You are helping me build the following AI agent workflow.

## Goal
Sync And Score PLG Leads: Automates the PQL lifecycle by scoring trial users daily and syncing intent data from Segment to Attio for instant outreach.

## Specification
- What it does: You get instant outreach to high-intent trial users by having this agent score them daily and sync their intent data from Segment directly to Attio. It automatically routes these leads into conversion sequences while using AI to scan for buying signals or churn risks in Intercom, significantly reducing your manual SalesOps work.
- Trigger: Triggered by an event (Scheduled · daily 7:00 and Event · on new lead)
- Autonomy: Fully hands-off
- Expected setup effort: a few focused days
- Tools/services involved:
  - Segment: Webhook trigger for product usage data
  - Anthropic: Classifying PQL intent via Claude
  - OpenAI: Analyzing Intercom conversations
  - Attio: CRM deal and profile management
  - Lemlist: Automating outreach sequences

## Known pitfalls, handle each one explicitly in your implementation
1. LLM latency may delay real-time scoring so cache the classification result for a short window before re-evaluating.
2. Data schema mismatches between Segment and Attio will break syncs so validate field types during initial integration setup.

## Reference implementation
https://n8n.io/workflows/15297 (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/sync-and-score-plg-leads-with-ai/ via usecasesforagents.com