FirstDropHQ This workflow corresponds to n8n.io template #17427 — we link there as the canonical source.
This workflow follows the Google Sheets → HTTP Request recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "Lead Qualifier & Scorer",
"nodes": [
{
"id": "6b1f2a01-0000-4000-8000-00000000e701",
"name": "When clicking 'Execute workflow'",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-380,
200
],
"parameters": {},
"typeVersion": 1
},
{
"id": "6b1f2a02-0000-4000-8000-00000000e702",
"name": "\u2b50 Configure Your Run",
"type": "n8n-nodes-base.set",
"position": [
-180,
200
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "6b1f2a21-+1234567890000e721",
"name": "max_per_run",
"type": "string",
"value": "25"
},
{
"id": "6b1f2a22-+1234567890000e722",
"name": "openai_model",
"type": "string",
"value": "gpt-4o-mini"
},
{
"id": "6b1f2a23-+1234567890000e723",
"name": "icp_description",
"type": "string",
"value": "Independent direct-to-consumer brands that sell physical products online through their own store (e.g. Shopify or WooCommerce), roughly 5-100 staff. Not agencies, not banks or financial services, not large enterprises."
},
{
"id": "6b1f2a24-+1234567890000e724",
"name": "min_qualified_score",
"type": "string",
"value": "0"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "6b1f2a03-0000-4000-8000-00000000e703",
"name": "Read Leads",
"type": "n8n-nodes-base.googleSheets",
"position": [
40,
200
],
"parameters": {
"options": {},
"sheetName": {
"__rl": true,
"mode": "name",
"value": "leads"
},
"documentId": {
"__rl": true,
"mode": "url",
"value": "PASTE_YOUR_GOOGLE_SHEET_URL"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4
},
{
"id": "6b1f2a04-0000-4000-8000-00000000e704",
"name": "Select Pending",
"type": "n8n-nodes-base.code",
"position": [
240,
200
],
"parameters": {
"jsCode": "\n// Select Pending \u2014 status-driven idempotency + per-run cap + model allowlist. No web fetch.\nconst APPROVED_MODELS = [\"gpt-4o-mini\", \"gpt-4.1-mini\"];\nconst DEFAULT_MODEL = \"gpt-4o-mini\";\nconst HARD_CAP = 100;\nconst DEFAULT_CAP = 25;\n\nconst cfg = $('\u2b50 Configure Your Run').first().json;\nlet model = String(cfg.openai_model || '').trim();\nif (!APPROVED_MODELS.includes(model)) model = DEFAULT_MODEL;\n\nlet cap = Number(cfg.max_per_run);\nif (!Number.isFinite(cap) || cap <= 0) cap = DEFAULT_CAP;\ncap = Math.min(Math.floor(cap), HARD_CAP);\n\nconst icp = String(cfg.icp_description || '').trim();\n\n// Validate min_qualified_score HERE, before any billable call: a typo like 750 must be a clear\n// config error up front, not a silent empty hand-off after every lead has been charged.\nconst minqRaw = String(cfg.min_qualified_score ?? '').trim();\nconst minq = minqRaw === '' ? 0 : Number(minqRaw);\nif (!Number.isFinite(minq) || minq < 0 || minq > 100) {\n throw new Error(\"Configuration error: min_qualified_score must be a number between 0 and 100 \" +\n \"(scores are 0-100). Got: '\" + minqRaw + \"'. Fix it in \u2b50 Configure Your Run.\");\n}\n\nconst rows = $input.all();\nconst out = [];\nfor (const item of rows) {\n const j = item.json;\n const name = String(j.name || '').trim();\n const company = String(j.company || '').trim();\n const role = String(j.role || '').trim();\n const website = String(j.website || '').trim();\n const notes = String(j.notes || '').trim();\n const hasContent = name || company || website; // skip genuinely empty rows\n const done = String(j.status || '').trim().toLowerCase() === 'done'; // status-driven: clear 'status' to re-score\n if (!hasContent || done) continue; // 'failed'/blank rows are (re)processed\n out.push({ json: {\n row_number: j.row_number, // stable per-row match key\n name, company, role, website, notes,\n _model: model,\n _icp: icp,\n }});\n if (out.length >= cap) break;\n}\nreturn out;\n"
},
"typeVersion": 2
},
{
"id": "6b1f2a06-0000-4000-8000-00000000e706",
"name": "Build Scoring Prompt",
"type": "n8n-nodes-base.code",
"position": [
440,
200
],
"parameters": {
"jsCode": "\n// Build Scoring Prompt \u2014 compose the ICP + one lead into a strict scoring request.\nconst SYSTEM_RULES = \"You are a B2B lead-qualification assistant. Given an Ideal Customer Profile (ICP) and ONE lead's details, assess how well the lead fits the ICP and produce an actionable, honest evaluation. (1) Use ONLY the ICP and the lead fields provided \\u2014 NEVER invent facts about the lead (no assumed company size, funding, location, tech stack, intent, or names not present in the input). If a detail is missing, treat it as unknown and LOWER both the score band and the confidence rather than guessing. (2) NEVER MERGE SEPARATE FACTS INTO ONE CLAIM. Base red_flags, next_action and personalization_angle only on what the input actually says. (3) SCORE = integer 0-100 for fit to the ICP. Apply this rubric CONSISTENTLY; the band is set by how completely the lead meets the ICP and how material any caveat is: 90-100 = exceptional, near-exact fit meeting the ICP's core criteria with NO material caveat; 75-89 = strong fit with only a MINOR caveat or one small unknown; 55-74 = good but CAVEATED fit \\u2014 meets some ICP criteria while a MATERIAL caveat or key unknown (relies partly on a marketplace, unclear size, mixed business model) clearly holds it back; 35-54 = partial or uncertain fit \\u2014 a few criteria met, several missing or unknown; 15-34 = weak fit, mostly misaligned with the ICP; 0-14 = clear non-fit or an explicit disqualifier (excluded industry/type, size far outside the range). A lead that plainly matches EVERY stated ICP criterion belongs in 90-100, not the 80s; a genuine caveat (e.g. sells partly via a marketplace) must drop it into the caveated band, not keep it near the top. (4) tier follows the band: 'hot' = 75-100, 'warm' = 35-74, 'cold' = 0-34. (5) reason = 1-2 plain sentences naming the specific ICP criteria the lead meets or misses, and the caveat that set the band. (6) next_action = ONE specific, practical next step GROUNDED in this lead's own evidence (their product, stage, channel, role or notes) \\u2014 never generic filler such as 'reach out to discuss collaboration'. If the input is too sparse to be specific, state the exact information to gather first (e.g. 'confirm staff size and whether they sell on their own store before any outreach'). (7) personalization_angle = one specific, genuine hook drawn from the lead's own details (empty string if the input offers nothing genuine \\u2014 never fabricate one). (8) red_flags = a short comma-separated list of concrete disqualifiers or risks from the input (empty string if none). confidence = 'high|medium|low' ('low' when fields are sparse or the fit is uncertain). (9) Plain spoken English, no marketing fluff, no emojis, no exclamation marks. (10) Return STRICT JSON only: {\\\"score\\\":0,\\\"tier\\\":\\\"hot|warm|cold\\\",\\\"reason\\\":\\\"...\\\",\\\"next_action\\\":\\\"...\\\",\\\"personalization_angle\\\":\\\"...\\\",\\\"red_flags\\\":\\\"...\\\",\\\"confidence\\\":\\\"high|medium|low\\\"}.\";\nconst leads = $input.all();\nconst out = [];\nfor (let i = 0; i < leads.length; i++) {\n const lead = leads[i].json;\n const icp = String(lead._icp || '').trim();\n const leadFields = {\n name: lead.name || '', company: lead.company || '', role: lead.role || '',\n website: lead.website || '', notes: lead.notes || '',\n };\n const user = [\n 'IDEAL CUSTOMER PROFILE (ICP):',\n icp || '(No ICP was provided. Score general B2B fit conservatively and set confidence to \"low\".)',\n 'LEAD (use ONLY these fields \u2014 do not invent anything else):',\n JSON.stringify(leadFields),\n 'Return the assessment as strict JSON only.',\n ].join('\\n\\n');\n out.push({ json: { ...lead,\n _oai_body: {\n model: lead._model,\n messages: [\n { role: 'system', content: SYSTEM_RULES },\n { role: 'user', content: user },\n ],\n response_format: { type: 'json_object' },\n max_tokens: 500,\n temperature: 0.2,\n }\n }});\n}\nreturn out;\n"
},
"typeVersion": 2
},
{
"id": "6b1f2a07-0000-4000-8000-00000000e707",
"name": "Score Lead (OpenAI)",
"type": "n8n-nodes-base.httpRequest",
"onError": "continueRegularOutput",
"position": [
640,
200
],
"parameters": {
"url": "https://api.openai.com/v1/chat/completions",
"method": "POST",
"options": {
"timeout": 60000
},
"jsonBody": "={{ JSON.stringify($json._oai_body) }}",
"sendBody": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "openAiApi"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "6b1f2a08-0000-4000-8000-00000000e708",
"name": "Parse Score",
"type": "n8n-nodes-base.code",
"position": [
840,
200
],
"parameters": {
"jsCode": "\n// Parse Score \u2014 robust parse; honest fallback; status-driven, retryable. No fabricated scores.\nconst inputs = $input.all();\nconst prepared = $('Build Scoring Prompt').all();\nif (inputs.length !== prepared.length) throw new Error('openai/prepare item count mismatch: ' + inputs.length + ' vs ' + prepared.length);\nconst clean = s => String(s == null ? '' : s).replace(/[\\r\\n]+/g, ' ').trim();\nconst out = [];\nfor (let i = 0; i < inputs.length; i++) {\n const j = inputs[i].json;\n const lead = prepared[i].json;\n let score = null, tier = '', reason = '', nextAction = '', angle = '', redFlags = '', confidence = 'low';\n const apiFailed = !!j.error || !j.choices;\n\n if (!apiFailed) {\n try {\n const p = JSON.parse(j.choices?.[0]?.message?.content || '');\n const n = Number(p.score);\n if (Number.isFinite(n)) score = Math.max(0, Math.min(100, Math.round(n)));\n tier = clean(p.tier).toLowerCase();\n reason = clean(p.reason);\n nextAction = clean(p.next_action);\n angle = clean(p.personalization_angle);\n redFlags = clean(p.red_flags);\n confidence = clean(p.confidence).toLowerCase();\n } catch (e) { /* fallback below */ }\n }\n // A real success needs a numeric score AND a reason. Otherwise keep the row RETRYABLE:\n // blank outputs + status='failed' so a re-run re-scores it. Never write a fake score.\n const failed = apiFailed || score === null || !reason;\n if (failed) {\n score = ''; tier = ''; reason = ''; nextAction = ''; angle = ''; redFlags = ''; confidence = 'low';\n } else {\n if (!['hot','warm','cold'].includes(tier)) tier = score >= 75 ? 'hot' : (score >= 35 ? 'warm' : 'cold');\n if (!['high','medium','low'].includes(confidence)) confidence = 'medium';\n }\n\n out.push({ json: {\n row_number: lead.row_number, // match key \u2014 write to THIS exact row\n score: score,\n tier: tier,\n reason: reason,\n next_action: nextAction,\n personalization_angle: angle,\n red_flags: redFlags,\n confidence: confidence,\n status: failed ? 'failed' : 'done',\n scored_at: new Date().toISOString().slice(0, 16).replace('T', ' '),\n }});\n}\nreturn out;\n"
},
"typeVersion": 2
},
{
"id": "6b1f2a09-0000-4000-8000-00000000e709",
"name": "Write Score",
"type": "n8n-nodes-base.googleSheets",
"maxTries": 3,
"position": [
1040,
200
],
"parameters": {
"columns": {
"value": {},
"schema": [
{
"id": "row_number",
"type": "number",
"display": true,
"removed": false,
"required": false,
"displayName": "row_number",
"canBeUsedToMatch": true
},
{
"id": "name",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "name",
"canBeUsedToMatch": true
},
{
"id": "company",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "company",
"canBeUsedToMatch": true
},
{
"id": "role",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "role",
"canBeUsedToMatch": true
},
{
"id": "website",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "website",
"canBeUsedToMatch": true
},
{
"id": "notes",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "notes",
"canBeUsedToMatch": true
},
{
"id": "score",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "score",
"canBeUsedToMatch": true
},
{
"id": "tier",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "tier",
"canBeUsedToMatch": true
},
{
"id": "reason",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "reason",
"canBeUsedToMatch": true
},
{
"id": "next_action",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "next_action",
"canBeUsedToMatch": true
},
{
"id": "personalization_angle",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "personalization_angle",
"canBeUsedToMatch": true
},
{
"id": "red_flags",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "red_flags",
"canBeUsedToMatch": true
},
{
"id": "confidence",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "confidence",
"canBeUsedToMatch": true
},
{
"id": "status",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "status",
"canBeUsedToMatch": true
},
{
"id": "scored_at",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "scored_at",
"canBeUsedToMatch": true
}
],
"mappingMode": "autoMapInputData",
"matchingColumns": [
"row_number"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {
"cellFormat": "RAW"
},
"operation": "update",
"sheetName": {
"__rl": true,
"mode": "name",
"value": "leads"
},
"documentId": {
"__rl": true,
"mode": "url",
"value": "PASTE_YOUR_GOOGLE_SHEET_URL"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"retryOnFail": true,
"typeVersion": 4,
"waitBetweenTries": 3000
},
{
"id": "6b1f2a10-0000-4000-8000-00000000e710",
"name": "Qualified Leads (\u2265 min score)",
"type": "n8n-nodes-base.code",
"position": [
1240,
200
],
"parameters": {
"jsCode": "\n// Qualified Leads \u2014 POST-SCORE qualification. Every pending lead has ALREADY been scored once above;\n// this forwards only leads whose score is at/above the Minimum Qualified Score. It does NOT skip or\n// cheapen scoring \u2014 it just re-joins lead identity so users can CHAIN further automation off this node\n// (send to CRM, draft outreach, Slack, etc.).\nconst cfg = $('\u2b50 Configure Your Run').first().json;\nlet min = Number(cfg.min_qualified_score);\nif (!Number.isFinite(min)) min = 0;\nmin = Math.max(0, Math.min(100, min)); // belt-and-braces: Select Pending already rejects out-of-range\nconst scored = $('Parse Score').all();\nconst leads = $('Build Scoring Prompt').all();\nconst out = [];\nfor (let i = 0; i < scored.length; i++) {\n const s = scored[i].json;\n const L = (leads[i] && leads[i].json) || {};\n const n = Number(s.score);\n if (s.status === 'done' && Number.isFinite(n) && n >= min) {\n out.push({ json: {\n row_number: s.row_number,\n name: L.name || '', company: L.company || '', role: L.role || '', website: L.website || '',\n score: n, tier: s.tier, reason: s.reason, next_action: s.next_action,\n personalization_angle: s.personalization_angle, red_flags: s.red_flags, confidence: s.confidence,\n }});\n }\n}\nreturn out;\n"
},
"typeVersion": 2
},
{
"id": "6b1f2a51-0000-4000-8000-00000000e751",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1120,
20
],
"parameters": {
"width": 620,
"height": 900,
"content": "## \ud83c\udfaf Lead Qualifier & Scorer\n\nDecide who to contact first. Scores every lead in your Google Sheet 0\u2013100 against your own Ideal Customer Profile \u2014 for founders, agencies, SDRs and small sales teams.\n\n### How it works\n1. **Read** \u2014 pulls your leads from the `leads` tab of your Google Sheet.\n2. **Select** \u2014 skips rows already marked `done`, so re-running is safe and won't re-charge them.\n3. **Score** \u2014 one OpenAI call per lead, judged against the ICP you wrote in plain English.\n4. **Write back** \u2014 score, tier (hot/warm/cold), reason, next action, personalisation angle, red flags and confidence go back onto the lead's own row.\n5. **Hand off** \u2014 leads at or above your Minimum Qualified Score are emitted from the **Qualified Leads** output, ready to chain into a CRM, an alert, or your outreach.\n\n### Setup steps\n- [ ] Copy the companion Google Sheet \u2014 open [this link](https://docs.google.com/spreadsheets/d/10FhTFY6eMKU2daCXifpBCw_RpitrU1S_fqb6bYW87LU/copy), sign in to Google if asked, then click **Make a copy**\n- [ ] Add your **Google Sheets** credential to *Read Leads* and *Write Score*\n- [ ] Add your **OpenAI** credential to *Score Lead (OpenAI)*\n- [ ] Paste **your copy's** Sheet URL into *Read Leads* and *Write Score*\n- [ ] Write your ICP in one sentence in **\u2b50 Configure Your Run**, then press **Execute workflow**\n\n### Customization\n- **Your ICP:** `icp_description` \u2014 one plain sentence describing your ideal customer. This is the whole scoring standard; change it and every score changes.\n- **Volume:** `max_per_run` \u2014 1\u2013100 leads per run.\n- **Qualification bar:** `min_qualified_score` (0\u2013100) \u2014 every pending lead is still scored; leave it at 0 to pass all of them through.\n- **Re-scoring:** clear the `status` column; failed rows retry automatically.\n\nBuilt by **FirstDropHQ** \u2014 firstdrophq.com"
},
"typeVersion": 1
},
{
"id": "6b1f2a52-0000-4000-8000-00000000e752",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-440,
20
],
"parameters": {
"color": 7,
"width": 840,
"height": 360,
"content": "## 1. Read your leads\n\nReads the `leads` tab of your Google Sheet and selects only the leads that have not been scored yet."
},
"typeVersion": 1
},
{
"id": "6b1f2a53-0000-4000-8000-00000000e753",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
400,
20
],
"parameters": {
"color": 7,
"width": 600,
"height": 360,
"content": "## 2. Score against your ICP\n\nBuilds the scoring prompt from your one-sentence Ideal Customer Profile and sends each lead to OpenAI once, under rules that forbid inventing facts about the lead."
},
"typeVersion": 1
},
{
"id": "6b1f2a54-0000-4000-8000-00000000e754",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1000,
20
],
"parameters": {
"color": 7,
"width": 400,
"height": 360,
"content": "## 3. Write back and hand off\n\nWrites the score, tier and reasoning onto the lead's own row. Leads at or above your Minimum Qualified Score are emitted from the **Qualified Leads** output \u2014 connect your CRM or alert here."
},
"typeVersion": 1
},
{
"id": "6b1f2a55-0000-4000-8000-00000000e755",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
500,
440
],
"parameters": {
"color": 3,
"width": 600,
"height": 310,
"content": "## \u26a0\ufe0f Runs on your own OpenAI key\n\nEvery lead is one OpenAI call **billed to your key** \u2014 well under $0.0005 per lead on `gpt-4o-mini` (comfortably under $0.05 per 100 leads). Rows marked `done` are never re-charged \u2014 but if the write-back to your Sheet fails after scoring (rare; it retries first), those rows re-bill on the next run.\n\nNo key yet? Create one at **platform.openai.com \u2192 API keys**.\n\n**Score quality tracks ICP quality** \u2014 a vague one-word ICP produces vague, low-confidence scores."
},
"typeVersion": 1
}
],
"settings": {
"executionOrder": "v1"
},
"connections": {
"Read Leads": {
"main": [
[
{
"node": "Select Pending",
"type": "main",
"index": 0
}
]
]
},
"Parse Score": {
"main": [
[
{
"node": "Write Score",
"type": "main",
"index": 0
}
]
]
},
"Write Score": {
"main": [
[
{
"node": "Qualified Leads (\u2265 min score)",
"type": "main",
"index": 0
}
]
]
},
"Select Pending": {
"main": [
[
{
"node": "Build Scoring Prompt",
"type": "main",
"index": 0
}
]
]
},
"Score Lead (OpenAI)": {
"main": [
[
{
"node": "Parse Score",
"type": "main",
"index": 0
}
]
]
},
"Build Scoring Prompt": {
"main": [
[
{
"node": "Score Lead (OpenAI)",
"type": "main",
"index": 0
}
]
]
},
"\u2b50 Configure Your Run": {
"main": [
[
{
"node": "Read Leads",
"type": "main",
"index": 0
}
]
]
},
"When clicking 'Execute workflow'": {
"main": [
[
{
"node": "\u2b50 Configure Your Run",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googleSheetsOAuth2ApiopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow reads leads from a Google Sheets spreadsheet, scores each pending lead against your Ideal Customer Profile using the OpenAI Chat Completions API, writes the results back to the sheet, and outputs only leads that meet your minimum qualified score. Starts when you…
Source: https://n8n.io/workflows/17427/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This n8n workflow automatically generates presentation-style "screen recording" videos with AI-generated slides and a talking head avatar overlay. You provide a topic and intention, and the workflow h
HTTP Request, N8N Nodes Veed, Google Drive +1
Monitor Google Drive folder, parsing PDF, DOCX and image file into a destination folder, ready for further processing (e.g. RAG ingestion, translation, etc.) Keep processing log in Google Sheet and se
Google Drive Trigger, Google Drive, HTTP Request +2
This workflow is designed for individuals and businesses looking to streamline the creation of engaging promotional videos. Whether you're marketing a product or developing a personal brand, this AI-d
HTTP Request, Google Cloud Storage, Google Sheets
Automatically create YouTube short videos using Elevenlabs, Hailuo AI. Uses httpRequest, googleCloudStorage, googleSheets. Event-driven trigger; 38 nodes.
HTTP Request, Google Cloud Storage, Google Sheets
Transform trending Google News articles into engaging YouTube Shorts with this fully automated workflow. Save time and effort while creating dynamic, eye-catching videos that are perfect for content c
HTTP Request, Google Cloud Storage, Google Sheets +1