Teaching Agents to Search with NVIDIA Data Designer — Dhruv Nathawani, NVIDIA
Dhruv Nathawani uses that funnel to explain how NVIDIA builds synthetic data that teaches a model to search, rather than answer from memory.
Proof1 independent outlet
Key points
- 50,000 seed examples become 7,000 training records after generation and filtering.
- Data Designer turns those seeds into questions, tool calls and responses, with Tavily providing search through MCP.
- Questions distinguish seed generation from agent execution, explore reinforcement learning alternatives and discuss other training tasks.
- 0:00 - Turn an agent behavior into a data pipeline
Sources (1)
- [1]Teaching Agents to Search with NVIDIA Data Designer — Dhruv Nathawani, NVIDIAAI Engineer (YouTube) · Oct 11, 04:30 PM
Dhruv Nathawani uses that funnel to explain how NVIDIA builds synthetic data that teaches a model to search, rather than answer from memory.
50,000 seed examples become 7,000 training records after generation and filtering.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 11, 2026AI Security Engineer Foundations + Certificate — Micah Silverman, Snyk
- Oct 9, 2026Show HN: Edi Life OS – self-hosted life dashboard with an MCP server for AI
- Oct 8, 2026openai/codex rust-v0.162.0: 0.162.0
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 8, 2026DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition
- Oct 7, 2026MotherTree: Meta-learning on synthetic data improves decision tree training
