Teaching Sidekick to say no: automated data curation with LLM judge consensus (2026) - Shopify
Our Sidekick team used LLM judges to automatically curate training data and teach domain-specific models how to refuse impossible queries.
Score breakdown
- Technical depth52
- Practical value75
- Originality100
- Writing quality100
- Source reputation86
- Recency1
- External engagement0
- On-site engagement0
More like this
Etsy — Code as Craft58
Machine Learning in Content Moderation at Etsy
David Azcona·unknown·5 min read
Netflix Tech Blog55
The Data Canary: How Netflix Validates Catalog Metadata
Netflix Technology Blog·unknown·7 min read
Etsy — Code as Craft50
Kafka App? There’s a Skill for That
Isobel Scott·unknown·6 min read
Airbnb Engineering53
From weeks to a day: how we made LLM evaluation fast enough to iterate on
Baharak Saberidokht·unknown·10 min read
Engradar shows a summary and links to the original article. The full article is hosted on shopify.engineering.