← All Sales & Outreach
Predictleads email verification with BillionVerify
PredictLeads delivers company intelligence and buying signals to help sales and revenue teams identify and prioritise outreach targets. Because the platform surfaces contact data and company email patterns for prospecting, verifying those addresses with BillionVerify before outreach is essential to maintaining high deliverability and protecting the sender reputation of your sales domain.
Why verify before the send
Prospect email addresses sourced from intelligence tools are often unverified and can include outdated contacts, role-based addresses, and disposable emails. Sending cold outreach to invalid addresses generates hard bounces that damage your domain reputation and risk landing future emails in spam. BillionVerify validates every address before it enters your sequences, so only reachable prospects receive outreach.
Ready-to-use n8n workflow
Import this workflow into n8n — it verifies every address with BillionVerify before Predictleads sends, so only deliverable contacts are emailed. Install the BillionVerify community node first, then add your API key. Adapted from this n8n template
verify-emails-in-predictleads.json
{
"name": "Automate Job applications 🧑🏻💼📄with Chatbot, PredictLeads and ScrapegraphAI + BillionVerify",
"nodes": [
{
"id": "9c0b9b16-0e6e-4d91-ab72-f0e93e4f220b",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-640,
832
],
"webhookId": "b0d13c2b-fc2d-4c26-8d83-e63ef4a316d5",
"parameters": {
"options": {
"responseMode": "responseNodes"
}
},
"typeVersion": 1.4
},
{
"id": "5e084958-ce74-410b-b9ec-248157c4a398",
"name": "OpenAI Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
272,
1520
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini",
"cachedResultName": "gpt-4.1-mini"
},
"options": {},
"builtInTools": {}
},
"credentials": {
"openAiApi": {
"id": "TefveNaDaMERl1hY",
"name": "OpenAi account (Eure)"
}
},
"typeVersion": 1.3
},
{
"id": "c0a4d07e-c795-4234-bf9b-5af8a59fdb2c",
"name": "Context7",
"type": "@n8n/n8n-nodes-langchain.mcpClientTool",
"position": [
-336,
1056
],
"parameters": {
"options": {},
"endpointUrl": "https://mcp.context7.com/mcp",
"authentication": "headerAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "8IJX1tJ5g6LPA0NR",
"name": "Context7"
}
},
"typeVersion": 1.2
},
{
"id": "0551424c-5338-40b6-8b9a-a4cd9cf095b5",
"name": "PredictLeads",
"type": "@n8n/n8n-nodes-langchain.mcpClientTool",
"position": [
-224,
1056
],
"parameters": {
"include": "selected",
"options": {},
"endpointUrl": "https://mcp.predictleads.com/",
"includeTools": [
"predictleads_job_opening",
"predictleads_discover_job_openings"
],
"authentication": "multipleHeadersAuth"
},
"credentials": {
"httpMultipleHeadersAuth": {
"id": "Wi8DEie5g9eQmTYt",
"name": "Multiple Headers PredictLeads"
}
},
"typeVersion": 1.2
},
{
"id": "141ca5a1-ba2a-407d-a9e5-d04e4314339f",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
880,
1584
],
"parameters": {
"contextWindowLength": 20
},
"typeVersion": 1.3
},
{
"id": "e70f9ff8-12a2-485f-b67c-eb0b0e3ca841",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
592,
800
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"array\",\n\t\"properties\": {\n\t\t\"link\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"typeVersion": 1.3
},
{
"id": "cc86414f-a623-4a3a-9e77-96cd409f4f02",
"name": "Loop Over Items",
"type": "n8n-nodes-base.splitInBatches",
"position": [
1184,
672
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "8e57f53b-152c-4783-91d5-ae5a882471c4",
"name": "Google Gemini Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
2224,
752
],
"parameters": {
"options": {}
},
"credentials": {
"googlePalmApi": {
"id": "AaNPKXAphyMzRgfA",
"name": "Google Gemini(PaLM) (Eure)"
}
},
"typeVersion": 1
},
{
"id": "7f9a2404-7177-48bd-a44f-a4da855dc04d",
"name": "Chat",
"type": "@n8n/n8n-nodes-langchain.chat",
"position": [
480,
1008
],
"webhookId": "236633f4-46a7-4ccf-b020-22fe02d6763d",
"parameters": {
"message": "={{ $json.message }}",
"options": {
"memoryConnection": true
}
},
"typeVersion": 1.2
},
{
"id": "8c843fce-a962-47fa-8b9f-c209f1d4a89c",
"name": "Create email",
"type": "@n8n/n8n-nodes-langchain.chatHitlTool",
"position": [
2432,
800
],
"webhookId": "cf7c44cf-8e3b-470b-9dfb-355d874d9ef5",
"parameters": {
"message": "=The agent wants to call {{ $tool.name }}\n\n{{ JSON.stringify($tool.parameters, null, 2) }}",
"options": {},
"approvalOptions": {
"values": {
"approvalType": "double"
}
}
},
"typeVersion": 1.2
},
{
"id": "c6906efa-6186-4399-b770-5ba3ce9184d5",
"name": "Chat1",
"type": "@n8n/n8n-nodes-langchain.chat",
"position": [
2928,
1104
],
"webhookId": "3f871230-27a9-4fa1-a8c2-d2c4b7ec4069",
"parameters": {
"message": "={{ $json.output }}",
"options": {
"memoryConnection": true
}
},
"typeVersion": 1.2
},
{
"id": "2775f022-3c08-4669-8c23-d9a5371cb598",
"name": "Limit",
"type": "n8n-nodes-base.limit",
"disabled": true,
"position": [
960,
672
],
"parameters": {},
"typeVersion": 1
},
{
"id": "b305684c-8c7f-4a95-907c-a35dba17450a",
"name": "When Executed by Another Workflow",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"position": [
2400,
1552
],
"parameters": {
"workflowInputs": {
"values": [
{
"name": "emailTo"
},
{
"name": "subject"
},
{
"name": "text"
}
]
}
},
"typeVersion": 1.1
},
{
"id": "7291f889-6a60-4e3b-8a7f-1a75b1ffa5c0",
"name": "Create a draft",
"type": "n8n-nodes-base.gmail",
"position": [
2848,
1552
],
"webhookId": "e220a165-b52c-49df-b201-c25f3bbfd278",
"parameters": {
"message": "={{ $('When Executed by Another Workflow').item.json.text }}",
"options": {
"sendTo": "={{ $('When Executed by Another Workflow').item.json.emailTo }}",
"attachmentsUi": {
"attachmentsBinary": [
{
"property": "data"
}
]
}
},
"subject": "={{ $('When Executed by Another Workflow').item.json.subject }}",
"resource": "draft"
},
"credentials": {
"gmailOAuth2": {
"id": "nyuHvSX5HuqfMPlW",
"name": "Gmail account (n3w.it)"
}
},
"typeVersion": 2.2
},
{
"id": "0d6ff9a6-3e14-4c04-957f-38512efed081",
"name": "Job application Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
2288,
592
],
"parameters": {
"text": "=Email annuncio: {{ $json.result.email }}\nPosizione aperta annuncio: {{ $json.result.position }}\n\nTesto annuncio: {{ $json.result.text }}",
"options": {
"systemMessage": "You are an expert in job applications and professional email communication.\n\nYour task is to generate a job application email based on the information provided in each request.\n\nYou MUST use the tool **\"Create email\"** to generate:\n\n* The subject line of the email\n* The full body text of the email\n\nAlways ensure the email is:\n\n* Professional and well-structured\n* Clear and concise\n* Tailored to the job position provided\n* Written in a confident but polite tone\n\nUse the following personal information of the candidate when generating the email:\n\nName: XXX\nBorn: XXX\nResident: XXX\nOther: Dynamic person, strong problem-solving skills\n\nDo not invent additional personal details unless explicitly provided.\nIf any required information is missing, write the email using only the available data.\n\nThe final output must be ready to send.\n"
},
"promptType": "define"
},
"typeVersion": 3.1
},
{
"id": "53913e61-d146-4ad5-8c3d-ecc9fa46ba09",
"name": "Send email",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"position": [
2384,
1008
],
"parameters": {
"workflowId": {
"__rl": true,
"mode": "id",
"value": "=ZhpFW0At1ondVya0",
"cachedResultUrl": "/workflow/=ZhpFW0At1ondVya0"
},
"workflowInputs": {
"value": {
"text": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('text', ``, 'string') }}",
"emailTo": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('emailTo', ``, 'string') }}",
"subject": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('subject', ``, 'string') }}"
},
"schema": [
{
"id": "emailTo",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "emailTo",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "subject",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "subject",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "text",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "text",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"typeVersion": 2.2
},
{
"id": "c9a51e83-6dea-4738-af93-350c7d3d0003",
"name": "Get CV",
"type": "n8n-nodes-base.httpRequest",
"position": [
2624,
1552
],
"parameters": {
"url": "https://xxx/cv.pdf",
"options": {}
},
"typeVersion": 4.4
},
{
"id": "7078edd1-57b2-4d0b-bd93-90a200cddfde",
"name": "Scrape Job",
"type": "n8n-nodes-scrapegraphai.scrapegraphAi",
"position": [
1488,
688
],
"parameters": {
"userPrompt": "Extract the email address to which applications should be sent. If no email address is available, return \"null\". Also extract the open job position.",
"websiteUrl": "={{ $json.output }}",
"outputSchema": "{\n \"type\": \"object\",\n \"title\": \"ProductSchema\",\n \"properties\": {\n \"email\": {\n \"type\": \"string\",\n \"title\": \"email\",\n \"description\": \"Email to send CV\"\n },\n \"position\": {\n \"type\": \"string\",\n \"title\": \"position\",\n \"description\": \"Open job position\"\n },\n \"text\": {\n \"type\": \"string\",\n \"title\": \"text\",\n \"description\": \"Complete text\"\n }\n },\n \"required\": [\"email\", \"position\", \"text\"]\n}",
"useOutputSchema": true
},
"credentials": {
"scrapegraphAIApi": {
"id": "EOxCPnl9IynxgpyB",
"name": "ScrapegraphAI account"
}
},
"typeVersion": 1
},
{
"id": "0752da9b-d89b-46ba-8afe-8849356fa380",
"name": "Contain email?",
"type": "n8n-nodes-base.if",
"position": [
1760,
688
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "846b1ced-a841-4fa7-bd13-5f893df93225",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $json.result.email }}",
"rightValue": "=@"
}
]
}
},
"typeVersion": 2.3
},
{
"id": "ffb70025-0e02-46ba-b533-7eaed5aced2d",
"name": "Links Extractor",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
448,
592
],
"parameters": {
"text": "={{ $json.message }}",
"batching": {},
"messages": {
"messageValues": [
{
"message": "Extract the links"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.9
},
{
"id": "32df0f47-36fc-4f6c-9686-1e93d013e537",
"name": "PredictLeads Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-416,
832
],
"parameters": {
"options": {
"systemMessage": "You are an AI automation agent running inside an n8n workflow.\n\nYour mission is to help the workflow by answering user requests and orchestrating tool usage when needed.\nAlways follow the rules below exactly.\n\nTOOL USAGE RULES (CRITICAL)\n1) For any request involving company research (e.g., information about a company, firmographics, funding, headcount, industry, competitors, subsidiaries, acquisitions, locations, executives, news about a company, etc.):\n - You MUST consult the tool \"Context7\" FIRST.\n - Only after using Context7, if additional or verified company data is needed, you MAY call \"PredictLeads\".\n - Never call PredictLeads before Context7 for company research requests.\n\n2) If the request is NOT company research, you may decide whether tools are necessary. Do not use tools unnecessarily.\n\nOUTPUT FORMAT (MANDATORY)\nYou MUST always output a single valid JSON object, nothing else (no markdown, no extra text).\n\nThe JSON schema must be:\n{\n \"list\": boolean,\n \"output\": string\n}\n\n- \"list\" must be set to true ONLY when the result is a list from:\n a) a job search / job listings request, OR\n b) a list of companies, OR\n c) data originating from PredictLeads (including lists of results returned by PredictLeads).\n- Otherwise set \"list\" to false.\n\n- \"output\" must contain the COMPLETE final message to the user (fully formed, ready to be shown).\n Include all relevant details, steps, and results in plain text.\n\nGENERAL BEHAVIOR\n- Be clear, concise, and actionable.\n- If information is uncertain, state assumptions explicitly.\n- If the user request is ambiguous, make a best-effort interpretation and proceed, minimizing follow-up questions.\n- Do not expose internal tool call details unless the user explicitly asks for them."
}
},
"typeVersion": 3.1
},
{
"id": "55457900-e1b9-4a94-96c4-8de46a91af4c",
"name": "Parser",
"type": "n8n-nodes-base.code",
"position": [
-64,
832
],
"parameters": {
"jsCode": "for (const item of $input.all()) {\n try {\n let rawOutput = item.json.output;\n\n rawOutput = String(rawOutput)\n .replace(/```json\\n?/gi, \"\")\n .replace(/```\\n?/g, \"\")\n .trim();\n\n rawOutput = rawOutput.replace(/\\\\'/g, \"'\");\n\n const parsedData = JSON.parse(rawOutput);\n const cleanData = parsedData.properties || parsedData;\n\n // Caso 1: output \"message\" (come nel tuo esempio)\n if (typeof cleanData.message === \"string\" && cleanData.message.trim()) {\n item.json = {\n list: !!cleanData.list,\n message: cleanData.message.trim(),\n };\n continue;\n }\n\n // Caso 2: output \"card\" (title/prompt) come nello script originale\n if (!cleanData.title || !cleanData.prompt) {\n throw new Error(\"Campi obbligatori mancanti: (message) oppure (title e prompt)\");\n }\n\n item.json = {\n title: String(cleanData.title).trim(),\n style: cleanData.style ? String(cleanData.style).trim() : \"\",\n prompt: String(cleanData.prompt).trim(),\n negativeTags: cleanData.negativeTags ? String(cleanData.negativeTags).trim() : \"\",\n };\n } catch (error) {\n throw new Error(\"Errore nel parsing JSON: \" + error.message);\n }\n}\n\nreturn $input.all();"
},
"typeVersion": 2
},
{
"id": "a39c4a07-c0fb-46d1-b366-4945e39520a9",
"name": "Split Out",
"type": "n8n-nodes-base.splitOut",
"position": [
736,
672
],
"parameters": {
"options": {},
"fieldToSplitOut": "output"
},
"typeVersion": 1
},
{
"id": "0387d1ca-d76c-4d95-a3cc-c24e69788fb4",
"name": "Chat2",
"type": "@n8n/n8n-nodes-langchain.chat",
"position": [
1968,
880
],
"webhookId": "3f871230-27a9-4fa1-a8c2-d2c4b7ec4069",
"parameters": {
"message": "=This ad doesn't contain an email address. You'll likely need to apply directly from the website. Here's the link: {{ $json.website_url }}",
"options": {
"memoryConnection": true
}
},
"typeVersion": 1.2
},
{
"id": "8c1b5b5b-7aaa-4dad-b7ec-2b53d967d3a0",
"name": "If list?",
"type": "n8n-nodes-base.if",
"position": [
160,
832
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "ee88996d-2d85-4692-a6a5-f978bd1674da",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.list }}",
"rightValue": false
}
]
}
},
"typeVersion": 2.3
},
{
"id": "0f3b659a-bee8-4cb4-883d-13a909b348b9",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-496,
96
],
"parameters": {
"width": 800,
"height": 544,
"content": "## Chatbot Job Apply System with PredictLeads & Scrapegraph AI\n\nThis Chatbot automates the process of discovering job openings and generating tailored job application emails. \n\nIt combines AI agents, web scraping, and email drafting to streamline job applications.\n\n### How it works:\n\nThis workflow starts from a Chat Trigger and uses a LangChain-based PredictLeads Agent to interpret user intent and optionally perform company research via Context7 and PredictLeads. The agent output is parsed into structured JSON to determine whether to return a direct response or extract and process job URLs. For each job link, the workflow scrapes position details and contact email using ScrapegraphAI, then conditionally generates a tailored application email via a Gemini-powered agent. The email is formatted using a dedicated tool and a draft is created in Gmail with the CV attached, while maintaining human-in-the-loop approval and structured error handling.\n\n### Setup steps:\n\nConfigure required credentials for OpenAI, Google Gemini, Context7, PredictLeads (with appropriate headers), ScrapegraphAI, and Gmail OAuth2. Ensure the CV is publicly accessible via the HTTP Request node and verify the “Send email” workflow ID matches the current workflow. Optionally customize system prompts in the PredictLeads Agent and Job Application Agent to include candidate-specific information. The Chat Trigger and Simple Memory nodes require no setup but must remain correctly connected to preserve conversation context and workflow continuity.\n"
},
"typeVersion": 1
},
{
"id": "580d8879-5cd5-4d0c-8e7a-9edf9bd88bf2",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-496,
688
],
"parameters": {
"color": 7,
"width": 800,
"height": 592,
"content": "## STEP 1 - PredictLeads Agent \n**[PredictLeads](https://predictleads.com/) Agent processes the request** – A LangChain agent determines the user's intent. If the request involves **company research**, it first queries **Context7**, then optionally **PredictLeads** for deeper data."
},
"typeVersion": 1
},
{
"id": "97d26b08-34f2-4e0e-ab89-ce696fdb7074",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
416,
480
],
"parameters": {
"color": 7,
"width": 704,
"height": 480,
"content": "## STEP 2 - Extract Links\nExtract job posting URLs from the user's input."
},
"typeVersion": 1
},
{
"id": "e03b3653-a8d4-44c9-bdf0-ce58fb1dedd2",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1152,
480
],
"parameters": {
"color": 7,
"width": 736,
"height": 480,
"content": "## STEP 3 - Scrape Job\nThe Scrape Job node (powered by [ScrapegraphAI](https://dashboard.scrapegraphai.com/?via=n3witalia)) extracts: Email address to send the application to, Job position title, Full job description text"
},
"typeVersion": 1
},
{
"id": "ad56f348-b8de-410e-ae29-4aa263d52898",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1920,
480
],
"parameters": {
"color": 7,
"width": 880,
"height": 672,
"content": "## STEP 4 - Job Application Agent\nA Gemini-powered agent generates a professional email using: Candidate's personal info (name, location, skills), Job position and description. A tool (Create email) to format the subject and body"
},
"typeVersion": 1
},
{
"id": "f70961ce-02a9-48e0-8965-bc6f1f81996e",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
2320,
1424
],
"parameters": {
"color": 7,
"width": 880,
"height": 320,
"content": "## STEP 5 - Send email with CV\n The agent triggers the Send email workflow, which: Fetches the CV from a public URL, Creates a draft in Gmail with the CV attached"
},
"typeVersion": 1
},
{
"id": "db743866-7b48-40b4-a891-9be23b60429d",
"name": "Sticky Note9",
"type": "n8n-nodes-base.stickyNote",
"position": [
416,
-304
],
"parameters": {
"color": 7,
"width": 736,
"height": 736,
"content": "## MY NEW YOUTUBE CHANNEL\n👉 [Subscribe to my new **YouTube channel**](https://youtube.com/@n3witalia). Here I’ll share videos and Shorts with practical tutorials and **FREE templates for n8n**.\n\n[](https://youtube.com/@n3witalia)"
},
"typeVersion": 1
},
{
"parameters": {
"operation": "verify",
"email": "={{ $json.email || $json.Email }}",
"additionalOptions": {}
},
"type": "n8n-nodes-billionverify.billionVerify",
"typeVersion": 1,
"position": [
2488,
1552
],
"name": "Verify Email (BillionVerify)",
"credentials": {
"billionVerifyApi": {
"id": "",
"name": "BillionVerify account"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "is-deliverable",
"leftValue": "={{ $json.is_deliverable }}",
"rightValue": "",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
}
}
]
}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
2668,
1552
],
"name": "IF deliverable"
}
],
"connections": {
"Chat1": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Chat2": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Limit": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Get CV": {
"main": [
[
{
"node": "Verify Email (BillionVerify)",
"type": "main",
"index": 0
}
]
]
},
"Parser": {
"main": [
[
{
"node": "If list?",
"type": "main",
"index": 0
}
]
]
},
"Context7": {
"ai_tool": [
[
{
"node": "PredictLeads Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"If list?": {
"main": [
[
{
"node": "Links Extractor",
"type": "main",
"index": 0
}
],
[
{
"node": "Chat",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "Limit",
"type": "main",
"index": 0
}
]
]
},
"Scrape Job": {
"main": [
[
{
"node": "Contain email?",
"type": "main",
"index": 0
}
]
]
},
"Send email": {
"ai_tool": [
[
{
"node": "Create email",
"type": "ai_tool",
"index": 0
}
]
]
},
"Create email": {
"ai_tool": [
[
{
"node": "Job application Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"PredictLeads": {
"ai_tool": [
[
{
"node": "PredictLeads Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "PredictLeads Agent",
"type": "ai_memory",
"index": 0
},
{
"node": "Job application Agent",
"type": "ai_memory",
"index": 0
},
{
"node": "Chat1",
"type": "ai_memory",
"index": 0
},
{
"node": "Chat",
"type": "ai_memory",
"index": 0
},
{
"node": "Chat2",
"type": "ai_memory",
"index": 0
}
]
]
},
"Contain email?": {
"main": [
[
{
"node": "Job application Agent",
"type": "main",
"index": 0
}
],
[
{
"node": "Chat2",
"type": "main",
"index": 0
}
]
]
},
"Links Extractor": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[],
[
{
"node": "Scrape Job",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "PredictLeads Agent",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Links Extractor",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"PredictLeads Agent": {
"main": [
[
{
"node": "Parser",
"type": "main",
"index": 0
}
]
]
},
"Job application Agent": {
"main": [
[
{
"node": "Chat1",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Links Extractor",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Google Gemini Chat Model1": {
"ai_languageModel": [
[
{
"node": "Job application Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "PredictLeads Agent",
"type": "main",
"index": 0
}
]
]
},
"When Executed by Another Workflow": {
"main": [
[
{
"node": "Get CV",
"type": "main",
"index": 0
}
]
]
},
"Verify Email (BillionVerify)": {
"main": [
[
{
"node": "IF deliverable",
"type": "main",
"index": 0
}
]
]
},
"IF deliverable": {
"main": [
[
{
"node": "Create a draft",
"type": "main",
"index": 0
}
],
[]
]
}
},
"settings": {
"binaryMode": "separate",
"availableInMCP": false,
"executionOrder": "v1"
}
}Workflow templates with Predictleads
Ready-to-use workflows that verify emails before Predictleads sends.
How it works
- 1
Connect BillionVerify to PredictLeads via the n8n community node, Integrately, or the BillionVerify REST API.
- 2
Trigger email verification whenever PredictLeads surfaces a new contact or buying signal with an associated email address.
- 3
BillionVerify performs DNS, MX, and SMTP checks to confirm whether the address is deliverable, disposable, or role-based.
- 4
Contacts that pass verification are pushed to your CRM or outreach tool; those that fail are quarantined for manual review.
- 5
Your sales sequences receive only clean, validated prospects, resulting in lower bounce rates and better email deliverability.
When to use this
Scrub PredictLeads contacts before adding to outreach sequences
When PredictLeads surfaces new prospect contacts based on buying signals, pass each email through BillionVerify before adding them to your sales sequences. Filtering out invalid and risky addresses keeps bounce rates low and protects your sending infrastructure.
Filter catch-all and role-based addresses from prospecting exports
Company intelligence data often includes generic inboxes like contact@ or info@, which rarely reach decision-makers and can harm deliverability. BillionVerify identifies these address types so your team focuses outreach on verified personal inboxes.
Maintain a clean CRM pipeline from enrichment data
As PredictLeads enriches your CRM with new company and contact data, BillionVerify validates the associated emails in real time. Only records with confirmed deliverable addresses are created, keeping your pipeline data trustworthy from the start.
FAQ
Why is email verification especially important for sales intelligence data?
Sales intelligence platforms aggregate contact data from many sources, and accuracy can vary. Some emails may be outdated, belong to former employees, or be role-based. Verifying before outreach prevents hard bounces that accumulate and damage your domain's sending reputation.
Can BillionVerify handle bulk verification of large PredictLeads exports?
Yes. The BillionVerify REST API supports bulk verification, allowing you to process large contact lists from PredictLeads exports in a single request and receive structured results you can filter before importing into your CRM.
What happens to addresses flagged as catch-all by BillionVerify?
Catch-all addresses come from servers that accept all mail, making it impossible to confirm whether the specific mailbox exists. BillionVerify flags these separately so your team can decide whether to include or exclude them based on your acceptable risk threshold.
Does verifying emails slow down our prospecting workflow?
Single-address verification via the API typically completes in under a second. For bulk lists, asynchronous processing means your workflow is not blocked while results are returned, keeping your prospecting pipeline moving at speed.
Verify emails in Predictleads
Create a free account, grab your API key, and stop bounces before they happen.
Get started free