Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 13 additions & 19 deletions docs/guides/all/automatically-resolve-tickets-with-coding-agents.md
Original file line number Diff line number Diff line change
Expand Up @@ -125,37 +125,31 @@ Next, we will create an AI agent that generates GitHub issues from Jira tickets

```json showLineNumbers
{
"identifier": "github_issue_creation",
"title": "Github Issue Creation",
"identifier": "work_item_synchronizer",
"title": "Work Item Synchronizer",
"icon": "Details",
"team": [],
"properties": {
"description": "Creates Github issues from Jira tickets",
"description": "Ensures seamless workflow continuity across development tools",
"status": "active",
"allowed_blueprints": [
"service",
"githubIssue",
"githubRepository",
"_user",
"_team"
],
"allowed_actions": [
"create_github_issue"
],
"prompt": "Create a GitHub issue that builds on the context of a linked Jira ticket.\n\nThe GitHub issue should:\n1.\tSummarize and clearly explain the task, using the Jira description as a base.\n2.\tAugment the description with relevant insights from the repository — such as the README, setup or contribution instructions, existing issues, or implementation notes — to make the issue fully self-contained.\n3.\tThe **issue title MUST start with the Jira ticket key**, using the format: `<Jira-Ticket-ID> - <what needs to be done>` (e.g., `JIRA-1234 - Add missing lint configuration`). This ensures PRs created by Copilot are linkable back to Jira.\n4.\tAdd GitHub labels, including one with the Jira ticket key (e.g., `JIRA-1234`), and any additional relevant labels (e.g., bug, enhancement, infra).\n5.\tAlso include a label named `auto_assign` in all creations.\n6. The GitHub issue body should end with the following directive:\n🚨 **IMPORTANT NOTE FOR COPILOT**: When creating the pull request to resolve this issue:\n 1. You **must ALWAY include the Jira ticket ID** (e.g., `JIRA-1234`) in the **PR title**.\n 2. Do **not** rename the PR title or remove the Jira ticket reference.\n 3. Add GitHub labels with the Jira ticket key (e.g., `JIRA-1234`) to the PR.\n\nIf no direct match can be confidently made (e.g., across multiple repos), make a best guess, and clearly state any assumptions in the issue body.",
"execution_mode": "Automatic",
"conversation_starters": []
"conversation_starters": [],
"tools": [
"^(list|get|search|track|describe)_.*",
"run_create_github_issue"
]
},
"relations": {}
}
```
</details>

5. Click `Create` to save the agent.
:::tip MCP Enhanced Capabilities
The AI agent uses MCP (Model Context Protocol) enhanced capabilities to automatically discover important and relevant blueprint entities via its tools. The `^(list|get|search|track|describe)_.*` pattern allows the agent to access and analyze related entities in your software catalog, providing richer context for GitHub issue creation. Additionally, we explicitly add `run_create_github_issue` to the tools, which instructs the AI agent to call this specific action to create GitHub issues from Jira tickets.
:::

:::tip Enhance Context with Integrations
The more integrations and data you add to the agent, the richer the context it will provide to the Copilot agent. Consider integrating additional data sources like deployment history, related incidents, and more to enhance the AI agent's effectiveness.
:::
5. Click `Create` to save the agent.


## Set up automations
Expand Down Expand Up @@ -207,7 +201,7 @@ This automation can be configured to trigger based on various criteria. Currentl
},
"invocationMethod": {
"type": "WEBHOOK",
"url": "https://api.getport.io/v1/agent/github_issue_creation/invoke",
"url": "https://api.getport.io/v1/agent/work_item_synchronizer/invoke",
"agent": false,
"synchronized": true,
"method": "POST",
Expand Down
35 changes: 13 additions & 22 deletions docs/guides/all/enrich-tasks-with-ai.md
Original file line number Diff line number Diff line change
Expand Up @@ -65,37 +65,28 @@ Install the following integration to have access to these data sources:
```json showLineNumbers
{
"identifier": "task_assistant_ai_agent",
"title": "Task Assistant AI Agent",
"icon": "Airflow",
"title": "Clarity AI",
"icon": "Details",
"team": [],
"properties": {
"description": "Automatically enriches Jira tasks with relevant context when developers start working on them",
"status": "active",
"allowed_blueprints": [
"service",
"githubRepository",
"_user",
"githubPullRequest",
"jiraIssue",
"jiraProject",
"githubUser",
"_team",
"jiraUser"
],
"allowed_actions": [
"comment_on_jira_issue"
],
"executionMode": "Automatic",
"prompt": "## Comment Format\n\nHey there [User's First Name], it's Clarity - the Port AI agent!\nI noticed you just started working on a new task: [link to assigned issue].\nHere's some context to help you get started\n\nDevs who might have input:\nList up to 3 developers (excluding the user), explain briefly why each is relevant. If none, write a meaningful explanation.\n\nSimilar Jira Issues:\nList up to 3 Jira issues (not assigned to the user), mention the assigned person and why it's relevant. If none, explain why.\n\nSimilar Pull Requests:\nList up to 3 pull requests (not assigned to the user), mention the creator and why it's relevant. If none, explain why.\n\nEach section can have fewer than 3 items. Always explain if empty.\n\n## Instructions\n\nSend the comment according to the format above in the most relevant given JIRA Issue. Use the `comment_on_jira_issue` tool to achieve that.",
"allowed_tools": [
"Entities Search",
"Entities Similarity Search",
"Entities Group"
"prompt": "# Task\nUse the \"comment_on_jira_issue\" action, automatically send a greeting using their first name and explain this is an automatic message. Then share three sections with emojis for helpful context.\n\n## Message Format\nHey there [First Name], it's Clarity :crystal_ball: - the Port AI agent!\nI noticed you just started working on a new task: [link to assigned issue].\nHere's some context to help you get started :blobdance:\n\n:male-technologist: Devs who might have input:\nList up to 3 developers (excluding the user), explain briefly why each is relevant. If none, write a meaningful explanation.\n\n:jira: Similar Tasks:\nList up to 3 Jira issues (not assigned to the user), mention the assigned person and why it's relevant. If none, explain why.\n\n:github_on_fire: Similar Pull Requests:\nList up to 3 pull requests in statuses \"open\" or \"merged\", mention the creator and why it's relevant. If none, explain why.\n\n## Guidelines\n- Each section can have fewer than 3 items. Always explain\n",
"execution_mode": "Automatic",
"tools": [
"^(list|get|search|track|describe)_.*",
"run_comment_on_jira_issue"
]
},
"relations": {}
}
```
</details>

:::tip MCP Enhanced Capabilities
The AI agent uses MCP (Model Context Protocol) enhanced capabilities to automatically discover important and relevant blueprint entities via its tools. The `^(list|get|search|track|describe)_.*` pattern allows the agent to access and analyze related entities in your software catalog, providing richer context for task enrichment. Additionally, we explicitly add `run_comment_on_jira_issue` to the tools, which instructs the AI agent to call this specific action to comment on Jira issues with contextual information.
:::

5. Click on `Create` to save the agent.

### Set up the automation trigger
Expand Down