You are helping me build the following AI agent workflow.

## Goal
Coding From New Jira Tickets: New Jira ticket? The agent writes code in a cloud environment and posts deep links to resume the session directly back in the ticket.

## Specification
- What it does: When a new Jira ticket arrives, you get an AI coding session started in your cloud environment that generates code based on your request. The agent posts the results and deep links directly back to your ticket so you can resume work immediately from within Jira or your IDE.
- Trigger: Triggered by an event (Event · on new Jira issue created)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Jira Software: Trigger and update ticket comments
  - CloudCLI: Run isolated AI coding agent sessions
  - LLM: Generate code via Claude Code or similar

## Known pitfalls, handle each one explicitly in your implementation
1. Large ticket descriptions can exceed token limits so truncate the body or summarize it before sending to the LLM.
2. Ambiguous ticket requirements lead to poor code output so include explicit constraints in the generated system prompt.

## Reference implementation
https://n8n.io/workflows/14070 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/automate-ai-coding-from-new-jira-tickets/ via usecasesforagents.com