You are helping me build the following AI agent workflow. ## Goal Analyze Instagram Reels Trends And Save To Notion: Monitors selected Instagram accounts for trending Reels, analyzes engagement with Gemini. ## Specification - What it does: You stay ahead of viral Instagram trends by automatically tracking selected accounts with Gemini to spot high-engagement Reels early. The tool then saves these insights directly into your organized Notion database so you can quickly review what's working without manual data entry. - Trigger: On a schedule (Manual ยท on demand) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - Apify: Scraping Instagram Reels data - Gemini API: Analyzing engagement and detecting trends - Notion: Storing structured insights and results ## Known pitfalls, handle each one explicitly in your implementation 1. Instagram's anti-scraping measures can block your Apify actor, so implement random delays and rotate user agents carefully. 2. Gemini API costs can spike if you send large raw JSON blobs, so strip unnecessary metadata before sending the payload for analysis. 3. Reels metadata may lack direct engagement numbers due to privacy settings, so add fallback logic to use proxy metrics like comment density. ## Reference implementation https://n8n.io/workflows/5795 (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/analyze-instagram-reels-trends-and-save-to-notion/ via usecasesforagents.com