This workflow follows the HTTP Request → Postgres 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": "03 Scoring: Score, Tailor, Cover Letter",
"nodes": [
{
"parameters": {},
"id": "trg-manual",
"name": "Manual / After Dedup",
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
180,
300
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "SELECT id, raw_text FROM app.resumes WHERE is_default = true ORDER BY created_at DESC LIMIT 1;",
"options": {}
},
"id": "pg-resume",
"name": "Get Default Resume",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
380,
300
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "executeQuery",
"query": "SELECT id, title, company_name, coalesce(description,'') AS description FROM app.jobs WHERE status = 'deduped' ORDER BY discovered_at ASC LIMIT 10;",
"options": {}
},
"id": "pg-jobs",
"name": "Get Jobs to Score",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
600,
300
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "=http://{{ $env.OLLAMA_HOST || 'ollama' }}:{{ $env.OLLAMA_PORT || '11434' }}/api/generate",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ model: $env.OLLAMA_MODEL_REASONING || 'llama3.1:8b', stream: false, format: 'json', options: { temperature: 0.1, num_ctx: 8192 }, system: 'You are a strict technical recruiter. Score how well the candidate matches the job. Respond ONLY with JSON: {\"score\": <integer 0-100>, \"skills_match\": <0-100>, \"experience_match\": <0-100>, \"reasoning\": \"<two sentences>\"}.', prompt: 'MASTER RESUME:\\n' + $('Get Default Resume').first().json.raw_text + '\\n\\nJOB: ' + $json.title + ' at ' + $json.company_name + '\\n' + ($json.description || '').slice(0, 3000) }) }}",
"options": {
"timeout": 300000
}
},
"id": "http-score",
"name": "Score Job",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
820,
300
]
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "// Parse the score JSON, build the persist SQL, and decide apply/park.\nfunction q(s){ return String(s==null?'':s).replace(/'/g, \"''\"); }\nconst raw = $json.response || '';\nlet p; try { p = JSON.parse(raw); } catch(e){ const m = raw.match(/\\{[\\s\\S]*\\}/); p = m ? JSON.parse(m[0]) : { score: 0 }; }\nconst job = $('Get Jobs to Score').item.json;\nconst resume = $('Get Default Resume').first().json;\nconst score = Math.max(0, Math.min(100, Number(p.score) || 0));\nconst minApply = Number($env.SCORE_MIN_TO_APPLY || 70);\nconst apply = score >= minApply;\nconst breakdown = q(JSON.stringify({ skills_match: p.skills_match ?? null, experience_match: p.experience_match ?? null }));\nconst model = $env.OLLAMA_MODEL_REASONING || 'llama3.1:8b';\nconst query = `INSERT INTO app.job_scores (job_id, resume_id, score, breakdown, reasoning, model) VALUES ('${job.id}','${resume.id}',${score},'${breakdown}'::jsonb,'${q(p.reasoning)}','${q(model)}') ON CONFLICT (job_id, resume_id) DO UPDATE SET score = EXCLUDED.score, breakdown = EXCLUDED.breakdown, reasoning = EXCLUDED.reasoning; UPDATE app.jobs SET status = '${apply ? 'scored' : 'parked'}' WHERE id = '${job.id}';`;\nreturn { json: { job_id: job.id, resume_id: resume.id, title: job.title, company: job.company_name, description: job.description, resume_text: resume.raw_text, score, apply, query } };"
},
"id": "code-parse",
"name": "Parse Score",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1040,
300
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "={{ $json.query }}",
"options": {}
},
"id": "pg-savescore",
"name": "Save Score",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
1260,
300
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"leftValue": "={{ $('Parse Score').item.json.apply }}",
"rightValue": true,
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
}
}
],
"combinator": "and"
}
},
"id": "if-apply",
"name": "Apply?",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
1480,
300
]
},
{
"parameters": {
"method": "POST",
"url": "=http://{{ $env.OLLAMA_HOST || 'ollama' }}:{{ $env.OLLAMA_PORT || '11434' }}/api/generate",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ model: $env.OLLAMA_MODEL_REASONING || 'llama3.1:8b', stream: false, options: { temperature: 0.3, num_ctx: 8192 }, system: 'You are an expert resume editor. Rewrite and reorder the resume to target the job. CRITICAL RULE: use ONLY facts present in the master resume. Never invent employers, titles, dates, skills, metrics, or achievements. If a required skill is absent, do not claim it. Output clean markdown.', prompt: 'MASTER RESUME:\\n' + $('Parse Score').item.json.resume_text + '\\n\\nTARGET JOB: ' + $('Parse Score').item.json.title + ' at ' + $('Parse Score').item.json.company + '\\n' + ($('Parse Score').item.json.description || '').slice(0, 3000) }) }}",
"options": {
"timeout": 300000
}
},
"id": "http-tailor",
"name": "Tailor Resume",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1700,
220
]
},
{
"parameters": {
"method": "POST",
"url": "=http://{{ $env.OLLAMA_HOST || 'ollama' }}:{{ $env.OLLAMA_PORT || '11434' }}/api/generate",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ model: $env.OLLAMA_MODEL_REASONING || 'llama3.1:8b', stream: false, options: { temperature: 0.4, num_ctx: 8192 }, system: 'Write a concise, specific, truthful cover letter (max 250 words). Use ONLY facts from the resume. No invented achievements. Professional, warm, not sycophantic.', prompt: 'RESUME:\\n' + $('Parse Score').item.json.resume_text + '\\n\\nJOB: ' + $('Parse Score').item.json.title + ' at ' + $('Parse Score').item.json.company + '\\n' + ($('Parse Score').item.json.description || '').slice(0, 3000) }) }}",
"options": {
"timeout": 300000
}
},
"id": "http-cover",
"name": "Cover Letter",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1920,
220
]
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "// Assemble the application package file + persist SQL.\nconst ps = $('Parse Score').item.json;\nconst tailored = $('Tailor Resume').item.json.response || '';\nconst cover = $('Cover Letter').item.json.response || '';\nconst md = `# Tailored Resume \\u2014 ${ps.title} @ ${ps.company}\\n\\n${tailored}\\n\\n---\\n\\n# Cover Letter\\n\\n${cover}\\n`;\nconst path = `/data/storage/applications/${ps.job_id}.md`;\nconst query = `INSERT INTO app.applications (job_id, resume_id, tailored_resume_path, cover_letter_path, status) VALUES ('${ps.job_id}','${ps.resume_id}','${path}','${path}','ready') ON CONFLICT (job_id, resume_id) DO UPDATE SET tailored_resume_path = EXCLUDED.tailored_resume_path, cover_letter_path = EXCLUDED.cover_letter_path, status = 'ready'; UPDATE app.jobs SET status = 'ready' WHERE id = '${ps.job_id}';`;\nreturn { json: { job_id: ps.job_id, path, query }, binary: { data: { data: Buffer.from(md).toString('base64'), fileName: `${ps.job_id}.md`, mimeType: 'text/markdown' } } };"
},
"id": "code-assemble",
"name": "Assemble Package",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2140,
220
]
},
{
"parameters": {
"operation": "write",
"fileName": "={{ $json.path }}",
"dataPropertyName": "data",
"options": {}
},
"id": "fs-write",
"name": "Write Package File",
"type": "n8n-nodes-base.readWriteFile",
"typeVersion": 1,
"position": [
2360,
220
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "={{ $('Assemble Package').item.json.query }}",
"options": {}
},
"id": "pg-app",
"name": "Create Application",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
2580,
220
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Manual / After Dedup": {
"main": [
[
{
"node": "Get Default Resume",
"type": "main",
"index": 0
}
]
]
},
"Get Default Resume": {
"main": [
[
{
"node": "Get Jobs to Score",
"type": "main",
"index": 0
}
]
]
},
"Get Jobs to Score": {
"main": [
[
{
"node": "Score Job",
"type": "main",
"index": 0
}
]
]
},
"Score Job": {
"main": [
[
{
"node": "Parse Score",
"type": "main",
"index": 0
}
]
]
},
"Parse Score": {
"main": [
[
{
"node": "Save Score",
"type": "main",
"index": 0
},
{
"node": "Apply?",
"type": "main",
"index": 0
}
]
]
},
"Save Score": {
"main": [
[]
]
},
"Apply?": {
"main": [
[
{
"node": "Tailor Resume",
"type": "main",
"index": 0
}
],
[]
]
},
"Tailor Resume": {
"main": [
[
{
"node": "Cover Letter",
"type": "main",
"index": 0
}
]
]
},
"Cover Letter": {
"main": [
[
{
"node": "Assemble Package",
"type": "main",
"index": 0
}
]
]
},
"Assemble Package": {
"main": [
[
{
"node": "Write Package File",
"type": "main",
"index": 0
}
]
]
},
"Write Package File": {
"main": [
[
{
"node": "Create Application",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
}
}
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.
postgres
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
03 Scoring: Score, Tailor, Cover Letter. Uses postgres, httpRequest, readWriteFile. Event-driven trigger; 12 nodes.
Source: https://github.com/AskariJafri/job-search-os/blob/main/n8n/workflows/03-scoring/score-and-tailor.json — 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.
Reagendamiento_v2. Uses executeWorkflowTrigger, redis, httpRequest, n8n-nodes-evolution-api. Event-driven trigger; 89 nodes.
Execute Workflow Trigger, Redis, HTTP Request +3
This workflow acts as a junior finance research analyst for a UK boutique M&A or corporate finance team. It listens for Slack messages, classifies the request, gathers company or market data, and prod
HTTP Request, Google Drive, Google Docs +5
Agendamiento_v2. Uses n8n-nodes-evolution-api, redis, httpRequest, executeWorkflowTrigger. Event-driven trigger; 59 nodes.
N8N Nodes Evolution Api, Redis, HTTP Request +3
Cancelacion_v2. Uses executeWorkflowTrigger, redis, httpRequest, n8n-nodes-evolution-api. Event-driven trigger; 46 nodes.
Execute Workflow Trigger, Redis, HTTP Request +3
Components. Uses postgres, readWriteFile. Event-driven trigger; 42 nodes.
Postgres, Read Write File