Deep Research

Deep Research is source-grounded investigation for professionals and teams. Ask a work question, attach library, Drive, or team material when you have it, say what the work needs to produce, and the agent investigates — filling gaps from the open web — then returns a circulatable artifact: a brief, comparison table, cited report, slide deck, or training pack.

It is not a web-search chatbot. The job is a work artifact out: a cited review, a comparison, a one-page brief, or training the team can use. Attach sources when they exist; start from a question when the evidence is public.

Starting a Research Session

Open Research from the Create menu or from Home's Research composer. Both take you to Research, where past investigations sit under a composer.

The composer is one row. Type the question, attach sources if you have them, and press start.

1. Type the question, or attach sources from your library, a team library, Google Drive, or an upload. Sources are optional when the evidence is public.
2. Choose what to Produce: Brief, Table, Cited report, or Slides. You can pick more than one.
3. Optionally start from a job — Literature review, Market landscape, Policy analysis, or Due diligence memo. A job pre-fills the setup for that kind of investigation; you can still change anything before starting.
4. Everything else — output, evidence class, depth, model, project, and the Extended toggle — lives in a single Options menu next to the prompt.

Your projects sit above Recent on the research page, so a session can start in the right workspace.

If you still have an old /home?create=research bookmark, that guided source flow still works.

Starting from AI Chat

You can also start a research session from any AI chat. Ask the AI to investigate a work question — for example, "research these vendor claims against our RFP" or "map this year's regulatory changes for leadership." The AI asks what you want produced, then runs the investigation in the background. When the work is ready, it appears inline in the conversation.

Evidence filters

Before starting, you can favor specific evidence classes. Choose one or more from the Evidence control:

• Papers & journals — Peer-reviewed journals, working papers, and scholarly articles.
• Handbooks & manuals — Professional handbooks, codes, manuals, and textbooks used as reference works.
• News & industry — Recent reporting and industry analysis.
• Government & policy — Official publications, statutes, agencies, and public data.

Leave all filters off to search across all source types.

Linking Your Library

Sources are first-class. Click the attach control on the composer to add:

• PDFs and other documents you have uploaded
• Pages you have written
• Library files — saved notes, outlines, CSVs, code, and other text/data files
• Folders from your workspace or a team library
• AI Meeting Notes (with their transcripts)
• Podcasts (with their transcripts)
• Previous research reports

You can also pick Google Drive files directly — Google Docs, Sheets, Slides, PDFs, Word docs, PowerPoints, or text files — without downloading and re-uploading. See Connections.

Attaching Files Directly

You can also attach a file directly into a research session. Deep Research reads PDFs, PowerPoint, Word, and text files, not just images. Drop them into the composer the same way you'd attach an image.

Linked and uploaded sources are primary. The agent researches the open web to fill gaps, not to replace what you attached. Linking a previous report is useful for extending an earlier investigation instead of starting over.

Clarifying Questions

If you already picked a Produce chip or named the artifact in the prompt, preparation can skip the output question. Otherwise the AI asks what you want produced — a cited report, slides, a one-page brief, a comparison table, a training outline, or more than one of those. Options are tailored to your request, and you can pick several or type your own. It may also ask a short follow-up about audience, angle, or timeframe when that would change the result.

If the questions are not relevant, skip them to jump straight into research. A cited report is the default when you skip and did not already name an output.

Report Length

Choose how long the finished work should be from the length dropdown next to the prompt:

• Short — One-page brief.
• Medium (default) — Decision memo.
• Long — Full investigation.

AI Model

Choose which model plans the investigation, analyzes sources, and writes the result from the model picker next to the prompt. Paid plans can pick a specific model; free users can browse the options with locked models shown behind a lock badge. Scholarly remembers the model you pick for Research separately from AI Chat and your other creation tools. See Choosing an AI Model.

Extended Research

Switch on Extended in Options to put a team on the question instead of a single researcher: parallel researchers, a currency scout, an independent fact checker, and a reviewer. It costs 3 AI creations, takes about 10–20 minutes, and is available on paid plans.

Go deeper does the same thing to a report you already have, chasing newer data, primary sources, and whatever the first pass left open.

Both have their own guide: Extended Research and Go Deeper.

Research Plan and Progress

Once research begins, a live timeline shows what is happening:

• The step it is on, and how long the run has taken so far against the typical range for that kind of research.
• How many sources it has read and how many facts it has found.
• The latest sourced facts, appearing as sources are read.
• On Extended runs, a running count of what the fact checker confirmed and corrected, with each claim marked Confirmed, Corrected, Contested, or Unsupported.
• Who did each step — on an Extended run the steps are attributed to the researcher, scout, fact checker, reviewer, or analyst who did them, including the messages they sent each other.

You can leave the page. The run keeps going and you are told when the report is ready.

Code Execution

The AI can run Python code, analyze data, and create visualizations during research. This happens automatically when the work involves data processing or when charts and graphs would strengthen the result.

Summary: the Answer and the Files

A finished investigation opens on Summary — a brief, not a stack of cards:

• The answer in a few sentences, how confident it is, and what is still open. There are no all-caps labels or nested cards to read past.
• Open questions are tappable. Tap one to ask it in the research chat, rather than being pushed toward making a video or a deck out of it.
• Files — By default the cited report arrives as one polished PDF rather than the same document duplicated across several formats. Alongside it, the agent produces the additional working files the investigation actually calls for: a comparison spreadsheet or CSV, a findings file, charts, and the working data behind every number it computed — including the analysis script, so you can rerun the math with your own assumptions. Every file opens in its own tab, and each can be saved to your library as a Library file.
• Report — The complete cited narrative, one click away from the Files list. It opens fully formatted rather than flashing plain text first, and keeps inline source pills, citations, embedded images, and charts.

The agent decides which supporting files the work needs and creates them on its own — you do not have to ask. Naming a specific artifact in the prompt or on the Produce row still steers exactly what gets made.

Sources

The Sources tab leads with the sources the report actually cites, ranked by how often each one is cited, with every retrieved source one tap away behind Show all retrieved sources.

Exports and citation lists share one menu. Citations copy straight to your clipboard in the style you pick, so you can paste a bibliography without downloading anything.

Each fact keeps the exact page it came from and its date, so a citation points at the page that carried the claim rather than the site's front door, and a newer figure wins over a stale one.

Report Timeline

The sidebar shows a clickable timeline of all reports in the session. Click any entry to jump directly to that report. Linked content from your library is also visible in the sidebar.

Follow-Up Questions

After the initial report is delivered, you can ask follow-up questions in the same session. The AI builds on its previous findings, so follow-ups are faster and more targeted than starting from scratch.

Actions from Research

After a report is complete, you can branch directly into other workflows from the actions above the report:

• Copy report -- Copy the report text to your clipboard.
• Create Page -- Turn the report into an editable page.
• Create Flashcards -- Generate flashcards from the findings.
• Download report -- Save the report to your device.
• Export -- Send the report out as an editable Word document or PowerPoint deck, or straight to Google Docs or Google Slides when Google Drive is connected. The source list exports on its own as a Word document, or a Google Doc with Drive connected, so you can hand over the bibliography without the narrative. Citation styles and the page options stay on the PDF export. Editable exports need a paid plan, and exporting creates a separate copy rather than changing the original. See Exporting Your Work.

To expand or refine the report itself, ask a follow-up question in the same session instead -- see Follow-Up Questions above.

Sharing

Share a completed research report with others. Recipients can view the full report including all sections, citations, and visualizations.

Archive and Restore

Archive research sessions you no longer need from the home page. Archived sessions are hidden from your main content list but not deleted. Restore them at any time to bring them back.

Research Index

The research page opens to a composer for a new investigation, with jobs you can start from and recent sessions underneath. Click any past session to jump back in, scan a previous report, or ask follow-up questions. Deleted sessions disappear right away — you don't need to refresh.

Limits

Deep Research draws from your shared AI Creation Credit allowance — the same pool that powers flashcards, podcasts, video lectures, slides, and other AI tools. On Free, those are lifetime free credits and do not reset. You can spend your free creations however you like instead of being capped on a separate research limit. Paid plans raise the allowance. See Plans and Limits.

A standard research run costs 1 AI creation. Extended research and Go deeper cost 3 and are available on paid plans.

Related

• Extended Research and Go Deeper — the research team, the fact checker, and Go deeper.
• Exporting Your Work — which formats a report and its source list export to, and what needs a paid plan.
• Library Files — saving the agent's working files and reusing them later.
• Connections — attaching Google Drive files and connecting Drive for Google exports.
• Plans and Limits — how research draws on your shared AI Creation Credits.