You are helping me build the following AI agent workflow.

## Goal
Hyper-Personalized Sales Pitch Generation: Analyzes buyer history, social activity, and context to generate hyper-personalized sales pitches tailored to their industry and buying...

## Specification
- What it does: You get hyper-personalized sales pitches automatically generated for every buyer by analyzing their history, social activity, and current context. These tailored messages match your prospects' specific industries and buying stages to ensure each communication resonates individually.
- Trigger: Run manually (Manual · on demand)
- Autonomy: You stay in control
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Pitchy: Writing hyper personal sales messages
  - LLM: Analyzing buyer context and generating content

## Known pitfalls, handle each one explicitly in your implementation
1. Social media data can be outdated or private so verify the recency and public nature of sources before including them in the prompt.
2. Over-personalization can feel creepy if it references minor details too intimately so set clear boundaries on what constitutes appropriate context.

## 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/hyper-personalized-sales-pitch-generation/ via usecasesforagents.com