You are helping me build the following AI agent workflow.

## Goal
Lead Prospecting & Research: Provide customer examples, then the agent uses Manis.AI and an LLM to research and identify new leads matching your Ideal.

## Specification
- What it does: You get new leads that match your ideal customer profile by providing example profiles for research. The agent uses Manis.AI and an LLM to find individuals globally or locally who fit these criteria.
- Trigger: Run manually (Manual · on demand)
- Autonomy: You stay in control
- Expected setup effort: under an hour
- Tools/services involved:
  - Manis.AI: ICP research and lead finding
  - LLM: Analyzing customer database examples to identify patterns

## Known pitfalls, handle each one explicitly in your implementation
1. Data privacy regulations like GDPR can restrict processing personal data, so implement strict filtering for compliant regions.
2. LLM hallucinations may invent contact details, add a verification step using authoritative third-party APIs before outputting results.
3. High volume requests can trigger API rate limits, configure batched processing with exponential backoff to maintain stability.

## Reference implementation
https://www.youtube.com/watch?v=5hZCTc_mwOg (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-lead-prospecting-research/ via usecasesforagents.com