You are helping me build the following AI agent workflow.

## Goal
Marker.io Issues to Intercom Conversations: When a bug is reported via Marker.io, it automatically creates an Intercom conversation with the reporter's details and attaches all...

## Specification
- What it does: You get instant Intercom conversations created whenever a bug is reported via Marker.io, complete with attached screenshots, console logs, and browser details. This ensures your support team receives full technical context and synchronized reporter information immediately to resolve issues faster.
- Trigger: Triggered by an event (Event · on new bug report)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Marker.io: Receiving bug reports via webhook
  - Intercom: Creating support conversations and contacts
  - HTTP Request: Sending data to Intercom API
  - Code: Formatting and extracting payload information

## Known pitfalls, handle each one explicitly in your implementation
1. Intercom requires a valid user email to link conversations, so you must ensure the Marker.io payload includes an email or create an anonymous contact first.
2. Large screenshot URLs may exceed API body size limits, so strip binary data or use direct image upload endpoints instead of embedding them in the JSON payload.
3. Authentication tokens expire without warning, so implement a refresh mechanism for your Intercom access token to prevent silent failures during long-running workflows.

## Reference implementation
https://n8n.io/workflows/7388 (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-marker-io-issues-to-intercom-conversations/ via usecasesforagents.com