ToolsAugust 22, 2026via InfoQ AI/ML
Presentation: SafeChat: Building AI-Powered Safety Systems at Scale in a Real-Time Marketplace
Why it matters
A real production case study showing how to build scalable AI moderation without LLM-only economics. Practitioners deploying safety systems at scale will see actionable architectural patterns.
Key signals
- Hybrid moderation pattern: fast internal models for obvious cases + LLM for nuanced multi-axis scoring
- Replaces costly LLM-only pipelines
- No-code workflows with backtesting built in
- Scaled to millions of daily messages
- Cut safety incidents while reducing cost
- Content-agnostic design (reusable across use cases)
- Hybrid architecture: fast internal models for obvious cases + LLM multi-axis scoring for nuance
- No-code workflows with backtesting capability
- Scales to millions of daily messages
- Reduced safety incidents vs. LLM-only pipeline
- Cost optimization through architectural pattern (internal models first, LLM as refinement layer)
The hook
DoorDash cut safety-incident costs by hybrid-stacking: fast internal models + LLM multi-axis scoring. Here's the architecture.
Bruna Pereira explains how DoorDash built a content-agnostic AI moderation platform. She covers replacing costly LLM-only pipelines with a hybrid pattern: using fast internal models to filter obvious cases, LLM multi-axis scoring for nuanced decisions, and no-code workflows with backtesting. Discove…