Lesson 404 of 2116
ChatGPT For Research: Connectors And Document Q&A
ChatGPT can now read your Drive, your Notion, your wiki — if you let it. The research workflow that emerges is genuinely new, and so are the trust and access questions.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1Connectors, in plain English
- 2connectors
- 3document Q&A
- 4permission scope
Concept cluster
Terms to connect while reading
Section 1
Connectors, in plain English
A connector is a permission grant that lets ChatGPT search and read content from another service — Google Drive, SharePoint, Notion, internal wikis. Once granted, the model can answer questions across those sources with citations. It is the consumer-tier version of enterprise document search, with all the access-control implications that come with it.
What changes about your research workflow
- You stop pasting documents into chats — the model retrieves the right passages on demand.
- You ask cross-source questions — 'what did we decide about pricing in last quarter's Drive memos AND last month's Notion docs?'
- You start trusting citations as a navigation aid — click through to the source, do not assume the model summarized correctly.
- You realize how messy your file structure is, because the model surfaces it.
Compare the options
| Connector | Best at | Worst at |
|---|---|---|
| Google Drive | Cross-document Q&A on owned content | Files you have access to but don't own |
| SharePoint / OneDrive | Workplace knowledge | External-facing collateral |
| Notion | Active project documentation | Long-archived pages |
| Internal wiki connectors | Process and policy lookup | Real-time data, dashboards |
Permission scoping is everything
When you connect Drive, the model can see whatever YOU can see. That includes documents shared with you, accidental over-sharing, and the team folder a former colleague gave you in 2021. Audit the scope, not the connector.
Deep Research vs connector Q&A
Deep Research mode runs a longer, multi-step research loop with its own retrieval and citations — typically across the public web. Connector Q&A is faster but private. Use Deep Research for public-knowledge synthesis, connectors for grounded answers about your own corpus, and combine them only when you understand which sources are which.
Applied exercise
- 1Pick one research question you currently solve by tab-hopping across files.
- 2Connect the relevant store, ask the question, and click every citation.
- 3Note one citation that did not fully support the claim made.
- 4Decide a scoping rule for yourself — 'I will only keep connectors live for the current quarter's projects'.
Key terms in this lesson
The big idea: connectors give ChatGPT real reach into your work. The work of using them well is permission hygiene plus citation verification, every time.
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “ChatGPT For Research: Connectors And Document Q&A”?
Ask anything about this lesson. I’ll answer using just what you’re reading — short, friendly, grounded.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 32 min
Kimi Research Mode — autonomous deep research
Kimi's Research Mode plans, browses, and synthesizes across dozens of sources. Here is how to get the most out of it.
Creators · 40 min
ElevenLabs v3 — voice cloning use cases
ElevenLabs v3 clones a voice from seconds of audio. Here is what to build, what to avoid, and how to stay on the right side of consent.
Creators · 10 min
Code Interpreter / Advanced Data Analysis: What It Can And Can't Do
Code Interpreter looks magical and is genuinely useful, but it runs in a sandbox with real limits. Knowing those limits saves hours of stuck-in-a-loop debugging. What is actually happening when ChatGPT runs code Code Interpreter (also known as Advanced Data Analysis) is a Python sandbox running on OpenAI's servers.