Create content with AI Studio

“Turn this into something I can share” is not quite a prompt yet. The useful question is what the next person should open: a document they can edit, a grid they can sort, an image they can review, a recording they can play, or a web page they can explore.

The short version

Choose Auto when you want AI Studio to select the output, or choose Doc, Table, Image, Audio file, or Web page when the deliverable is already clear. Add a focused prompt and only the files, URLs, or selected canvas objects the result needs. Submit once, review the draft on the canvas, and verify important facts before you share it.

AI Studio creates those first drafts directly on your canvas. Write a prompt, attach files or URLs, or select existing canvas objects to give the result context. The same source material can become five very different artifacts, so choosing the output is the first real decision.

Treat every result as a draft. AI Studio gets the first useful shape onto the canvas; you still own the facts, tone, dates, source permissions, and final handoff.

This article helps you choose an output and covers the workflow every output shares. For the step-by-step canvas entry flow, see Use AI Studio in a canvas.

Before you start

AI Studio creates canvas content, so it is available to workspace members who can edit the canvas. On desktop it appears as the canvas AI panel; on supported mobile or narrow screens it uses the canvas toolbar panel.

Credits are checked at submit time: AI work starts only after the workspace credit check passes. Workspace admins buy credits in Billing; other members need an admin to add them.

Choose what to create

Choose the artifact someone needs to use next. Auto is the safest starting point when the outcome is clear but the best artifact is not. It resolves the output type from the prompt and context. With completed files or URL tiles, it can also decide whether to save the source material, open Object Chat, or generate something new.

The subject does not choose the type. “Write a launch brief for a landing page” is a Doc. “Build the landing page” is a Web page. A comparison with recommendations is usually a Doc; a comparison people need to sort row by row is a Table.

This walkthrough shows selected canvas references becoming a web page, then moves from the canvas result into preview and sharing.

Image generation adds choices for model, references, count, style, ratio, speed, and relative cost. Those decisions belong in Create images with AI Studio; the overview only needs one rule: start with Auto unless a specific production constraint makes the choice matter.

The image workflow uses canvas references and a focused prompt, then places the finished result beside its source material.

Add the context AI Studio needs

The best prompt gives AI Studio the material it needs, not the most words.

When selected references provide a usable anchor, new placeholders appear to their right or below. Without one, AI Studio falls back to the visible center of your viewport so the generated work remains easy to see, move, or cancel. On a freeform whiteboard, smart arrows from a source object to a result let AI Studio and Object Chat treat the source as prior context.

Attachments

AI Studio accepts up to 10 attachments per draft (images, PDF, Office and HWP, Markdown, text and code, CSV, JSON, SRT, and spreadsheets), reading each for context up to a 20 MB per-file cap. Split oversized source material first.

Completed uploads are included in the request; in-progress uploads are not; failed uploads stay visible with an error so you can remove and retry. Draft recovery stores completed upload metadata, prompt text, selected context, and options, but not files that were still uploading, so reattach those.

When Auto sees completed attachments or prompt URLs, it runs an intent check before generating:

So "what does this say?" on a pasted URL gives you a source object plus Object Chat, while "turn this into a client-ready launch brief" gives you a generated Doc.

Write prompts that reduce cleanup

Give the model the decision shape you want, not just the topic: audience, format, source objects, and constraints. For example: Turn the selected notes into a one-page project brief for a product lead, with headings, risks, decisions, and next steps.

If a result is bland, do not keep regenerating the same vague request. Add the missing audience, format, source object, or constraint. Manual editing is often cheaper than asking AI to guess again.

Voice input is prompt writing, not generation: it checks credits before the browser microphone starts, then records, transcribes, and appends the transcript. If the microphone is blocked or missing, or transcription fails, the error appears in the prompt box; recordings with no speech are treated as empty. Skim the transcript before submitting, because a small transcription mistake becomes a large mistake in the object.

Check generation status and review the result

After AI Studio accepts a request, work continues in the background and the placeholder is the live sign of progress. While it processes, output actions (edit, preview, download, duplicate, copy, lock, thumbnail) stay blocked; selection and deletion are the safe controls.

To cancel, delete the processing placeholder; deleting the canvas also stops any generation still running there. If generation already finished or credits were already consumed, deleting the final object does not undo the spend. Longer file-heavy, audio, image, and web page jobs continue server-side after you leave, so return to the canvas to review rather than resubmitting the same expensive prompt.

AI Studio and Object Chat are different

Use AI Studio when the next step is to create or save something on the canvas. Use Object Chat when the next step is to ask about one existing object or keep working on one result. It explains, rewrites, critiques, or edits an artifact after it exists. Generated and AI-edited objects can show an AI badge as their object-level AI entry point, which is separate from human comments. Before using AI output in client-facing work, read Review AI output and share web pages.

How credits are used

AI credits belong to the workspace. The actor is recorded for audit, but the balance is checked at the workspace level before any AI work runs. AI Studio generation, Object Chat messages, recommendation buttons, and voice transcription all go through the same check.

Admins recover by buying credits in Billing; non-admin members, external collaborators, and guests cannot buy credits from the blocked flow and need a workspace admin. Successful AI work can spend credits even if the output is later wrong, deleted, or needs cleanup, so check that the prompt and source context are worth the spend before a large image, audio, or web page request. For details, read Understand AI credits and AI credit billing.

When the result is not right

When you contact support, send the workspace name, canvas link, output type, prompt summary, attachment types, approximate time, and whether credits were blocked or spent. Do not send passwords, API keys, private customer data, or unnecessary source files.