You are helping me build the following AI agent workflow.

## Goal
Prospect Audit & Lead Scoring: One prompt triggers five parallel agents that research companies, find decision-makers, qualify leads.

## Specification
- What it does: Get a full prospect audit with researched companies, identified decision-makers, qualified leads, and personalized outreach sequences in under one minute by simply entering your target details.
- Trigger: Run manually (Manual · on demand)
- Autonomy: You stay in control
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Claude Code: Orchestrating parallel agents for research and outreach

## Known pitfalls, handle each one explicitly in your implementation
1. Parallel agents may exceed token limits if company research returns overly verbose data so implement strict summarization steps before aggregation.
2. Decision-maker identification can yield false positives if relying solely on public profiles so verify roles against current organizational charts where possible.
3. Personalized outreach might sound generic if the LLM fails to incorporate specific recent news about the target company so include a mandatory context injection step.

## Reference implementation
https://www.youtube.com/watch?v=JqXkPlX_4gQ (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-prospect-audit-lead-scoring/ via usecasesforagents.com