This workflow follows the Agent → Chat Trigger 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": "Jira AI Test Case Generator",
"nodes": [
{
"parameters": {
"public": true,
"initialMessages": "Hi there! \ud83d\udc4b\nMy name is Abdulrhman. How can I assist you today?",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.4,
"position": [
-1184,
-224
],
"id": "96abbcc5-b525-476b-9463-74561e0875cd",
"name": "When chat message received"
},
{
"parameters": {
"promptType": "define",
"text": "=Analyze the provided Jira user story and generate comprehensive manual test cases.\n\nStory Key:\n{{ $json.storyKey }}\n\nSummary:\n{{ $json.summary }}\n\nDescription:\n{{ $json.description }}",
"options": {
"systemMessage": "You are a Senior QA Engineer specialized in manual testing.\n\nAnalyze the provided Jira user story and perform a comprehensive QA analysis before generating manual test cases.\n\nAnalyze all available information including:\n- User Story\n- Description\n- Acceptance Criteria\n- Business Rules\n- Preconditions\n- Field Validations\n- UI Requirements\n- Error Messages\n- Edge Cases\n\nIdentify all possible test scenarios based on:\n- Functional behavior\n- Acceptance Criteria\n- Business Rules\n- Validations\n- User inputs\n- System responses\n- Error handling\n- Edge Cases\n- State transitions\n- Data variations\n- Security considerations (when applicable)\n\nGenerate manual test cases for every identified scenario required to achieve complete functional coverage.\n\nEnsure coverage includes:\n- Happy Path\n- Alternate Flows\n- Negative Scenarios\n- Validations\n- Business Rules\n- Error Handling\n- Edge Cases\n- State Transitions\n- Boundary Conditions (when applicable)\n\nGenerate at least one unique manual test case for every identified test scenario.\n\nFor each test case:\n\n- title\n Write a clear verification statement starting with \"Verify\".\n This will be used as the Jira Subtask Summary.\n\n Example:\n Verify that a registered user can log in successfully using a valid email address or phone number and the correct password.\n\n- description\n Write ONLY a short scenario name.\n Examples:\n - Successful login with valid email or phone and password\n - Empty email\n - Empty password\n - Invalid email format\n - Wrong password\n - Locked account\n - Disabled account\n\n- steps\n Return an ordered array of detailed manual execution steps.\n Prefix every step with its number (for example: \"1. Open the login page\", \"2. Enter a valid email address\", \"3. Click Login\"). This formatting is required for better rendering in Jira.\n\n- expectedResult\n Describe the expected system behavior after executing the steps.\n If the expected result contains multiple outcomes, format them as a numbered list (for example: \"1. User is authenticated.\\n2. Home page is displayed.\\n3. User profile is loaded.\"). If there is only one outcome, prefix it with \"1.\".\n\nRules:\n\n- Preserve the original storyKey.\n- Generate only unique test cases.\n- Do not invent requirements that do not exist.\n- Do not return duplicate scenarios.\n- Never leave any field empty.\n- Do not return markdown.\n- Do not wrap the response in code blocks.\n- Return ONLY valid JSON.\n\nReturn exactly this schema:\n\n{\n \"storyKey\": \"\",\n \"testCases\": [\n {\n \"title\": \"\",\n \"description\": \"\",\n \"steps\": [],\n \"expectedResult\": \"\"\n }\n ]\n}"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 3.1,
"position": [
-272,
-224
],
"id": "c2cfe24f-c9e8-432d-a6d1-915e9b298369",
"name": "AI Agent"
},
{
"parameters": {
"modelName": "models/gemini-3.5-flash",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1.1,
"position": [
-480,
0
],
"id": "7a913fb9-9d21-4184-9fff-68298d144eba",
"name": "Google Gemini Chat Model",
"credentials": {}
},
{
"parameters": {
"model": "=llama3.1:8b",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
-272,
16
],
"id": "d4a02c21-cdd4-4685-b9a7-76c2acea00bc",
"name": "Ollama Chat Model",
"credentials": {}
},
{
"parameters": {
"fieldToSplitOut": "testCases",
"options": {}
},
"type": "n8n-nodes-base.splitOut",
"typeVersion": 1,
"position": [
240,
-192
],
"id": "a6bbc7d6-3d65-4660-81c0-978cc8d6fce6",
"name": "Split Out"
},
{
"parameters": {
"project": {
"__rl": true,
"value": "<PROJECT_ID>",
"mode": "list",
"cachedResultName": ""
},
"issueType": {
"__rl": true,
"value": "<ISSUE_TYPE_ID>",
"mode": "list",
"cachedResultName": ""
},
"summary": "={{ $json.title }}",
"additionalFields": {
"assignee": {},
"description": "=h2. Description\n\n{{$json.description}}\n\nh2. Steps\n\n{{ $json.steps.join('\\n') }}\n\nh2. Expected Result\n\n{{$json.expectedResult}}",
"parentIssueKey": "={{ $('Get an issue').first().json.key }}",
"reporter": {}
}
},
"type": "n8n-nodes-base.jira",
"typeVersion": 1,
"position": [
464,
-176
],
"id": "637fd855-fd75-49bc-9dfa-c94f28f76d91",
"name": "Create an issue",
"credentials": {}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "a3d0a9ed-c9a1-492b-b4c6-8eeb7fbeabcd",
"name": "=storyKey",
"value": "={{\nJSON.parse(\n $json.output.match(/\\{[\\s\\S]*\\}/)[0]\n).storyKey\n}}",
"type": "string"
},
{
"id": "a34d7729-de18-4c29-9090-c47f206e10c4",
"name": "testCases",
"value": "={{\nJSON.parse(\n $json.output.match(/\\{[\\s\\S]*\\}/)[0]\n).testCases\n}}",
"type": "array"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
48,
-176
],
"id": "fde2beee-859a-420f-b84d-d3704e286907",
"name": "testCases"
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.4,
"position": [
-64,
80
],
"id": "4f9e64e9-30ae-45d7-b3ca-c4902bcc7252",
"name": "Simple Memory"
},
{
"parameters": {
"operation": "get",
"issueKey": "={{$json.issueKey}}",
"additionalFields": {}
},
"type": "n8n-nodes-base.jira",
"typeVersion": 1,
"position": [
-768,
-224
],
"id": "41b28944-f016-4843-90cf-c0922b40089f",
"name": "Get an issue",
"credentials": {}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "b170f265-bb60-4fea-8897-39054cd776f5",
"name": "storyKey",
"value": "={{$json.key}}",
"type": "string"
},
{
"id": "c6a20eb3-707c-44f8-bab0-0a3d45c34c66",
"name": "summary",
"value": "={{$json.fields.summary}}",
"type": "string"
},
{
"id": "6a10e2f9-936f-40f0-9e71-168cb25e6068",
"name": "description",
"value": "={{$json.fields.description}}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-528,
-208
],
"id": "888ed569-53e9-4131-947f-e6f081957794",
"name": "Set Story Context"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "3bcf857c-36ee-4d97-800a-4bf66d041a68",
"name": "issueKey",
"value": "={{\n($json.chatInput.match(/[A-Z]+-\\d+/) || [])[0]\n}}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-992,
-112
],
"id": "2fe72467-6c52-41b4-8cb2-546beeb41dde",
"name": "Set Issue Key"
}
],
"connections": {
"When chat message received": {
"main": [
[
{
"node": "Set Issue Key",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Ollama Chat Model": {
"ai_languageModel": [
[]
]
},
"AI Agent": {
"main": [
[
{
"node": "testCases",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "Create an issue",
"type": "main",
"index": 0
}
]
]
},
"testCases": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Set Story Context": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Get an issue": {
"main": [
[
{
"node": "Set Story Context",
"type": "main",
"index": 0
}
]
]
},
"Set Issue Key": {
"main": [
[
{
"node": "Get an issue",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate",
"availableInMCP": false
},
"versionId": "7a1ae2b4-e5f7-44f6-b2e8-262c68e238f0",
"meta": {
"templateCredsSetupCompleted": true
},
"nodeGroups": [],
"id": "U197wOyrA7gUjC9V",
"tags": []
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Jira AI Test Case Generator. Uses chatTrigger, agent, lmChatGoogleGemini, lmChatOllama. Chat trigger; 11 nodes.
Source: https://github.com/AbdulrhmanTalaat/jira-ai-testcase-generator/blob/main/workflow/jira-ai-testcase-generator.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.
Automate Google Classroom via the Google Classroom API to efficiently manage courses, topics, teachers, students, announcements, and coursework.
Chat Trigger, Agent Tool, HTTP Request Tool +3
This Chatbot automates the process of discovering job openings and generating tailored job application emails.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
Job Application PredictLeads & ScrapeGraph AI. Uses chatTrigger, lmChatOpenAi, mcpClientTool, memoryBufferWindow. Chat trigger; 32 nodes.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
Job Application PredictLeads & ScrapeGraph AI. Uses chatTrigger, lmChatOpenAi, mcpClientTool, memoryBufferWindow. Chat trigger; 32 nodes.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
An intelligent IT support agent that uses Azure AI Search for knowledge retrieval, Microsoft Entra ID integration for user management, and Jira for ticket creation. The agent can answer questions usin
Chat Trigger, Google Gemini Chat, Memory Buffer Window +5