Deep research

Garden · not yet reviewed Established: widely used Widely discussed since 2024-12

An AI mode that spends several minutes searching many sources, reading and cross-checking them, and returns a longer cited report on a question.

Also called: Research mode · DeepSearch · research agent · Deep Research

Connections

Understand first

Ideas this one builds on.

• Agents (garden)

Related

Often used together or easily confused.

• Verification (garden)
• Hallucination (garden)
• Clarifying questions (garden)
• Reasoning models (garden)

Resources that teach it

• Behind the Craft — Transcripts (garden)
• ChatGPT vs Claude vs Gemini: The Best AI Model for Each Use Case in 2025 (garden)
• Perplexity Academy (garden)
• Perplexity at Work Guide (garden)
• Search vs Computer (garden)

Competency

• Frame the outcome
• Check the result

Find deep research on the commons map ↗

You may know it from

• academia a literature review Gathering and summarising what many sources say on a question, with references a reader can follow.
• consulting an analyst's briefing memo

In products

The same idea, under different names in different tools.

Provider	What they call it
Anthropic	Claude Research
OpenAI	ChatGPT deep research
Google	Gemini Deep Research
Perplexity	Perplexity Research
xAI	Grok DeepSearch

In plain words

Deep research is a research agent. You ask a question, it may ask a few clarifying questions, and then it runs dozens of searches, reads pages and documents, and writes a report with citations. It takes minutes instead of seconds, and the result is much longer than a normal answer.

It is good for getting oriented fast: the range of options, the main arguments on a policy question, what competitors offer. It is weaker on very recent events, paywalled sources and niche facts, and it can cite a source that doesn’t say what the report claims.

The report looks finished, which makes it easy to trust too much. Treat it as a well-organised first pass. Open the citations behind the claims you plan to rely on, and notice which important sources are missing.

Example

A policy analyst asks for a summary of how five cities fund after-school programs. The report is useful, but two of the figures trace back to a 2019 page. She updates them from current budgets before sharing.

How it connects

• A specialised agent focused on searching and reading.
• Many versions start with clarifying questions before the long job begins.
• Polished reports still need verification; citations reduce hallucination but don’t remove it.

Try it

Pick a question for deep research and write down three sources or facts a good answer should include. When the report arrives, check whether they’re there, and open one citation to confirm it says what the report claims.

---

Read this card as plain Markdown: /concepts/con-deep-research.md. Know a parallel from your own field, or a product that implements this? Add it.