Companion videos

Deep Research mode: a 20-page report without reading 50 tabs — companion videos

The article frames Deep Research as a different mode of working with AI — one query, a wait, a long cited document — and walks through when it earns the wait. The picks below show that flow on real tasks: a literature review for a PhD-shaped problem, and the same kind of feature inside Perplexity in a wider data-analysis workflow.

Primary pick

13:59

How to Use ChatGPT's Deep Research to Save HOURS on Research

Andy Stapleton

Stapleton runs Deep Research against the exact use case it shines at — a literature review with a clear scope, time frame, and structure — and shows the clarifying-questions handshake, the 10-minute wait, the 40-source output, and where the citations and tone still need a human pass. Calls out the limits honestly (no BibTeX export, occasionally too generous in source choice).

What you should get from this: Scope a deep-research task, wait for the report, then verify citations and source quality before using it.

Watch or know first: A research question where source quality matters and enough domain knowledge to reject weak references.

AI Expert note: Deep-research products change quickly across ChatGPT, Gemini, Perplexity and Claude. Keep the workflow discipline: ask for scope, inspect sources, check missing viewpoints and rewrite conclusions yourself.

Open video page

Also worth watching

21:48

AI For Data Analysis In 21 Minutes

Tina Huang

Tina puts Perplexity's Deep Research and ChatGPT/Claude analysis modes in the context of a working analyst's day — pulling together market signals, exploratory data analysis, and structured outputs. Useful as the "what else is this good for besides academic literature reviews" companion to the primary pick.

What you should get from this: See deep research and analysis modes applied to business research rather than only academic literature.

Watch or know first: Basic spreadsheet or market-research comfort.

AI Expert note: Watch for tool boundaries: research, data analysis and presentation generation are different jobs. Validate numbers, sources and assumptions before turning an AI-produced analysis into a business recommendation.

Open video page