You are helping me build the following AI agent workflow.

## Goal
Real-Time Lead Scoring and Alerting: Monitors live video calls to score leads by buying signals and competitor mentions, sending instant Slack alerts for hot opportunities.

## Specification
- What it does: You get instant Slack alerts when live video calls reveal hot leads based on buying signals or competitor mentions. This lets your sales team immediately prioritize high-scoring prospects while they are still engaged.
- Trigger: Triggered by an event (Event · on new message)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - BeyondPresence: Video agent conversation monitoring
  - Slack: Sending real-time alerts and notifications
  - Code: Scoring engine and competitor detection logic

## Known pitfalls, handle each one explicitly in your implementation
1. LLM latency may delay real-time alerts significantly, so cache simple keyword matches and use the LLM asynchronously for deeper analysis when possible.
2. Sensitive customer data might be sent to third-party LLM APIs, ensure you strip PII from transcripts before sending them to the model for scoring.

## Reference implementation
https://n8n.io/workflows/4454 (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/real-time-lead-scoring-and-alerting/ via usecasesforagents.com