Safety · AI System Designstaff

Trust & Safety / Content Moderation at Scale

Components

Drag onto the canvas, or click to add.Tap to add to the canvas.

Utilities

Text Box

Group / Container

Circle

Diamond

Divider Line

Heading

Recommended

Client / User

LLM / Model

Model Router

Database / State

Guardrail / Classifier

Observability / Tracing

Human-in-the-Loop

Entry & gateway

Client / User

LLM Gateway

API Gateway

Orchestration

Orchestrator / Planner

Agent / Worker

Agent Loop

Models

LLM / Model

Model Router

Embedding Model

STT / TTS

Retrieval / RAG

Retriever

Reranker

Vector Store

Knowledge Source

Tools & execution

Tool / Function

MCP Server

Code Sandbox

Browser / Computer Env

External API

Memory & state

Working Memory

Long-Term Memory

Cache (semantic/prompt)

Safety & eval

Guardrail / Classifier

PII Filter / Redactor

Eval / Judge

Observability / Tracing

Infra & data

Database / State

Queue / Event Bus

Human

Human-in-the-Loop

Drag or click a component on the leftTap Components to add your first piece

connect · iterate · submit for review

// brief

Trust & Safety / Content Moderation at Scale

Design LLM-based moderation for a platform with millions of posts/day — detect and act on harmful content under tight latency.

Key Requirements

01Tiered pipeline: cheap fast filter → LLM only for borderline
02Per-category precision/recall targets by severity
03Hash-matching/specialized pipelines for the worst content (not LLM)
04Human review queue + appeals (false-positive recovery)
05Adversarial robustness; regional policy; explainability

Rubric must-haves

0/3

Has classifier/guardrail stage(s)
Has tiering/routing (cheap → LLM)
Has a human review queue

These checks are the structure score, 30% of your total. They update as you draw.

Practise it like the real round

60-minute timer paced through requirements, design and deep dive. The follow-up questions stay hidden until the last phase, and solution hints are off.

AI Review

0/5

Review me as:

Build your design, then submit for an AI-powered review with dimension scores, strengths, gaps, and actionable suggestions.

Try designing your solution first before viewing hints.

Comments (0)

Loading comments...