You are helping me build the following AI agent workflow.

## Goal
Lead Qualification via DMs: Qualifies social DM prospects against three must-have criteria using Revieo and LLM to filter out unqualified leads before human engagement.

## Specification
- What it does: You save time by automatically filtering unqualified social DMs against three must-have criteria using Revieo and an LLM before you engage. This ensures only serious prospects reach your inbox for further conversation.
- Trigger: Triggered by an event (Event · on new DM)
- Autonomy: You approve along the way
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Revieo: Social DM interaction and qualification
  - LLM: Filtering tire kickers based on criteria

## Known pitfalls, handle each one explicitly in your implementation
1. Prospects might share sensitive personal data in chats so ensure the pipeline encrypts or redacts PII immediately upon receipt.
2. Context windows can fill up quickly during long conversations so implement a sliding window strategy to keep only recent relevant messages.

## Reference implementation
https://www.youtube.com/watch?v=b3yuAekDS4U (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/ai-lead-qualification-via-dms/ via usecasesforagents.com