You are helping me build the following AI agent workflow.

## Goal
Instagram Content Discovery & Repurposing: Monitors competitor Instagram reels, extracts insights via AI, and generates original scripts stored in your spreadsheet.

## Specification
- What it does: Track competitor Instagram reels and instantly generate tailored video scripts stored directly in your spreadsheet. The system transcribes content, filters for relevant tools, and uses AI insights to create original drafts optimized for your audience without manual duplication checks.
- Trigger: On a schedule (Scheduled · daily)
- Autonomy: You stay in control
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Apify: Instagram scraping and content discovery
  - OpenAI: Video transcription and script generation
  - Perplexity AI: Enhanced research and insights
  - Google Sheets: Database for tracking posts and scripts

## Known pitfalls, handle each one explicitly in your implementation
1. Apify scrapers can fail if Instagram changes its HTML structure so you should monitor actor logs and update selectors regularly.
2. Video transcription may include background noise or overlapping speech which requires post-processing prompts to clean up the text.

## Reference implementation
https://n8n.io/workflows/4658 (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/instagram-content-discovery-repurposing/ via usecasesforagents.com