You are helping me build the following AI agent workflow.

## Goal
Detect Churn Risk From Competitor Tech Adoption: Weekly scan of customer tech stacks flags high churn risk when competitors like HubSpot are detected within 90 days of renewal.

## Specification
- What it does: You get immediate alerts when your customers adopt competitor tools like HubSpot or Salesforce within 90 days of their renewal date, allowing you to intervene proactively before they churn. This weekly scan checks tech stacks via PredictLeads and notifies the assigned Customer Success Manager through email so you can secure retention early.
- Trigger: On a schedule (Scheduled · weekly)
- Autonomy: You stay in control
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Google Sheets: Store customer domains and renewal dates
  - PredictLeads API: Fetch tech stack and detect competitor tools
  - Gmail: Send churn risk alerts to CSMs
  - Slack: Optional team notifications
  - Code: Logic for competitor detection and risk calculation

## Known pitfalls, handle each one explicitly in your implementation
1. The PredictLeads API may return inconsistent casing for tool names so normalize all strings to lowercase before comparison.
2. Email delivery can fail if the Gmail account lacks proper OAuth scopes so verify permissions in the Google Cloud Console first.
3. False positives may occur if a customer uses a free tier of a competitor tool so refine the detection logic to prioritize enterprise plans.

## Reference implementation
https://n8n.io/workflows/14882 (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/detect-churn-risk-from-competitor-tech-adoption/ via usecasesforagents.com