You are helping me build the following AI agent workflow.

## Goal
Summarize YouTube Videos: Pastes YouTube links into a Google Sheet and automatically fills in the transcript, summary, key points, and main topics using AI.

## Specification
- What it does: You simply paste YouTube links into a Google Sheet, and the system instantly fills in transcripts, AI-generated summaries, key points, and main topics for each video using Supadata.ai and DeepSeek Chat Model. All results are automatically organized back into your sheet so you can review them immediately without manual transcription work.
- Trigger: Triggered by an event (Manual · on new row in Google Sheets)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - Google Sheets: Input video URLs and store results
  - Supadata.ai: Generate video transcripts
  - DeepSeek Chat Model: Create summaries and key points

## Known pitfalls, handle each one explicitly in your implementation
1. Supadata.ai may fail on copyright-protected content, so add error handling to skip invalid URLs and log the failure for manual review.
2. Long transcripts might exceed DeepSeek's context window, so implement logic in the code node to chunk the text before sending it to the LLM.

## Reference implementation
https://n8n.io/workflows/5412 (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/summarize-youtube-videos-with-ai/ via usecasesforagents.com