All templates By NappAI team Jira issue type classifier
Jira agent that classifies the corresponding issue type for each issue in a specific project.
graph TD
%%{init: {'theme': 'mc','layout': 'elk'}}%%
ParseData-aice2[<div><img alt="logo" src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data]
style ParseData-aice2 stroke:#a170ff
Prompt-8pfns[<div><img alt="logo" src="/_astro/square-terminal.BMOXc-nZ.svg" style="height: 20px !important;width: 20px !important"/></div>Prompt]
style Prompt-8pfns stroke:#a170ff
ChatOutput-zqoh9[<div><img alt="logo" src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output]
style ChatOutput-zqoh9 stroke:#a170ff
OpenAIModel-zu1vo[<div><img alt="logo" src="/_astro/openAI.BhmuxEs3.svg" style="height: 20px !important;width: 20px !important"/></div>OpenAI]
style OpenAIModel-zu1vo stroke:#a170ff
JiraReader-i2erv[List Issue Types]
style JiraReader-i2erv stroke:#a170ff
JiraIssueHandler-8ctxx[Update Subtask]
style JiraIssueHandler-8ctxx stroke:#a170ff
JiraIssueHandler-phklc[Update Issue]
style JiraIssueHandler-phklc stroke:#a170ff
JiraReader-3f3ut[Jira Reader]
style JiraReader-3f3ut stroke:#a170ff
AdvancedAgent-4g9ht[Agent2]
style AdvancedAgent-4g9ht stroke:#a170ff
ParseData-aice2 -.- Prompt-8pfns
linkStyle 0 stroke:#a170ff
JiraReader-3f3ut -.- ParseData-aice2
linkStyle 1 stroke:#a170ff
Prompt-8pfns -.- AdvancedAgent-4g9ht
linkStyle 2 stroke:#a170ff
AdvancedAgent-4g9ht -.- ChatOutput-zqoh9
linkStyle 3 stroke:#a170ff
OpenAIModel-zu1vo -.- AdvancedAgent-4g9ht
linkStyle 4 stroke:#a170ff
JiraIssueHandler-phklc -.- AdvancedAgent-4g9ht
linkStyle 5 stroke:#a170ff
JiraIssueHandler-8ctxx -.- AdvancedAgent-4g9ht
linkStyle 6 stroke:#a170ff
JiraReader-i2erv -.- AdvancedAgent-4g9ht
linkStyle 7 stroke:#a170ff
🧩 Overview
The workflow automatically classifies the type of each Jira issue within a given project and updates the issue type accordingly. It retrieves the list of issues, formats them into a prompt, uses an advanced AI agent to decide the most suitable issue type for each entry, and finally applies the changes via Jira tools while presenting the outcome in a chat‑style interface.
⚙️ Main Features
- Automated issue retrieval from Jira projects.
- Dynamic prompt construction that lists each issue with key details.
- AI‑driven decision making using a large language model and a set of specialized Jira tools.
- Automatic issue‑type updates performed by the agent through the Jira Issue Handler.
- Human‑readable chat output that summarizes the actions taken.
🔄 Workflow Steps
| Component Name | Role in the Workflow | Key Inputs | Key Outputs |
|---|---|---|---|
| Jira Reader (List Issues) | Retrieves all issues from a specified Jira project. | Project Key (e.g., “SCRUM”) | jira_response Data (list of issue records) |
| Parse Data | Formats the retrieved issue data into a plain‑text list using a predefined template. | jira_response Data |
text Message (formatted list of issues) |
| Prompt | Builds the final prompt by inserting the formatted issue list into the task description. | issues_list Message (from Parse Data) |
prompt Message (AI prompt) |
| Advanced Agent | Orchestrates the AI reasoning process, manages tool usage, and produces the final response. | prompt Message, llm (OpenAI Model), tools (JiraReader tool, JiraIssueHandler – Update Subtask, JiraIssueHandler – Update Issue) |
response Message (agent’s conclusion and actions) |
| OpenAI Model | Provides the language model that the agent uses to generate responses. | Model Name (gpt‑4.1), temperature, other parameters | model_output LanguageModel (supplied to the agent) |
| Chat Output | Displays the agent’s final message in a chat‑style format. | response Message |
Displayed chat message |
🧠Notes
- The OpenAI Model is configured with gpt‑4.1 and a low temperature (0.1) to encourage consistent, deterministic responses.
- The Advanced Agent can fall back to other models if the primary one fails, though only the primary is shown in this flow.
- Tools are exposed to the agent as reusable actions:
- JiraReader tool (List Issues) – provides fresh issue data on demand.
- JiraIssueHandler – Update Subtask – updates a sub‑task’s issue type.
- JiraIssueHandler – Update Issue – updates a main issue’s type.
- All data flows are strictly sequential; no branching is used in this configuration.
- The system assumes valid Jira credentials and network connectivity to the Jira instance.
- The chat output is purely for human readability; it does not alter the underlying data beyond the Jira updates performed by the agent.