers\": {\n          \"style\": \"<e.g., Enclosed in Box, Underlined, Dotted Line>\",\n          \"alignment\": \"<e.g., Left Aligned, Floating Left>\"\n        },\n        \"level_3_body\": {\n          \"font_style\": \"<e.g., Standard Sans-Serif>\",\n          \"list_style\": \"<e.g., Bullet points, paragraphs>\"\n        }\n      },\n      \"graphical_elements\": {\n        \"dividers\": \"<Describe specific lines: Solid, Dotted, Hairline>\",\n        \"shapes\": \"<Describe specific shapes: Full-bleed banners, Sidebar blocks, Boxed anchors>\",\n        \"icons_used\": \"<true/false>\"\n      },\n      \"data_placement_instructions\": {\n        \"header_area\": \"<What data goes here? e.g., Name + Contact>\",\n        \"sidebar_area\": \"<What data goes here? e.g., Skills, Education, or 'None'>\",\n        \"main_content_area\": \"<What data goes here? e.g., Work History, Summary>\"\n      }\n    }\n  }\n}"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 3
},
{
"id": "386f1921-79d0-4955-a99d-9a4fb49ef5e1",
"name": "Structured Parse A",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
760,
230
],
"parameters": {
"autoFix": true,
"jsonSchemaExample": "{\n  \"Resume\": {\n    \"meta\": {\n      \"candidate_name\": \"<Extracted Name>\",\n      \"candidate_industry\": \"<Detected Industry>\",\n      \"selected_design_row_number\": \"<Integer from the input JSON>\",\n      \"match_reasoning\": \"<Explain why this design fits this candidate's industry based on the 'Vibe' description>\"\n    },\n    \"visual_blueprint\": {\n      \"layout_engine\": {\n        \"structure_type\": \"<e.g., Asymmetrical 2-Column, Offset Single-Column, Linear>\",\n        \"column_ratio\": \"<e.g., 35% Left / 65% Right>\",\n        \"margins_and_padding\": \"<Detailed description of whitespace/padding rules from the text>\"\n      },\n      \"color_system\": {\n        \"background_hex\": \"<Precise Hex Code from text>\",\n        \"primary_text_hex\": \"<Precise Hex Code from text>\",\n        \"header_background_hex\": \"<Precise Hex Code from text or 'None'>\",\n        \"accent_hex\": \"<Precise Hex Code or 'None'>\",\n        \"aesthetic_vibe\": \"<e.g., Industrial, Nurturing, Academic>\"\n      },\n      \"typography_hierarchy\": {\n        \"level_1_name\": {\n          \"font_style\": \"<e.g., Sans-Serif, Geometric>\",\n          \"casing\": \"<e.g., UPPERCASE, Title Case>\",\n          \"weight\": \"<e.g., Bold, Heavy>\",\n          \"tracking\": \"<e.g., Wide Letter Spacing, Normal>\"\n        },\n        \"level_2_headers\": {\n          \"style\": \"<e.g., Enclosed in Box, Underlined, Dotted Line>\",\n          \"alignment\": \"<e.g., Left Aligned, Floating Left>\"\n        },\n        \"level_3_body\": {\n          \"font_style\": \"<e.g., Standard Sans-Serif>\",\n          \"list_style\": \"<e.g., Bullet points, paragraphs>\"\n        }\n      },\n      \"graphical_elements\": {\n        \"dividers\": \"<Describe specific lines: Solid, Dotted, Hairline>\",\n        \"shapes\": \"<Describe specific shapes: Full-bleed banners, Sidebar blocks, Boxed anchors>\",\n        \"icons_used\": \"<true/false>\"\n      },\n      \"data_placement_instructions\": {\n        \"header_area\": \"<What data goes here? e.g., Name + Contact>\",\n        \"sidebar_area\": \"<What data goes here? e.g., Skills, Education, or 'None'>\",\n        \"main_content_area\": \"<What data goes here? e.g., Work History, Summary>\"\n      }\n    }\n  }\n}"
},
"typeVersion": 1.3
},
{
"id": "ff62e4f9-4069-4b6b-8f93-d09fbefb7909",
"name": "Gemini Chat Model B",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
560,
230
],
"parameters": {
"options": []
},
"credentials": {
"googlePalmApi": {
"id": "9pXYiybR74j5zn4d",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "c87bd274-022f-4e59-97e1-a1b79c2e45e4",
"name": "Wipe Sheet Rows",
"type": "n8n-nodes-base.googleSheets",
"position": [
300,
320
],
"parameters": {
"operation": "clear",
"sheetName": {
"__rl": true,
"mode": "id",
"value": "parameter.SheetID == <SheetID>  Or Select From List"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "=parameter.SpreadSheetID == <SpreadSheetID>  Or Select From List"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "BSirjWRAwIzOFp7c",
"name": ""
}
},
"typeVersion": 4.7
},
{
"id": "c0607040-a6b2-49a1-b9e8-d30a56a7084a",
"name": "Batch Iterator",
"type": "n8n-nodes-base.splitInBatches",
"position": [
0,
330
],
"parameters": {
"options": []
},
"typeVersion": 3
},
{
"id": "7414cf29-b4be-4b56-a7c1-d9cf1cc51dc1",
"name": "Gemini Chat Model A",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
670,
520
],
"parameters": {
"options": []
},
"credentials": {
"googlePalmApi": {
"id": "9pXYiybR74j5zn4d",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "dc2ad052-af8c-49c6-8f61-9e9410bc70ae",
"name": "Structured Parse Base",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1240,
200
],
"parameters": {
"autoFix": true,
"jsonSchemaExample": "{\"Type\": \"Resume\", \"Category\": \"extracted_Category\" ,\"Resume\" : \"User_Resume\"}"
},
"typeVersion": 1.3
},
{
"id": "e363cdbe-87b9-46fc-829a-cab96c471546",
"name": "Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1060,
230
],
"parameters": {
"options": []
},
"credentials": {
"googlePalmApi": {
"id": "9pXYiybR74j5zn4d",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "a1c2dd73-b6d6-4864-9f14-416683de08c2",
"name": "Validate Incoming Text",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
880,
210
],
"parameters": {
"text": "={{ $json.message.text }}",
"options": {
"systemMessage": "You are an input classification engine. Your sole purpose is to analyze user text and output a JSON object based on specific criteria. Do not generate conversational text; only output the raw JSON.\n\nRules for Classification (evaluated in order of priority):\n\n1. Resume PROCESSING (Priority 1):\nif the user sends a resume or asks to create a resume based on the provided skills or similar content   \n- CRITICAL CHECK: Does the input contain a valid Resume and skills?\n     - IF YES (Link is present):\n       - Set \"Type\" to \" Resume\".\n       - Extract the Category of the user as \" Category \".\n       - Extract and refine user resume input as \u201cResume\u201d\n       - Output format: {\"Type\": \"Resume\", \"Category\": \"extracted_Category\" ,\"Resume\" : \"User_Resume\"}\n     \n     - IF NO (User Resume is missing):\n       - Treat this strictly as \"NoData\".\n       - Output format: {\"Type\": \"NoData\", \"Category\": \"Null\" , \" Resume \": \"Null\" }\n\n2. REGULAR CHAT (Priority 2):\n   If the user input is a greeting, small talk, or general conversational filler (e.g., \"Hello,\" \"How are you?\", \"Tell me a joke\") without asking for link processing.\n   - Output format: {\"Type\": \"Chat\", \"Link\": \"Null\", \"Resume \": \"Null\" }\n\n3. INSUFFICIENT DATA (Priority 3):\n   If the user input is gibberish, vague, or if it matched the \" Resume \" intent but lacked a User Resume (as per Rule 1).\n   - Output format: {\"Type\": \"NoData\", \"Category \": \"Null\", \"Resume\": \"Null\"}\n\nOutput Constraint:\nReturn ONLY the raw JSON object. Do not wrap it in markdown code blocks. Do not add explanations.\n"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 3
},
{
"id": "34627454-d9b4-4fd2-ad31-d2d9499101a5",
"name": "Telegram Message Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
1120,
160
],
"webhookId": "a98e8455-ba5a-447e-b928-733483d34db4",
"parameters": {
"updates": [
"message"
],
"additionalFields": []
},
"credentials": {
"telegramApi": {
"id": "gJnGTVzNOeiM3LHZ",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "d2ea304d-cdf3-4b39-9261-24f61ca1cfd3",
"name": "Route Input Type",
"type": "n8n-nodes-base.switch",
"position": [
660,
250
],
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "9e003f66-d011-459a-a313-b603c0e14551",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.Type }}",
"rightValue": "Resume"
}
]
}
},
{
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "2ebb24ec-bd32-4e96-a022-93d066fda17f",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.Type }}",
"rightValue": "Chat"
}
]
}
},
{
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "24d355dd-efec-4946-96fe-3d82f3ee4d71",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.output.Type }}",
"rightValue": "NoData"
}
]
}
}
]
},
"options": []
},
"typeVersion": 3.4
},
{
"id": "2fc3f933-841c-4b75-9b6d-0f58f6504862",
"name": "Execute BrowserAct Flow",
"type": "n8n-nodes-browseract.browserAct",
"position": [
480,
330
],
"parameters": {
"type": "WORKFLOW",
"timeout": 7200,
"workflowId": "[YOUR_ID]",
"workflowConfig": {
"value": [],
"schema": [
{
"id": "input-JobHero",
"type": "string",
"display": true,
"removed": true,
"required": false,
"description": "If left blank, the default value defined in BrowserAct will be used.",
"displayName": "JobHero",
"defaultMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"input-JobHero",
"input-Category"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"open_incognito_mode": false
},
"credentials": {
"browserActApi": {
"id": "G1U5ih38TKU5wcI5",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "6a3e15d2-500d-4d60-89c1-d3260fae6492",
"name": "Split BrowserAct Items",
"type": "n8n-nodes-base.code",
"position": [
130,
310
],
"parameters": {
"jsCode": "// Get the JSON string using the exact path provided by the user.\nconst jsonString = $input.first().json.output.string;\n\nlet parsedData;\n\n// Check if the string exists before attempting to parse\nif (!jsonString) {\n    // Return an empty array or throw an error if no string is found\n    // Throwing an error is usually better to stop the workflow if data is missing.\n    throw new Error(\"Input string is empty or missing at the specified path: $input.first().json.output.string\");\n}\n\ntry {\n    // 1. Parse the JSON string into a JavaScript array of objects\n    parsedData = JSON.parse(jsonString);\n} catch (error) {\n    // Handle JSON parsing errors (e.g., if the string is malformed)\n    throw new Error(`Failed to parse JSON string: ${error.message}`);\n}\n\n// 2. Ensure the parsed data is an array\nif (!Array.isArray(parsedData)) {\n    throw new Error('Parsed data is not an array. It cannot be split into multiple items.');\n}\n\n// 3. Map the array of objects into the n8n item format { json: object }\n// Each element in this array will be treated as a new item by n8n, achieving the split.\nconst outputItems = parsedData.map(item => ({\n    json: item,\n}));\n\n// 4. Return the new array of items\nreturn outputItems;"
},
"typeVersion": 2
},
{
"id": "915fc10f-b8a0-42c9-bd11-4a20d17f8acd",
"name": "Compose User Reply",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
480,
490
],
"parameters": {
"text": "=Input type : {{ $json.output.Type }} | User Input : {{ $('Telegram Message Trigger').item.json.message.text }}",
"options": {
"systemMessage": "if the input type is Nodata ask the user to provide the Resume with education, skills and name.\n\nif the input type is chat, analyze the user input and generate single response\n\nsend the result out as a raw text.\navoid using any tags or notations like ```text ```"
},
"promptType": "define"
},
"typeVersion": 3
},
{
"id": "c2b616bd-0384-4532-9ba5-235c3d12c720",
"name": "Convert SVG to JPG",
"type": "@cloudconvert/n8n-nodes-cloudconvert.cloudConvert",
"position": [
400,
490
],
"parameters": {
"outputFormat": "jpg"
},
"credentials": {
"cloudConvertOAuth2Api": {
"id": "G0ciopniMabxoUXg",
"name": ""
}
},
"executeOnce": false,
"typeVersion": 1
},
{
"id": "e558b724-28e8-4229-a9e1-403d9a10e23b",
"name": "Inspect Resume Image",
"type": "@n8n/n8n-nodes-langchain.googleGemini",
"position": [
610,
510
],
"parameters": {
"text": "You are a Creative Director Expert. Your goal is to analyze the raw image of a jpeg resume to reverse-engineer its visual design, layout structure, and aesthetic \"vibe\" to provide design inspiration for the user.\n\nPrimary Objective: Translate the Image (coordinates, shapes, styles, and grouping) into a vivid visual description of the layout, color palette, and typographic hierarchy.\n\nOperational Protocols:\n\n1. Layout & Spatial Analysis (The \"Where\")\n\nCoordinate Mapping: Analyze x and y coordinates and <g> groupings to determine the page structure.\n\nSidebar Detection: Look for specific background rectangles (<rect>) or text aligned to the far left/right to identify if there is a sidebar/rail.\n\nHeader Analysis: Check the top y coordinates. Is the name centered, left-aligned, or huge?\n\nGrid Structure: Determine if the content is Single Column, Two-Column (50/50), or Asymmetrical (e.g., 30/70 split).\n\nWhitespace: Look for gaps in coordinate clusters to describe the spacing and \"breathing room\" of the design.\n\n2. Aesthetic & Stylistic Analysis (The \"Look\")\n\nColor Palette: Extract fill and stroke hex codes. Convert these into descriptive color names (e.g., \"Slate Grey,\" \"Electric Blue,\" \"Soft Pastel\"). Describe the mood (Professional, Creative, Dark Mode, Minimalist).\n\nTypography: Analyze font-family, font-weight, and relative font-size.\n\nIs the design using serif (classic) or sans-serif (modern) fonts?\n\nHow does it distinguish headers? (e.g., \"Headers are All-Caps and Bold,\" or \"Headers are colored blue\").\n\nGraphic Elements: Identify decorative elements like:\n\nLine separators (<line> or <path>).\n\nIcons or circular photo masks (<clipPath>, <circle>).\n\nBackground patterns or gradients (<linearGradient>).\n\n3. Output Formatting Rules Provide a descriptive breakdown categorized for design inspiration:\n\n1. The Layout Blueprint\n\nStructure: [e.g., \"A classic 2-column layout with a dark left sidebar taking up 30% of the width.\"]\n\nHeader Style: [e.g., \"Massive, centered name header that spans the full width.\"]\n\nSectioning: [e.g., \"Sections are separated by thin horizontal gray lines.\"]\n\n2. Color & Vibe\n\nPrimary Colors: [List dominant colors]\n\nAccent Colors: [List highlight colors used for links or headers]\n\nAesthetic: [e.g., \"Corporate Minimalist,\" \"Tech-Dark Mode,\" or \"Playful/Creative.\"]\n\n3. Typography & Hierarchy\n\nFont Style: [Description of font usage]\n\nEmphasis: [How they highlight skills\u2014bolding? capsules? colored text?]\n\n4. Unique Design Features (Inspiration)\n\n[List 1-2 cool code-based design tricks found, e.g., \"A cool circular progress bar for language skills\" or \"A distinct geometric background pattern.\"]",
"modelId": {
"__rl": true,
"mode": "list",
"value": "models/gemini-3-pro-preview",
"cachedResultName": "models/gemini-3-pro-preview"
},
"options": [],
"resource": "image",
"inputType": "binary",
"operation": "analyze"
},
"credentials": {
"googlePalmApi": {
"id": "9pXYiybR74j5zn4d",
"name": ""
}
},
"executeOnce": false,
"typeVersion": 1
},
{
"id": "5b790b27-a250-403f-844f-ef34d114e8ca",
"name": "Append Sheet Data",
"type": "n8n-nodes-base.googleSheets",
"position": [
820,
490
],
"parameters": {
"columns": {
"value": {
"Resume Details": "={{ $json.content.parts[0].text }}"
},
"schema": [
{
"id": "Resume Details",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Resume Details",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"Resume Details"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "id",
"value": "=parameter.SheetID == <SheetID>  Or Select From List"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "=parameter.SpreadSheetID == <SpreadSheetID> Or Select From List"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "BSirjWRAwIzOFp7c",
"name": ""
}
},
"typeVersion": 4.7
},
{
"id": "27b1f40d-c146-44f6-bb1b-7774b0cc4393",
"name": "Create Image Prompt",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
630,
160
],
"parameters": {
"text": "={{ $json.output.Resume }}",
"options": {
"systemMessage": "# Role\nYou are the **Nano Banana Pro Prompt Specialist**. You are an expert in converting structured data into highly technical, parameter-rich image generation prompts.\n\n# Input Data\nYou will receive a JSON object with the key `\"Resume\"`. This object contains a \"Visual Blueprint\" describing a specific resume design (layout, hex codes, fonts, lines, and arrangement).\n\n# Your Mission\nTransform the input JSON into a single, comprehensive **natural language prompt** optimized for the \"Nano Banana Pro\" image generator. You must describe every visual element in excruciating detail to ensure the generated image matches the blueprint exactly.\n\n# Guidelines for the Generated Prompt\nInside your output JSON, the text string must cover:\n\n1.  **Canvas & Coordinates:**\n    * Explicitly state the aspect ratio (Vertical A4/US Letter).\n    * Define the exact spatial arrangement (e.g., \"A split layout where the left 30% is a sidebar...\").\n    * Mention alignment (e.g., \"Text strictly left-aligned at x-coordinate 50\").\n\n2.  **Colors & Hex Accuracy:**\n    * You **must** include the specific Hex codes found in the input (e.g., \"Background color #45505b\").\n    * Describe the contrast and material (e.g., \"Matte white paper texture\", \"Flat digital vector\").\n\n3.  **Typography & Lines:**\n    * Describe the font characteristics (e.g., \"Heavy geometric sans-serif in all-caps\").\n    * Describe line weights and styles (e.g., \"1px dotted border in maroon\", \"Solid rectangular border\").\n    * Describe specific text hierarchies (e.g., \"Name is the largest element, approx 24pt\").\n\n4.  **Graphical Details:**\n    * Describe any stickers, icons, or UI elements (e.g., \"Circular phone icon\", \"Boxed section anchors\").\n    * Describe whitespace usage (e.g., \"Generous padding around the text blocks\").\n\n# Output Format (Strict JSON)\nYou must output **ONLY** a valid JSON object. No markdown formatting (like ```json), no conversational text.\n\n# Output Format (Strict JSON)\nYou must output **ONLY** a valid JSON object. No markdown, no filler.\n\n{\n  \"Image_Prompt\": \"<YOUR_HUGE_DETAILED_PROMPT_STRING_HERE>\"\n}"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 3
},
{
"id": "29a409d8-bc77-4ea7-9b86-339ac6256767",
"name": "Render Resume Image",
"type": "@n8n/n8n-nodes-langchain.googleGemini",
"position": [
840,
140
],
"parameters": {
"prompt": "={{ $json.output.Image_Prompt }}",
"modelId": {
"__rl": true,
"mode": "list",
"value": "models/gemini-3-pro-image-preview",
"cachedResultName": "models/gemini-3-pro-image-preview (Nano Banana Pro)"
},
"options": {
"binaryPropertyOutput": "data"
},
"resource": "image"
},
"credentials": {
"googlePalmApi": {
"id": "9pXYiybR74j5zn4d",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "bb1c7677-b0af-4836-9cad-c3b884bce38d",
"name": "Send Resume Result",
"type": "n8n-nodes-base.telegram",
"position": [
1020,
120
],
"webhookId": "85fc60f7-2215-433d-9a33-e85d18e055ea",
"parameters": {
"chatId": "=parameters.chatId=={{ $('Telegram Message Trigger').first().json.message.chat.id }}",
"operation": "sendPhoto",
"binaryData": true,
"additionalFields": []
},
"credentials": {
"telegramApi": {
"id": "gJnGTVzNOeiM3LHZ",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "5e04fa2f-c02e-4486-854f-808afc27d60f",
"name": "Aggregate Sheet Records",
"type": "n8n-nodes-base.aggregate",
"position": [
240,
190
],
"parameters": {
"options": [],
"aggregate": "aggregateAllItemData"
},
"typeVersion": 1
},
{
"id": "c7ac1d7c-b7fe-4ce6-81ca-29e61b70ae5d",
"name": "Retrieve Sheet Rows",
"type": "n8n-nodes-base.googleSheets",
"position": [
20,
180
],
"parameters": {
"options": [],
"sheetName": {
"__rl": true,
"mode": "id",
"value": "parameter.SheetID == <SheetID>  Or Select From List"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "=parameter.SpreadSheetID == <SpreadSheetID>  Or Select From List"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "BSirjWRAwIzOFp7c",
"name": ""
}
},
"typeVersion": 4.7
},
{
"id": "4de33096-5416-4777-88fb-74d5a7db003d",
"name": "Send Text Response",
"type": "n8n-nodes-base.telegram",
"position": [
260,
510
],
"webhookId": "23e1fb3a-33d8-40fa-aa49-08b320348b0a",
"parameters": {
"text": "={{ $json.output }}",
"chatId": "=parameters.chatId=={{ $('Telegram Message Trigger').item.json.message.chat.id }}",
"additionalFields": {
"parse_mode": "HTML",
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "gJnGTVzNOeiM3LHZ",
"name": ""
}
},
"typeVersion": 1.2
}
],
"active": false,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": "",
"connections": {
"Append Sheet Data": {
"main": [
[
{
"node": "Batch Iterator",
"type": "main",
"index": 0
}
]
]
},
"Convert SVG to JPG": {
"main": [
[
{
"node": "Inspect Resume Image",
"type": "main",
"index": 0
}
]
]
},
"Wipe Sheet Rows": {
"main": [
[
{
"node": "Split BrowserAct Items",
"type": "main",
"index": 0
}
]
]
},
"Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Structured Parse Base",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Validate Incoming Text",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Resume Blueprint Writer": {
"main": [
[
{
"node": "Create Image Prompt",
"type": "main",
"index": 0
}
]
]
},
"Gemini Chat Model A": {
"ai_languageModel": [
[
{
"node": "Compose User Reply",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Gemini Chat Model B": {
"ai_languageModel": [
[
{
"node": "Structured Parse A",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Resume Blueprint Writer",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Gemini Chat Model C": {
"ai_languageModel": [
[
{
"node": "Structured Parse B",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Create Image Prompt",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Fetch Resume File": {
"main": [
[
{
"node": "Convert SVG to JPG",
"type": "main",
"index": 0
}
]
]
},
"Render Resume Image": {
"main": [
[
{
"node": "Send Resume Result",
"type": "main",
"index": 0
}
]
]
},
"Batch Iterator": {
"main": [
[
{
"node": "Retrieve Sheet Rows",
"type": "main",
"index": 0
}
],
[
{
"node": "Fetch Resume File",
"type": "main",
"index": 0
}
]
]
},
"Retrieve Sheet Rows": {
"main": [
[
{
"node": "Aggregate Sheet Records",
"type": "main",
"index": 0
}
]
]
},
"Structured Parse Base": {
"ai_outputParser": [
[
{
"node": "Validate Incoming Text",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Compose User Reply": {
"main": [
[
{
"node": "Send Text Response",
"type": "main",
"index": 0
}
]
]
},
"Structured Parse A": {
"ai_outputParser": [
[
{
"node": "Resume Blueprint Writer",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Structured Parse B": {
"ai_outputParser": [
[
{
"node": "Create Image Prompt",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Execute BrowserAct Flow": {
"main": [
[
{
"node": "Wipe Sheet Rows",
"type": "main",
"index": 0
}
]
]
},
"Validate Incoming Text": {
"main": [
[
{
"node": "Route Input Type",
"type": "main",
"index": 0
}
]
]
},
"Inspect Resume Image": {
"main": [
[
{
"node": "Append Sheet Data",
"type": "main",
"index": 0
}
]
]
},
"Route Input Type": {
"main": [
[
{
"node": "Execute BrowserAct Flow",
"type": "main",
"index": 0
},
{
"node": "Alert Telegram User",
"type": "main",
"index": 0
}
],
[
{
"node": "Compose User Reply",
"type": "main",
"index": 0
}
],
[
{
"node": "Compose User Reply",
"type": "main",
"index": 0
}
]
]
},
"Create Image Prompt": {
"main": [
[
{
"node": "Render Resume Image",
"type": "main",
"index": 0
}
]
]
},
"Telegram Message Trigger": {
"main": [
[
{
"node": "Validate Incoming Text",
"type": "main",
"index": 0
}
]
]
},
"Split BrowserAct Items": {
"main": [
[
{
"node": "Batch Iterator",
"type": "main",
"index": 0
}
]
]
},
"Aggregate Sheet Records": {
"main": [
[
{
"node": "Resume Blueprint Writer",
"type": "main",
"index": 0
}
]
]
}
}
}