The client folder as context
The brand guide, past deliverables and the current brief from the shared Drive folder, so every draft starts from what the client already approved. See client projects.
If your business lives in Google Drive, the documents your AI needs are already written: the proposals, the meeting notes, the plans, the spreadsheets. Where Google Drive import is enabled, a MultipleChat Project lets you pick the files that matter and use them as context for ChatGPT, Claude, Gemini and the others, without downloading and re-uploading every time. This page is what it does, what it does not, and how to use it well.
Availability depends on your plan and region; the documentation has the current details.
| It does | It does not |
|---|---|
| Let you pick specific files or folders from your Drive to include in a Project | Index your entire Drive or watch it continuously |
| Make those files available as context for any model you use in that Project | Edit or write back to your Drive files |
| Let you re-sync a file when the Drive version changes | Replace Google Drive as the place your documents live |
| Work alongside direct uploads and, where enabled, GitHub import | Grant MultipleChat access beyond what you select |
Google Drive import is available on plans and in regions where it is enabled. If you do not see the option in a Project, check the documentation for your plan.
The brand guide, past deliverables and the current brief from the shared Drive folder, so every draft starts from what the client already approved. See client projects.
The business plan and the budget live in Drive and get edited there. Sync them into the Project and ask "what changed since last month, and what should I do about it?"
Import the meeting-notes doc. Ask what was decided about pricing in the last quarter, and get the answer with the date.
A folder of PDFs and docs on one topic, compared by several models for what each claims and where they contradict.
On team plans, colleagues work in the same Project against the same Drive-backed files. See team projects.
When someone leaves, the Project still holds the files and the reasoning. Nothing lived only in their chat history.
Context works best when it is relevant. Ten well-chosen documents beat two hundred.
"pricing.xlsx is the current price list; 2024-plan.docx is the old plan, for reference only." Models make fewer mistakes when told what to trust.
Prices, plans and notes drift. A quick sync makes the answer current.
"Quote the section" and "which sheet and cell" make answers checkable against the Drive original.
Working from real documents is exactly where model quality shows: following a question across a long plan, reconciling two versions, not inventing a number that is not in the sheet. The paid plans add the upload capacity a real document set needs and the models that read it properly.
Newer models hold your whole Project in view instead of the last few messages, reason through trade-offs instead of picking the first plausible answer, and are wrong less often and with less confidence. For the questions on this page, that is the difference between advice that sounds right and advice you can act on.
Pro from $20 a month, cancel any time. The free plan stays free.
Import the files that matter and describe them in the instructions. Then start here.
No. You connect your account and choose the specific files or folders to import into a Project. Nothing outside your selection is read.
No. Imported files stay in your account, are encrypted, and are never used to train any model by MultipleChat or the AI providers.
You re-sync a file when it has changed. It is not a continuous watch on your Drive.
Yes, from the integrations settings in your account.
It is available where enabled; the documentation and plans pages have the current details.
Yes. A Project can hold direct uploads, Drive imports and, where enabled, GitHub imports side by side.
Import them into a Project, describe them, and ask the question you have been meaning to ask. Free to start.
Also: analyse files with AI · GitHub projects · client projects · how Projects work
Continue learning
Run the same prompt through ChatGPT, Claude, Gemini and Grok before trusting one answer.
Core featureLet several models draft, challenge and verify each other instead of trusting one answer.
ProjectsKeep files, instructions, code and chats together so every model works from the same context.
FeaturesModels, Projects, collaboration, verification, Studios and images in one workspace.
ResearchSourced answers, a second model checking, evidence kept in a Project.
TrustClaim by claim, with a model that was not the author.
Market researchPerplexity Sonar Pro finds the facts with sources; the reasoning models check them and size the market.
FilesPDFs, spreadsheets, docs and notes, with numbers double-checked.
GitHubSelected repo files as context for every model.
ComparisonWhy disagreement between models is the useful answer.
ProjectsHow a Project keeps files, instructions and chats together.