Ryan Nolan This workflow corresponds to n8n.io template #12644 — we link there as the canonical source.
This workflow follows the Agent → Chainsummarization 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 →
{
"id": "TTOhMccGGYvjPhs8",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Set up evaluations in n8n",
"tags": [],
"nodes": [
{
"id": "cfaca160-61ac-4706-b17b-f1eb2e0390a0",
"name": "Evaluation",
"type": "n8n-nodes-base.evaluation",
"position": [
2336,
800
],
"parameters": {
"source": "googleSheets",
"outputs": {
"values": [
{
"outputName": "Result",
"outputValue": "={{ $json.output }}"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.8
},
{
"id": "7fe85f2f-bc1d-41da-907c-e4c3c1f1bee4",
"name": "Evaluation3",
"type": "n8n-nodes-base.evaluation",
"position": [
2048,
960
],
"parameters": {
"operation": "checkIfEvaluating"
},
"typeVersion": 4.8
},
{
"id": "9ac36a2b-c879-4d17-a508-d950182c1662",
"name": "When fetching a dataset row",
"type": "n8n-nodes-base.evaluationTrigger",
"position": [
1296,
960
],
"parameters": {
"source": "googleSheets",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.7
},
{
"id": "9ed4aea0-6cf4-474d-bd39-96c3101595eb",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1664,
1200
],
"parameters": {
"options": {},
"modelName": "models/gemini-3-pro-preview"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "c78f9dc6-fdca-41e0-868a-bceeb1503f67",
"name": "Evaluation5",
"type": "n8n-nodes-base.evaluation",
"position": [
2576,
800
],
"parameters": {
"metric": "categorization",
"options": {
"metricName": "Categorization"
},
"operation": "setMetrics",
"actualAnswer": "={{ $('Evaluation3').item.json.output }}",
"expectedAnswer": "={{ $('When fetching a dataset row').item.json.team }}"
},
"typeVersion": 4.8
},
{
"id": "a568f927-bcb3-453e-ac50-5275de890cf8",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
656,
-304
],
"parameters": {
"content": "Evaluation Trigger\n\nData Table or Google Sheets -> Expand in the future?"
},
"typeVersion": 1
},
{
"id": "06da59cd-5393-40b8-8db6-c3e1d93962db",
"name": "When fetching a dataset row1",
"type": "n8n-nodes-base.evaluationTrigger",
"position": [
720,
-96
],
"parameters": {
"dataTableId": {
"__rl": true,
"mode": "list",
"value": ""
}
},
"typeVersion": 4.7
},
{
"id": "9a2bb0ef-dabe-4c7a-9958-3048314b8ee5",
"name": "Evaluation4",
"type": "n8n-nodes-base.evaluation",
"position": [
1136,
-96
],
"parameters": {
"operation": "checkIfEvaluating"
},
"typeVersion": 4.8
},
{
"id": "82e526e6-3489-4760-8b78-29b90e3fef52",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1104,
-304
],
"parameters": {
"content": "checkIfEvaluating\n\nFlow branch -> Like if\nWorkflow either goes evaluation route or normal"
},
"typeVersion": 1
},
{
"id": "4520ee01-14c3-4eb8-8c22-772c0f950fe2",
"name": "Evaluation6",
"type": "n8n-nodes-base.evaluation",
"position": [
1616,
-80
],
"parameters": {
"source": "googleSheets",
"outputs": {
"values": [
{}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": 1858508822,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1IUZc2WSEMQ6QpEs_6-aTdMRJAh2z2Bq2cY81hnqeHj4/edit#gid=1858508822",
"cachedResultName": "Cases"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1IUZc2WSEMQ6QpEs_6-aTdMRJAh2z2Bq2cY81hnqeHj4",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1IUZc2WSEMQ6QpEs_6-aTdMRJAh2z2Bq2cY81hnqeHj4/edit?usp=drivesdk",
"cachedResultName": "Kenneth Spreadsheet"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.8
},
{
"id": "cc25269c-939e-4324-88b9-c028c12ce9f8",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1568,
-304
],
"parameters": {
"content": "set outputs\n\nPut the results from the run into Google Sheets or Data Table"
},
"typeVersion": 1
},
{
"id": "e6c4f32b-2106-413c-a1ed-4ea4689ecf4b",
"name": "Evaluation7",
"type": "n8n-nodes-base.evaluation",
"position": [
2352,
-80
],
"parameters": {
"options": {},
"operation": "setMetrics"
},
"typeVersion": 4.8
},
{
"id": "495e8cd1-a945-4eef-a646-1dcb6155862d",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
1984,
-304
],
"parameters": {
"content": "set metrics\n\nEvaluates how your run performed. May use a Model"
},
"typeVersion": 1
},
{
"id": "b73543b3-5ea8-4e54-a8e4-444af7bf0eca",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
2304,
-336
],
"parameters": {
"width": 320,
"height": 224,
"content": "Uses - AI\n\n\nCorrectness: Whether the answer's meaning is consistent with a supplied reference answer. Uses a scale of 1 to 5, with 5 being the best.\n\nHelpfulness: Whether the response answers the given query. Uses a scale of 1 to 5, with 5 being the best."
},
"typeVersion": 1
},
{
"id": "49726a2a-b593-408c-be82-0e8bf87ba095",
"name": "Evaluation8",
"type": "n8n-nodes-base.evaluation",
"position": [
2832,
-80
],
"parameters": {
"metric": "stringSimilarity",
"options": {},
"operation": "setMetrics"
},
"typeVersion": 4.8
},
{
"id": "ebbb357e-8452-4bc7-9975-a857e29a7a16",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
2704,
-336
],
"parameters": {
"width": 576,
"height": 224,
"content": "String Similarity: How close the answer is to the reference answer, measured character-by-character (edit distance). Returns a score between 0 and 1.\n\nCategorization: Whether the answer is an exact match with the reference answer. Returns 1 when matching and 0 otherwise.\n\nTools Used: Whether the execution used tools or not. Returns a score between 0 and 1."
},
"typeVersion": 1
},
{
"id": "f1fd87dd-4564-47f1-ae76-f38f80be3b1c",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
624,
928
],
"parameters": {
"color": 7,
"width": 528,
"height": 304,
"content": "## Example 1 Categorization\n\n\nCategorization: Whether the answer is an exact match with the reference answer. Returns 1 when matching and 0 otherwise.\n\n\nWorld Series Winners - No results 2024 and 2025"
},
"typeVersion": 1
},
{
"id": "0e9923e8-eee4-476a-b6da-7fa783c4410e",
"name": "Evaluation1",
"type": "n8n-nodes-base.evaluation",
"position": [
2304,
1408
],
"parameters": {
"source": "googleSheets",
"outputs": {
"values": [
{
"outputName": "Tools Used",
"outputValue": "={{ $json.intermediateSteps[0].action.tool }}"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": 890240055,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=890240055",
"cachedResultName": "Sheet2"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.8
},
{
"id": "1348c88c-86dd-40ad-af01-6f3d54f0d8c2",
"name": "Evaluation9",
"type": "n8n-nodes-base.evaluation",
"position": [
2016,
1568
],
"parameters": {
"operation": "checkIfEvaluating"
},
"typeVersion": 4.8
},
{
"id": "5594a949-59cc-4a87-a073-43b731185de2",
"name": "When fetching a dataset row2",
"type": "n8n-nodes-base.evaluationTrigger",
"position": [
1248,
1568
],
"parameters": {
"source": "googleSheets",
"sheetName": {
"__rl": true,
"mode": "list",
"value": 890240055,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=890240055",
"cachedResultName": "Sheet2"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.7
},
{
"id": "d16f94f2-d0b9-4dd4-8f8b-b0ddb1ec227c",
"name": "Evaluation10",
"type": "n8n-nodes-base.evaluation",
"position": [
2544,
1408
],
"parameters": {
"metric": "toolsUsed",
"options": {},
"operation": "setMetrics",
"expectedTools": "={{ $('When fetching a dataset row2').item.json.tool }}",
"intermediateSteps": "={{ $('Evaluation9').item.json.intermediateSteps[0].action.tool }}"
},
"typeVersion": 4.8
},
{
"id": "12580362-6d69-4694-8bfc-c076867ae27e",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
608,
1520
],
"parameters": {
"color": 7,
"width": 528,
"height": 304,
"content": "## Example 2 Tools Used\n\n\nTools Used: Whether the execution used tools or not. Returns a score between 0 and 1.\n\nWorld Series Winners - Use Perplexity to get new results"
},
"typeVersion": 1
},
{
"id": "257d9439-d1bc-4f0d-8af5-66c7f95278c9",
"name": "Evaluation2",
"type": "n8n-nodes-base.evaluation",
"position": [
2304,
2160
],
"parameters": {
"source": "googleSheets",
"outputs": {
"values": [
{
"outputName": "Result",
"outputValue": "={{ $json.output }}"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.8
},
{
"id": "0104ef2f-f1ba-4382-9662-b9df9f4a61cf",
"name": "Evaluation11",
"type": "n8n-nodes-base.evaluation",
"position": [
2016,
2320
],
"parameters": {
"operation": "checkIfEvaluating"
},
"typeVersion": 4.8
},
{
"id": "57f59d48-b620-472f-969d-b4c3a8505640",
"name": "When fetching a dataset row3",
"type": "n8n-nodes-base.evaluationTrigger",
"position": [
1248,
2320
],
"parameters": {
"source": "googleSheets",
"sheetName": {
"__rl": true,
"mode": "list",
"value": 1065824480,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=1065824480",
"cachedResultName": "Sheet3"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.7
},
{
"id": "547aad25-2b74-4cea-b9aa-071267d7702a",
"name": "Evaluation12",
"type": "n8n-nodes-base.evaluation",
"position": [
2544,
2160
],
"parameters": {
"metric": "stringSimilarity",
"options": {},
"operation": "setMetrics",
"actualAnswer": "={{ $('Evaluation11').item.json.output }}",
"expectedAnswer": "={{ $('When fetching a dataset row3').item.json['Expected clean data'] }}"
},
"typeVersion": 4.8
},
{
"id": "f298506c-68df-4851-9d54-8d632604b499",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
608,
2272
],
"parameters": {
"color": 7,
"width": 528,
"height": 464,
"content": "## Example 3 String Similarity\n\n\nString Similarity: How close the answer is to the reference answer, measured character-by-character (edit distance). Returns a score between 0 and 1.\n\n\nData Cleaning Validation\n"
},
"typeVersion": 1
},
{
"id": "71acfc91-8cd1-4217-8e01-a0f16a4621bb",
"name": "Evaluation13",
"type": "n8n-nodes-base.evaluation",
"position": [
2304,
3504
],
"parameters": {
"source": "googleSheets",
"outputs": {
"values": [
{
"outputName": "Result",
"outputValue": "={{ $json.output }}"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.8
},
{
"id": "95c4eac8-ad30-48bd-990d-9db3a5036ff7",
"name": "Evaluation14",
"type": "n8n-nodes-base.evaluation",
"position": [
2016,
3664
],
"parameters": {
"operation": "checkIfEvaluating"
},
"typeVersion": 4.8
},
{
"id": "13c4f810-a87f-4da7-9b00-0e128552c6e5",
"name": "When fetching a dataset row4",
"type": "n8n-nodes-base.evaluationTrigger",
"position": [
1248,
3664
],
"parameters": {
"dataTableId": {
"__rl": true,
"mode": "list",
"value": "yF4PbotpSaEboTBu",
"cachedResultUrl": "/projects/NQFxMgZQSYbqdMqk/datatables/yF4PbotpSaEboTBu",
"cachedResultName": "eval_vid"
}
},
"typeVersion": 4.7
},
{
"id": "82fb5900-198e-486e-ad0e-aaa77a7032ef",
"name": "Google Gemini Chat Model3",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1552,
3856
],
"parameters": {
"options": {},
"modelName": "models/gemini-3-pro-preview"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "0e0d92aa-3d38-4255-bb4e-c81303f0b649",
"name": "Evaluation15",
"type": "n8n-nodes-base.evaluation",
"position": [
2544,
3504
],
"parameters": {
"options": {},
"operation": "setMetrics",
"actualAnswer": "={{ $('Evaluation14').item.json.output }}",
"expectedAnswer": "={{ $('When fetching a dataset row4').item.json.team }}"
},
"typeVersion": 4.8
},
{
"id": "0eafc598-cf7d-4c4e-b2ce-7dfe8661c5a7",
"name": "Sticky Note9",
"type": "n8n-nodes-base.stickyNote",
"position": [
592,
3616
],
"parameters": {
"color": 7,
"width": 576,
"height": 400,
"content": "## Example 5 Correctness\n\nData Table + non AI Agent Node\n\nCorrectness: Whether the answer's meaning is consistent with a supplied reference answer. Uses a scale of 1 to 5, with 5 being the best.\n\n\nOption 2: Summary Accuracy Testing\n\nSet Node with long articles/documents\nAI Agent generates summaries\nSet Node with reference summaries\nEval Node scores if AI summary captures the same core meaning"
},
"typeVersion": 1
},
{
"id": "4cc26a18-934e-4631-910f-a55a3f865451",
"name": "Evaluation16",
"type": "n8n-nodes-base.evaluation",
"position": [
2288,
2928
],
"parameters": {
"source": "googleSheets",
"outputs": {
"values": [
{
"outputName": "Result",
"outputValue": "={{ $json.output }}"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.8
},
{
"id": "c080b1bd-1b51-476a-801e-f377ad9df12f",
"name": "Evaluation17",
"type": "n8n-nodes-base.evaluation",
"position": [
2000,
3088
],
"parameters": {
"operation": "checkIfEvaluating"
},
"typeVersion": 4.8
},
{
"id": "34420ecb-7a7f-471c-b7b2-d391ba85e9fc",
"name": "When fetching a dataset row5",
"type": "n8n-nodes-base.evaluationTrigger",
"position": [
1232,
3088
],
"parameters": {
"source": "googleSheets",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.7
},
{
"id": "7b8c0919-7f21-4489-90e2-73429c742192",
"name": "Google Gemini Chat Model4",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1616,
3328
],
"parameters": {
"options": {},
"modelName": "models/gemini-3-pro-preview"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "2904492e-bbba-4746-b09b-ecd580dfcb12",
"name": "Evaluation18",
"type": "n8n-nodes-base.evaluation",
"position": [
2528,
2928
],
"parameters": {
"metric": "helpfulness",
"options": {},
"operation": "setMetrics",
"actualAnswer": "={{ $('Evaluation17').item.json.output }}"
},
"typeVersion": 4.8
},
{
"id": "0b8125df-70db-43b9-b708-b365ce00d824",
"name": "Sticky Note10",
"type": "n8n-nodes-base.stickyNote",
"position": [
592,
3040
],
"parameters": {
"color": 7,
"width": 528,
"height": 304,
"content": "## Example 4 Helpfulness\n\n\nHelpfulness: Whether the response answers the given query. Uses a scale of 1 to 5, with 5 being the best.\n\nOption 1: Product Description Rewriting\n\nManual Trigger with original product descriptions\nAI Agent rewrites them to be more compelling/concise\nSet Node with ideal rewritten versions\nEval Node checks if meaning/key details are preserved (1-5 scale)"
},
"typeVersion": 1
},
{
"id": "98133e7a-0627-42e6-8f53-2b8bffff6886",
"name": "Anthropic Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
1616,
1792
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-sonnet-4-5-20250929",
"cachedResultName": "Claude Sonnet 4.5"
},
"options": {}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "bbb9d4e4-7a68-4bb0-b08f-f40d5856eaf1",
"name": "Perplexity Tool",
"type": "n8n-nodes-base.perplexityTool",
"position": [
1936,
1776
],
"parameters": {
"options": {},
"messages": {
"message": [
{
"content": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('message0_Text', ``, 'string') }}"
}
]
},
"requestOptions": {}
},
"credentials": {
"perplexityApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "90dfc88f-f960-4e89-9d23-d894d3e4203e",
"name": "Anthropic Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
1616,
2496
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-sonnet-4-5-20250929",
"cachedResultName": "Claude Sonnet 4.5"
},
"options": {}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "bd684c74-3095-490c-9ddc-d76b116a1382",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
2672,
3104
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5-mini",
"cachedResultName": "gpt-5-mini"
},
"options": {},
"builtInTools": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "e674cefb-8b08-4b3e-8533-74a4ef16628a",
"name": "OpenAI Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
2688,
3712
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5-mini",
"cachedResultName": "gpt-5-mini"
},
"options": {},
"builtInTools": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "f6accaf3-6b0e-4e97-81e1-31de085568c4",
"name": "Sticky Note11",
"type": "n8n-nodes-base.stickyNote",
"position": [
640,
240
],
"parameters": {
"color": 7,
"width": 512,
"height": 384,
"content": "## Evaluations in Action\n\nThis is a blank demo of a workflow where someone wants to use an information extractor. We grab a test dataset and look at using evaluations to improve the prompt"
},
"typeVersion": 1
},
{
"id": "4f6997b2-0f15-46b9-8bdc-177fac59de45",
"name": "When fetching a dataset row6",
"type": "n8n-nodes-base.evaluationTrigger",
"position": [
1520,
192
],
"parameters": {
"source": "googleSheets",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.7
},
{
"id": "0ad59ce6-ada8-4421-a851-e5985894cb73",
"name": "Gmail Trigger",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
1504,
528
],
"parameters": {
"filters": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "572d135b-1f41-4ccc-9781-c0088523297f",
"name": "Extract from File",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1744,
528
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "d1847d44-c232-49b5-857b-64020c93105e",
"name": "Information Extractor",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
2000,
368
],
"parameters": {
"text": "YOUR TEXT GOES HERE",
"options": {}
},
"typeVersion": 1.2
},
{
"id": "54075084-59cc-4734-8c9e-4be0576233c7",
"name": "Evaluation19",
"type": "n8n-nodes-base.evaluation",
"position": [
2592,
176
],
"parameters": {
"source": "googleSheets",
"outputs": {
"values": [
{
"outputName": "Result",
"outputValue": "={{ $json.output }}"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1absZ-35jdgX8hXWcyFOXlUA-uhQJ8wcuUiHUvomZKr0/edit?usp=drivesdk",
"cachedResultName": "eval test"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.8
},
{
"id": "e731f6f1-e36d-46ef-b893-352a422ef940",
"name": "Evaluation20",
"type": "n8n-nodes-base.evaluation",
"position": [
2320,
368
],
"parameters": {
"operation": "checkIfEvaluating"
},
"typeVersion": 4.8
},
{
"id": "0e05bdc8-039e-42da-8e9b-f2df1c75cd15",
"name": "Evaluation21",
"type": "n8n-nodes-base.evaluation",
"position": [
2832,
176
],
"parameters": {
"metric": "categorization",
"options": {
"metricName": "Categorization"
},
"operation": "setMetrics",
"actualAnswer": "={{ $('Evaluation20').item.json.output }}",
"expectedAnswer": "={{ $('When fetching a dataset row').item.json.team }}"
},
"typeVersion": 4.8
},
{
"id": "7a69f610-eedb-45c5-b507-659ded9a7de8",
"name": "If",
"type": "n8n-nodes-base.if",
"position": [
2592,
544
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "2bb8e68d-4306-4c6c-898a-1a3be8f14d15",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "7fee8df3-f97b-4684-b7b4-0604f79cbe8a",
"name": "Send a message",
"type": "n8n-nodes-base.gmail",
"position": [
2880,
448
],
"parameters": {
"options": {}
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "3bd7c899-fbcc-4dee-bfba-1582dcbb0792",
"name": "Send a message1",
"type": "n8n-nodes-base.gmail",
"position": [
2880,
624
],
"parameters": {
"options": {}
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "6be4c7b1-e157-419c-a5fd-54c49491e5f0",
"name": "Sticky Note12",
"type": "n8n-nodes-base.stickyNote",
"position": [
640,
-992
],
"parameters": {
"width": 880,
"height": 608,
"content": "@[youtube](-4LXYOhQ-Z0)\n"
},
"typeVersion": 1
},
{
"id": "64a39f11-df11-441c-8ca8-bedbe40ffe7a",
"name": "Sticky Note13",
"type": "n8n-nodes-base.stickyNote",
"position": [
1568,
-976
],
"parameters": {
"width": 1232,
"height": 592,
"content": "\n ## Setup steps\nThis template/tutorial goes through 6 different examples of utilizing evaluations in n8n that you can copy and paste into your workflows.\n\nIf you want to learn even more about how each evaluation works, there is a detailed YouTube video embedded in the template\n\n\n## How it works\n1. Evaluations start with fetching a test dataset in data tables or google sheets\n2. We then pass this into our AI Node which can be an agent, llm chain, information extractor or more\n3. After our AI nodes we have a check if evaluating node which splits our data. When testing with evaluations we branch the data north\n4. Once in the Evaluations branch we set the outputs to the original data table or sheets and then look at the desired metrics we want to test\n5. More evaluation data is present in the evaluations tab. The started plan only allows 1 evaluation workflow per account\n\n\n## Quick Notes\n\nThank you for downloading our free n8n Evaluations template. If you enjoyed the template + tutorial please subscribe to the YouTube channel. We are uploading weekly content on AI/n8n\n\n### Connect With Us\nCheck out the links down below. If you need help with this template, want 1:1 coaching, or have a n8n project you want to build, reach out at ryannolandata@gmail.com\n\n1. Free Skool AI/n8n Group: https://www.skool.com/data-and-ai\n2. LinkedIn: https://www.linkedin.com/in/ryan-p-nolan/\n3. Twitter/X:https://x.com/RyanMattDS\n4. Website: https://ryanandmattdatascience.com/\n"
},
"typeVersion": 1
},
{
"id": "d5af974e-af67-4a5b-a3f2-d37697c9e2d7",
"name": "Google Gemini Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
2000,
576
],
"parameters": {
"options": {},
"modelName": "models/gemini-3-pro-preview"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "2663e16b-33bc-46ff-9643-5fae0ed19f1a",
"name": "World Series Searcher",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1664,
960
],
"parameters": {
"text": "=Who won the world series for: {{ $json.year }} Only output the team name. If you do not know write: Undetermined",
"options": {
"returnIntermediateSteps": false
},
"promptType": "define"
},
"typeVersion": 3
},
{
"id": "12b12b7c-da9a-4deb-918e-46ef78c4fef6",
"name": "Sticky Note14",
"type": "n8n-nodes-base.stickyNote",
"position": [
640,
-1104
],
"parameters": {
"color": 6,
"width": 2144,
"height": 80,
"content": "# Set up evaluations in n8n\n\n"
},
"typeVersion": 1
},
{
"id": "25f19bb8-bac3-4bda-837a-99b2d1b8dc07",
"name": "World Series Searcher1",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1632,
1568
],
"parameters": {
"text": "=Who won the world series for: {{ $json.year }} Only output the team name. If you do not know write: Undetermined.\n\nBefore writing Undetermined use the perplexity tool as it has up to date information",
"options": {
"returnIntermediateSteps": true
},
"promptType": "define"
},
"typeVersion": 3
},
{
"id": "1ccadc7c-dbb4-4c7b-90f2-3a174e30257a",
"name": "US Postal Formatter",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1632,
2320
],
"parameters": {
"text": "=Standardize this address to proper US postal format with correct capitalization, spacing, and punctuation. Return only the cleaned address:\n\n\nAddress to clean: {{$json.messydata}}",
"options": {
"returnIntermediateSteps": false
},
"promptType": "define"
},
"typeVersion": 3
},
{
"id": "593091e1-17da-4f5b-ab3d-2cc81357398a",
"name": "Product Description Rewriter",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1616,
3088
],
"parameters": {
"text": "=Rewrite this product description to be more compelling and customer-focused while keeping it concise. \n\nRequirements:\n- Preserve ALL key specifications and features\n- Make it more engaging and benefit-driven\n- Keep the same essential information\n- Aim for 2-3 sentences maximum\n- Use active, persuasive language\n\nOriginal description:\n{{$json.originalDescription}}",
"options": {
"returnIntermediateSteps": false
},
"promptType": "define"
},
"typeVersion": 3
},
{
"id": "e07553f4-c85d-476e-88fe-f86a703b105e",
"name": "Article Reviewer",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
1552,
3664
],
"parameters": {
"options": {}
},
"typeVersion": 2.1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "4afe49c0-d3ed-425a-9b2d-4eb6fb182f66",
"connections": {
"If": {
"main": [
[
{
"node": "Send a message",
"type": "main",
"index": 0
}
],
[
{
"node": "Send a message1",
"type": "main",
"index": 0
}
]
]
},
"Evaluation": {
"main": [
[
{
"node": "Evaluation5",
"type": "main",
"index": 0
}
]
]
},
"Evaluation1": {
"main": [
[
{
"node": "Evaluation10",
"type": "main",
"index": 0
}
]
]
},
"Evaluation2": {
"main": [
[
{
"node": "Evaluation12",
"type": "main",
"index": 0
}
]
]
},
"Evaluation3": {
"main": [
[
{
"node": "Evaluation",
"type": "main",
"index": 0
}
],
[]
]
},
"Evaluation9": {
"main": [
[
{
"node": "Evaluation1",
"type": "main",
"index": 0
}
]
]
},
"Evaluation11": {
"main": [
[
{
"node": "Evaluation2",
"type": "main",
"index": 0
}
]
]
},
"Evaluation13": {
"main": [
[
{
"node": "Evaluation15",
"type": "main",
"index": 0
}
]
]
},
"Evaluation14": {
"main": [
[
{
"node": "Evaluation13",
"type": "main",
"index": 0
}
]
]
},
"Evaluation16": {
"main": [
[
{
"node": "Evaluation18",
"type": "main",
"index": 0
}
]
]
},
"Evaluation17": {
"main": [
[
{
"node": "Evaluation16",
"type": "main",
"index": 0
}
]
]
},
"Evaluation19": {
"main": [
[
{
"node": "Evaluation21",
"type": "main",
"index": 0
}
]
]
},
"Evaluation20": {
"main": [
[
{
"node": "Evaluation19",
"type": "main",
"index": 0
}
],
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"Gmail Trigger": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"Perplexity Tool": {
"ai_tool": [
[
{
"node": "World Series Searcher1",
"type": "ai_tool",
"index": 0
}
]
]
},
"Article Reviewer": {
"main": [
[
{
"node": "Evaluation14",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Information Extractor",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Evaluation18",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "Evaluation15",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"US Postal Formatter": {
"main": [
[
{
"node": "Evaluation11",
"type": "main",
"index": 0
}
]
]
},
"Anthropic Chat Model": {
"ai_languageModel": [
[
{
"node": "World Series Searcher1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Anthropic Chat Model1": {
"ai_languageModel": [
[
{
"node": "US Postal Formatter",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Information Extractor": {
"main": [
[
{
"node": "Evaluation20",
"type": "main",
"index": 0
}
]
]
},
"World Series Searcher": {
"main": [
[
{
"node": "Evaluation3",
"type": "main",
"index": 0
}
]
]
},
"World Series Searcher1": {
"main": [
[
{
"node": "Evaluation9",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "World Series Searcher",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model1": {
"ai_languageModel": [
[
{
"node": "Information Extractor",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model3": {
"ai_languageModel": [
[
{
"node": "Article Reviewer",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model4": {
"ai_languageModel": [
[
{
"node": "Product Description Rewriter",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When fetching a dataset row": {
"main": [
[
{
"node": "World Series Searcher",
"type": "main",
"index": 0
}
]
]
},
"Product Description Rewriter": {
"main": [
[
{
"node": "Evaluation17",
"type": "main",
"index": 0
}
]
]
},
"When fetching a dataset row2": {
"main": [
[
{
"node": "World Series Searcher1",
"type": "main",
"index": 0
}
]
]
},
"When fetching a dataset row3": {
"main": [
[
{
"node": "US Postal Formatter",
"type": "main",
"index": 0
}
]
]
},
"When fetching a dataset row4": {
"main": [
[
{
"node": "Article Reviewer",
"type": "main",
"index": 0
}
]
]
},
"When fetching a dataset row5": {
"main": [
[
{
"node": "Product Description Rewriter",
"type": "main",
"index": 0
}
]
]
},
"When fetching a dataset row6": {
"main": [
[
{
"node": "Information Extractor",
"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.
anthropicApigmailOAuth2googlePalmApigoogleSheetsOAuth2ApiopenAiApiperplexityApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This template and YouTube video goes over 5 different implementations of evaluations within n8n. Categorization Correctness Tools used String similarity Helpfulness
Source: https://n8n.io/workflows/12644/ — 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 is an automated blog post generation system that: Researches topics using AI agents and web search tools Writes complete blog posts with proper SEO structure Generates custom images for each post
Output Parser Structured, Google Gemini Chat, HTTP Request Tool +11
RESUME SCREENER. Uses agent, outputParserStructured, lmChatOpenAi, gmailTrigger. Event-driven trigger; 37 nodes.
Agent, Output Parser Structured, OpenAI Chat +7
This workflow is for hotel managers, travel agencies, and hospitality teams who receive booking requests via email. It eliminates the need for manual data entry by automatically parsing emails and att
Google Sheets, Gmail, Agent +4
Enterprise-grade resume screening automation built for production environments. This workflow combines intelligent AI analysis with comprehensive error handling to ensure reliable processing of candid
Gmail Trigger, Google Drive, HTTP Request +6
Episode 15: Startup ideas for YC RFS. Uses lmChatOpenAi, googleSheets, agent, informationExtractor. Event-driven trigger; 33 nodes.
OpenAI Chat, Google Sheets, Agent +12