🦞 4minAI.com
1 / 13
Day 15 of 28 Β· ChatGPT Course

Deep Research

Sometimes you need more than a quick answer. You need a thorough, multi-source investigation with citations, analysis, and structured conclusions. That is exactly what Deep Research does.

Deep Research is ChatGPT's built-in research agent. Instead of answering from memory, it goes out, reads dozens of web pages, cross-references information, synthesizes findings, and delivers a structured report complete with citations. Think of it as having a research analyst on call 24/7.

Today you will learn how to use Deep Research effectively, how to shape and guide the research plan, and how to get the most out of this powerful feature.

Deep Research workflow β€” ask a question, create plan, read sources, synthesize report
Deep Research reads dozens of sources and produces a cited, structured report.

How Deep Research works

When you activate Deep Research, ChatGPT does not just run a single web search. It performs multi-step research across multiple sources, following leads the way a human researcher would:

1. You submit your research question -- a topic, a comparison, a market question, anything that requires depth.

2. ChatGPT generates a research plan -- an outline of what it intends to investigate, which angles it will cover, and what sources it will look for.

3. You review and edit the plan -- you can add focus areas, remove irrelevant sections, or redirect the investigation before it begins.

4. The agent browses and reads -- it visits dozens of web pages, extracts relevant information, and takes notes. You can watch its progress in real time.

5. It synthesizes and delivers -- the final output is a structured report with inline citations linking back to every source it used.

Deep Research can take anywhere from a few minutes to over 30 minutes depending on the complexity of the question. It is designed for quality, not speed.

πŸ€–
ChatGPT
online
I need a deep research report on the current state of AI regulation in the EU, US, and China. Compare their approaches and highlight key differences.
I'll create a research plan for this. Here's what I intend to investigate: **Research Plan: AI Regulation Comparison** 1. EU AI Act -- current status, risk categories, enforcement timeline 2. US executive orders and proposed legislation -- federal vs. state approaches 3. China's AI regulations -- algorithm rules, generative AI measures, data laws 4. Side-by-side comparison of key provisions 5. Industry impact and compliance requirements 6. Expert commentary and future outlook Would you like me to adjust this plan before I begin? I can add or remove sections, or focus on specific aspects like enforcement or industry impact.
Add a section on how each region handles open-source AI models specifically. Then go ahead.
Added section 7: Open-source AI model policies by region. Starting research now. This will take approximately 10-15 minutes. I'll browse multiple government sources, legal analyses, and industry reports. You can watch my progress below and redirect me at any time.
↻ Replay conversation
Knowledge Check
What makes Deep Research different from a regular ChatGPT web search?
A
It uses a different AI model entirely
B
It only searches academic databases
C
It requires a separate subscription
D
It performs multi-step research across dozens of sources, synthesizes findings, and provides citations
Regular web search checks a few sources quickly. Deep Research is a multi-step agent that reads extensively across many sources, cross-references information, and produces a cited, structured report. It trades speed for thoroughness.

Editing and steering the research plan

One of the most powerful aspects of Deep Research is that you control the plan before it runs. This is where most people miss an opportunity. Instead of accepting the default plan, take a moment to shape it:

Add specificity. If you are researching a market, tell it to focus on your specific segment. "Focus on B2B SaaS companies with 50-200 employees" is far more useful than "research the SaaS market."

Remove noise. If the plan includes sections you do not care about, remove them. Fewer sections means deeper coverage on what matters.

Specify source types. You can tell Deep Research to prioritize certain kinds of sources: "Focus on peer-reviewed studies and government reports" or "Prioritize recent articles from the last 6 months."

Direct to specific sites. You can instruct Deep Research to look at particular websites or connected apps like Google Drive and OneDrive. For example: "Check our company's Google Drive for last quarter's sales data and compare it with public market reports."

Knowledge Check
When should you edit the Deep Research plan?
A
Only after the research is complete
B
Before it begins, to add focus areas, remove irrelevant sections, or specify source types
C
You cannot edit the research plan
D
Never -- the AI knows best what to research
Editing the plan before research begins is one of the most valuable things you can do. It focuses the research on what actually matters to you, resulting in more relevant and useful output. Think of it like briefing a research assistant before sending them to work.

Tracking progress and adjusting mid-run

While Deep Research is running, you can watch its progress in real time. ChatGPT shows you:

- Which sources it is currently reading

- What information it has gathered so far

- How far along it is in the research plan

You can also redirect the research mid-run. If you notice it is going down an unproductive path, you can step in and say "skip this section and focus more on competitor pricing" or "I need more data on the European market specifically." The agent will adjust its approach accordingly.

This makes Deep Research feel less like a black box and more like a collaborative process. You are the director; ChatGPT is the researcher doing the legwork.

πŸ€–
ChatGPT
online
Use Deep Research to find the best project management tools for remote teams under 50 people. Focus on pricing, integrations, and real user reviews.
**Deep Research Complete** (12 minutes) ## Best Project Management Tools for Remote Teams Under 50 People ### 1. Linear - **Pricing:** $8/user/month - **Best for:** Engineering-heavy teams - **Key integrations:** GitHub, Slack, Figma - **User sentiment:** Praised for speed and clean UI (4.8/5 on G2) [1] ### 2. Notion - **Pricing:** $10/user/month (Plus plan) - **Best for:** All-in-one workspace teams - **Key integrations:** Slack, Google Drive, Zapier - **User sentiment:** Loved for flexibility, some find it overwhelming (4.7/5) [2] ### 3. Asana - **Pricing:** $10.99/user/month (Starter) - **Best for:** Cross-functional teams - **Key integrations:** 200+ native integrations - **User sentiment:** Strong workflow automation, steeper learning curve (4.4/5) [3] *Report continues with 4 more tools, comparison table, and recommendation matrix...* **Sources:** 23 sources cited, including G2 reviews, official pricing pages, and industry comparison articles.
↻ Replay conversation
Knowledge Check
What can you do while Deep Research is actively running?
A
Cancel it and start over
B
Nothing -- you must wait until it finishes
C
Watch its progress and redirect it if it is going down an unproductive path
D
Run multiple Deep Research queries simultaneously
Deep Research shows real-time progress and allows you to intervene mid-run. If you see it heading in the wrong direction, you can redirect it to focus on what matters most. This collaborative approach leads to better results.

Best use cases for Deep Research

Deep Research shines when you need depth, breadth, and citations. Here are the use cases where it delivers the most value:

Strategy reports. Competitive landscape analysis, market entry research, technology evaluations. Deep Research can compare multiple companies, products, or approaches across dozens of sources.

Literature reviews. Academic and professional literature surveys. It can find and summarize relevant papers, articles, and reports on any topic.

Market analysis. Pricing comparisons, feature matrices, customer sentiment analysis. It pulls data from review sites, pricing pages, and industry reports.

Due diligence. Investigating companies, technologies, or partnerships. It digs into public information, news coverage, and expert commentary.

Travel and event planning. Detailed itineraries with pricing, reviews, and logistics pulled from multiple travel sources.

Learning new domains. When you need to quickly get up to speed on an unfamiliar field, Deep Research gives you a structured overview with pointers to the best sources.

The common thread: any time a simple answer is not enough and you need a well-researched, well-cited document, Deep Research is the right tool.

Knowledge Check
Which of the following is the BEST use case for Deep Research?
A
Getting a quick definition of a word
B
Asking what the weather will be tomorrow
C
Creating a competitive analysis report comparing five SaaS tools with pricing, features, and user reviews
D
Setting a reminder for a meeting
Deep Research is designed for complex, multi-source research tasks. A competitive analysis across five tools requires visiting many websites, comparing data points, and synthesizing findings -- exactly what Deep Research excels at. Simple questions are better handled by regular ChatGPT.
πŸ”¬
Day 15 Complete
"Deep Research turns ChatGPT from a quick-answer tool into a thorough research analyst. Shape the plan, watch the process, and get cited reports you can trust."
Tomorrow β€” Day 16
Projects
Learn how to organize your chats, files, and context into structured Projects for ongoing work.
πŸ”₯1
1 day streak!