You are helping me build the following AI agent workflow.

## Goal
Data Analysis for Operations and Finance: Ask ops or finance questions; the agent queries live records, runs Python analysis, and returns tailored insights.

## Specification
- What it does: Ask operational or finance questions and receive solid analysis from live data without manual digging. The system routes your query to the correct dataset, pulling operational records for operations teams or general ledger entries for finance teams. It then uses Python to analyze that specific data and deliver clear outputs tailored to your role.
- Trigger: Run manually (Manual · on demand)
- Autonomy: You stay in control
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Python: data analysis and processing
  - LLM: interpreting user questions and routing to data sources

## Known pitfalls, handle each one explicitly in your implementation
1. Financial data often contains sensitive PII, so implement strict row-level security filters before any LLM processing occurs.
2. Departmental terminology varies widely between teams, so maintain a glossary mapping common slang to standard financial terms.

## Reference implementation
https://www.youtube.com/watch?v=cbqEapA-2Po (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-data-analysis-for-operations-and-finance/ via usecasesforagents.com