Skip to content
InfratoApp

NVIDIA · Course

Build a Deep Research Agent (self-paced)

Build a Deep Research Agent is a self-paced, hands-on NVIDIA course on building autonomous research agents with the NVIDIA AI-Q Research Assistant Blueprint. You combine reasoning models, RAG and web search to produce cited research reports.

Open at NVIDIA ↗Common questions

Who it suits

  • Developers who want hands-on practice building an enterprise-style deep research agent.
  • Teams exploring agent workflows that plan, search several sources and synthesise reports.

What it covers

  • Deploying and interacting with NVIDIA Nemotron reasoning models on NVIDIA-hosted endpoints.
  • Building RAG pipelines for multimodal document ingestion and semantic retrieval.
  • Agentic workflows: planning, tool calling and iterative refinement.
  • Deploying the AI-Q Research Assistant Blueprint, and orchestrating parallel searches across private documents and the web.
  • Generating cited research reports with human-in-the-loop guidance.

Common questions about Build a Deep Research Agent (self-paced)

How is it taught?
Hands-on, through Jupyter notebooks and interactive web interfaces, per NVIDIA’s description.
Does it cost anything?
NVIDIA sells the self-paced course with Buy Now and Redeem Code options, and says online purchase is supported in select locations. Its page states the price, which changes, so check it.
What do I build?
A deep research agent that conducts multi-step research by combining reasoning models, retrieval-augmented generation and web search.

More like this

Keep learning on Infrato

Where this comes from

Written from NVIDIA’s own pages, read on 2026-10-13. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with NVIDIA and this is not an endorsement.