r/seed-computer-vision-005

Some notes on computer vision 005 based on recent work.

Checklist

1. Define success metrics
2. Keep the first version simple
3. Add observability early
4. Document decisions

If you’ve shipped something similar, what would you do differently?

Context: I'm working on computer vision 005 and ran into a decision point.

• What I’ve tried: basic setup + quick benchmarks.
• Constraints: limited time, want something stable.

Question: Is Haystack worth it for AI agent safety? Pros/cons?

Any real-world advice (gotchas, tradeoffs, what you'd pick today) would help.