You are helping me build the following AI agent workflow.

## Goal
Review of Slack Product Release Messages: New Slack release posted? The agent reviews it with AI to approve, exclude, or auto-generate the final message.

## Specification
- What it does: Review your Slack product release messages to determine if they are ready for public release or should be excluded. Generate a post automatically when the AI approves the announcement.
- Trigger: Triggered by an event (Event · on new release announcement)
- Autonomy: You approve along the way
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Slack: receiving product release messages
  - Make AI toolkit: analyzing message content and deciding on public release status

## Known pitfalls, handle each one explicitly in your implementation
1. Sensitive internal jargon might confuse external audiences, so explicitly instruct the LLM to translate technical terms into plain English.
2. Overly aggressive rewriting by the LLM may lose critical nuance, so include a 'do not change' constraint for specific regulatory or compliance statements in your prompt.

## Reference implementation
https://www.youtube.com/watch?v=DcpMaUuqOWc (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/ai-review-of-slack-product-release-messages/ via usecasesforagents.com