Workflow n8n : résumé quotidien des avis clients
Workflow n8n : récupère les avis Shopify du jour, les classe par sentiment avec un LLM, résume les négatifs et envoie le tout sur Slack chaque matin.
Access Medium
- Read files or data
- Modify or delete files : No
- Send data over the internet
- Run commands on the machine : No
| Input | Avis clients Shopify des dernières 24 h |
|---|---|
| Output | Message Slack chaque matin à 8 h |
Steps
- Déclenchement chaque matin à 8 h
- Récupérer les avis des dernières 24 h (API Shopify)
- Classer chaque avis (positif, neutre, négatif) et résumer les négatifs avec un LLM
- Envoyer le résumé dans le canal Slack du service client
Exported definition
{
"name": "Résumé quotidien des avis clients",
"nodes": [
{
"parameters": {
"rule": {
"interval": [
{
"field": "cronExpression",
"expression": "0 8 * * *"
}
]
}
},
"name": "Chaque matin à 8 h",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
0,
0
]
},
{
"parameters": {
"url": "https://VOTRE-BOUTIQUE.myshopify.com/admin/api/2024-10/reviews.json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "shopifyAccessTokenApi"
},
"name": "Avis des dernières 24 h",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
220,
0
]
},
{
"parameters": {
"method": "POST",
"url": "https://api.anthropic.com/v1/messages",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "anthropicApi",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\"model\": \"claude-haiku-4-5\", \"max_tokens\": 800, \"messages\": [{\"role\": \"user\", \"content\": \"Classe ces avis en positif, neutre ou négatif, puis résume les négatifs en 5 points maximum, avec le nombre d'avis par point.\\n\\n{{ JSON.stringify($json) }}\"}]}"
},
"name": "Classer et résumer (LLM)",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
440,
0
]
},
{
"parameters": {
"channel": "#service-client",
"text": "=Avis d'hier :\n{{ $json.content[0].text }}"
},
"name": "Envoyer sur Slack",
"type": "n8n-nodes-base.slack",
"typeVersion": 2.2,
"position": [
660,
0
]
}
],
"connections": {
"Chaque matin à 8 h": {
"main": [
[
{
"node": "Avis des dernières 24 h",
"type": "main",
"index": 0
}
]
]
},
"Avis des dernières 24 h": {
"main": [
[
{
"node": "Classer et résumer (LLM)",
"type": "main",
"index": 0
}
]
]
},
"Classer et résumer (LLM)": {
"main": [
[
{
"node": "Envoyer sur Slack",
"type": "main",
"index": 0
}
]
]
}
}
}Estimated cost
Input tokens per call : ≈ 992
| Model | Per call | Per 1,000 calls |
|---|---|---|
| Mistral Large · Mistral AI | €0.00044 | €0.44 |
| DeepSeek Flash · DeepSeek | €0.00026 | €0.26 |
| DeepSeek V4 Pro · DeepSeek | €0.00115 | €1.15 |
| GPT-6 Luna · OpenAI | €0.00009 | €0.09 |
| GPT-6 Sol · OpenAI | €0.00175 | €1.75 |
| Claude Sonnet 5.5 · Anthropic | €0.00175 | €1.75 |
| Claude Opus 5.5 · Anthropic | €0.00349 | €3.49 |
| Self-hosted open-source model (Ollama, vLLM) | €0 in API fees (server cost only) | |
Input cost only, excluding the model's answer. Providers' public standard prices (Mistral AI, DeepSeek, OpenAI, Anthropic) converted from USD to euros at the ECB rate of September 29, 2026. Estimate: 1 token ≈ 3.6 characters.
Common to all 3 regions
Created by the author, no outside source.
Commercial use allowed · credit the author · changes allowed.
Declared access : read files, send data online.
Hosted in France (Scaleway, Paris). No transfer outside the EU.
European Union · 4/5
Real data.
Legal basis not given.
No training data: no summary required.
United States · 4/5
Real data.
Legal basis not given.
No training data: no documentation to publish.
China · 4/5
Real data.
Legal basis not given.
No training data; AI-generated content published in China must be labelled (2025).
Indicative summary as of 30/09/2026, not a legal certification. Method and sources →
Statistics
Likes : 0 · Comments : 0
Click a counter to show or hide it, hover the chart for details. One view per visitor per day, bots excluded; counting started on 30 September 2026.
- Identifier
- contextetech--resume-avis-clients-n8n
- Type
- Workflows
- File
- resume-avis-clients-n8n.workflow.json
- Format
- JSON (application/json)
- Size
- 2,521 bytes (2.5 KB)
- Encoding
- UTF-8
- Estimated tokens
- ≈ 697
- Language
- French
- License
- MIT
- Commercial use
- Allowed
- Personal data
- Real
- Version
- 1.0
- Published on
- October 1, 2026 at 6:21 PM
- Updated on
- October 1, 2026 at 6:21 PM
- Storage
- in database
- Uses
- 0
- Likes
- 0
resume-avis-clients-n8n.workflow.json
{
"name": "Résumé quotidien des avis clients",
"nodes": [
{
"parameters": {
"rule": {
"interval": [
{
"field": "cronExpression",
"expression": "0 8 * * *"
}
]
}
},
"name": "Chaque matin à 8 h",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
0,
0
]
},
{
"parameters": {
"url": "https://VOTRE-BOUTIQUE.myshopify.com/admin/api/2024-10/reviews.json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "shopifyAccessTokenApi"
},
"name": "Avis des dernières 24 h",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
220,
0
]
},
{
"parameters": {
"method": "POST",
"url": "https://api.anthropic.com/v1/messages",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "anthropicApi",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\"model\": \"claude-haiku-4-5\", \"max_tokens\": 800, \"messages\": [{\"role\": \"user\", \"content\": \"Classe ces avis en positif, neutre ou négatif, puis résume les négatifs en 5 points maximum, avec le nombre d'avis par point.\\n\\n{{ JSON.stringify($json) }}\"}]}"
},
"name": "Classer et résumer (LLM)",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
440,
0
]
},
{
"parameters": {
"channel": "#service-client",
"text": "=Avis d'hier :\n{{ $json.content[0].text }}"
},
"name": "Envoyer sur Slack",
"type": "n8n-nodes-base.slack",
"typeVersion": 2.2,
"position": [
660,
0
]
}
],
"connections": {
"Chaque matin à 8 h": {
"main": [
[
{
"node": "Avis des dernières 24 h",
"type": "main",
"index": 0
}
]
]
},
"Avis des dernières 24 h": {
"main": [
[
{
"node": "Classer et résumer (LLM)",
"type": "main",
"index": 0
}
]
]
},
"Classer et résumer (LLM)": {
"main": [
[
{
"node": "Envoyer sur Slack",
"type": "main",
"index": 0
}
]
]
}
}
}
Import
# n8n : Workflows › Import from file › resume-avis-clients-n8n.workflow.json
Steps
1. Déclenchement chaque matin à 8 h 2. Récupérer les avis des dernières 24 h (API Shopify) 3. Classer chaque avis (positif, neutre, négatif) et résumer les négatifs avec un LLM 4. Envoyer le résumé dans le canal Slack du service client
Community
No comments yet. Share your feedback, it will help the next person.