You are helping me build the following AI agent workflow.

## Goal
Support Ticket Triage and Resolution: New support ticket? The agent labels it, simplifies the description, finds similar resolved issues, and suggests a fix.

## Specification
- What it does: You get new support tickets automatically labeled, prioritized, and simplified so your team can act faster. The agent finds similar resolved issues from Jira to suggest fixes directly within each ticket.
- Trigger: On a schedule (Scheduled · new JIRA tickets)
- Autonomy: You stay in control
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Jira Software: Issue management and ticket retrieval
  - OpenAI Chat Model: Analyzing tickets and suggesting fixes
  - Basic LLM Chain: Orchestrating the AI agent logic
  - Structured Output Parser: Formatting AI responses for JIRA updates

## Known pitfalls, handle each one explicitly in your implementation
1. LLM context windows can be exceeded by long comment threads so truncate historical summaries to the most relevant last few comments.
2. Sensitive customer data like PII could be sent to the LLM provider so ensure you mask or redact personal identifiers before processing.

## Reference implementation
https://n8n.io/workflows/3868 (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-support-ticket-triage-and-resolution/ via usecasesforagents.com