You are helping me build the following AI agent workflow. ## Goal YouTube Video Scheduling & AI Metadata Generation: Daily automation that extracts transcripts via Apify, generates SEO metadata with OpenAI, and schedules private videos for publication. ## Specification - What it does: You get your YouTube videos ready for publication automatically by having transcripts extracted via Apify and SEO-optimized descriptions generated with OpenAI. The workflow then updates the metadata and schedules each video to go live at strategic times while keeping it private until that moment. - Trigger: On a schedule (Scheduled ยท daily) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - n8n: Workflow orchestration and automation logic - YouTube: Video metadata retrieval, status updates, and scheduling - Apify: Extracting video transcripts for analysis - OpenAI: Generating SEO-optimized descriptions and tags from transcripts ## Known pitfalls, handle each one explicitly in your implementation 1. Transcripts may contain filler words that confuse the LLM, so instruct the model to ignore non-substantive speech patterns. 2. Scheduling too many videos at once can trigger spam filters, space out publish times by at least a few hours. ## Reference implementation https://n8n.io/workflows/3900 (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/automated-youtube-video-scheduling-ai-metadata-generation/ via usecasesforagents.com