You are helping me build the following AI agent workflow.

## Goal
Sales Pipeline Debrief and Reporting: Every morning, an LLM synthesizes overnight CRM data into a concise debrief of ad opt-ins, lead contacts, and qualified appointments.

## Specification
- What it does: Start your day with a concise debrief of overnight ad opt-ins, lead contacts, and qualified appointments synthesized from your CRM data. You receive this clear summary via your preferred channel so you can immediately prioritize your sales activities without sifting through raw metrics.
- Trigger: On a schedule (Scheduled · daily morning)
- Autonomy: Fully hands-off
- Expected setup effort: about an afternoon
- Tools/services involved:
  - LLM: Summarize sales activity and generate debrief text
  - CRM: Retrieve opt-ins, connections, and booked appointments data

## Known pitfalls, handle each one explicitly in your implementation
1. Sensitive customer data might leak if not filtered out before sending to external channels, so sanitize PII fields strictly.
2. Timezone mismatches can cause incorrect overnight windows, so explicitly define the UTC offset in your query parameters.

## Reference implementation
https://www.youtube.com/watch?v=AOcNeochPV8 (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/automated-sales-pipeline-debrief-and-reporting/ via usecasesforagents.com