What's new

School portal connection FAQ

School portal connection FAQ

Here are answers to the questions we hear most about connecting your school portal.

Q. How do I connect?

  • ① Open 'Connect school portal' from GPAI Drive or Pie.
  • ② Enter your school name or course portal address.
  • ③ Sign in with your school account and choose the courses to bring in.

Q. Is my school supported?

  • Yes. GPAI currently supports every university in Korea.
  • You sign in with the school account you already use and bring in only the course materials you want.
  • It's the same as downloading course materials yourself and keeping them in your own storage to study. GPAI just makes that easier.
  • If connecting doesn't go smoothly, let us know through the in-app feedback form, Instagram DM, or email. We'll look into it and fix it right away!

Q. What does it bring in?

  • GPAI only reads, on your behalf, materials your account can already see, from courses you asked to connect and selected.
  • It can't access other students' materials or classes you don't take.
  • It can't edit anything or post on your school portal.

Q. Where are the materials stored?

  • They're kept in your GPAI Drive, which only you can see and use. It's your own storage, like Google Drive, iCloud, or the storage on your PC or phone.
  • GPAI staff can't open your materials at will.
  • GPAI never uses your materials for anything other than your own studying.
  • They're never used to train AI models.

Q. Is it safe to enter my school password?

  • You sign in through a dedicated secure login window, separate from the GPAI app.
  • Your password never leaves that window and is never passed to the AI.
  • To save you from typing it every time, it's encrypted and stored only if you agree.
  • Neither GPAI's AI nor its staff can see the original password, and no one can access even the encrypted password at will.

Q. What if I want to disconnect or delete materials?

  • Delete materials: you can delete stored materials yourself at any time.
  • Disconnect: your saved login details and password are deleted immediately.
  • Delete account: your login details and Drive materials are all erased.

Q. Do I have to connect to use GPAI?

  • No. You can upload files yourself and ask questions or study together.
  • Connecting just saves you from finding and uploading class materials every time.
  • If you get stuck while connecting, tell us which step you were on and what screen you saw!

Meet Pie, your new agent

Meet Pie, your new agent

You can now do everything on GPAI from one chat with Pie, your AI partner for school and life.

It works from what you've already made Pie uses your files, solved problems, and outputs in GPAI. Ask for practice problems on a topic, and it can build them from your own material.

Your deadlines, in one place Connect your school portal and Pie brings in your courses, deadlines, and announcements, keeps them in view, and reminds you ahead of time. It works with Canvas and many other school LMSs.

Stuck on something? Just ask Upload notes or an assignment and Pie explains it, or ask about a problem and work through it step by step.

Open Pie and tell it what you need. It takes it from there.


3 new styles in Figure Generator

Apparatus Describe a setup, e.g. "an inclined plane with a pulley," and get a 3D drawing with each part labeled. If the setup moves, the drawing plays: front view first, then the camera turns, then the parts move.

Map Draw countries, regions, and routes. Maps can also show terrain and ocean depth, climate, tectonic plates, earthquakes and volcanoes, biomes, historical borders, and typhoon tracks.

Timing diagram Draw how digital signals like clock, data, and control lines change over time.

How to use Pick a style from the Style menu in Figure Generator. If you leave it on Auto, GPAI picks one of these when your prompt fits. AI Chat and Solver can draw them too.

Meet collaborative editing

Meet collaborative editing

Word, Excel, PowerPoint, and Hangul files now open right in GPAI. Edit them with your team and AI at the same time, with no downloading and no sending files back and forth.

One file, edited by everyone at once Open a Word (.docx), Excel (.xlsx), PowerPoint (.pptx), or Hangul (.hwpx) file in AI Drive and it opens straight in an editor. Share it, and everyone works on the same file at the same time. Edits from each person show up for everyone right away, with no locks and no "who has the latest version?"

AI edits alongside you Open AI chat in the editor and ask, e.g. "Clean up the table in section 2" or "Add a total to column C." AI edits the same file while your team keeps working, and marks what it changed.

See who's working with you The people in the file appear at the top of the editor. Click someone to follow along and see what they're looking at. Use cursor chat to talk right where you're working.

Choose who can do what Invite people by email as an Editor, Commenter, or Viewer, or turn on a link anyone can use to view the file. People without access can request it, and you approve it.

Comments and version history Leave comments on the text or cells you're talking about. Every change is saved in version history, so you can restore an earlier version anytime.

When you're done Download it in its original format.


Connect your school's course site

Connect your school's course site

Sign in with your school account Tell us your school's name or the address you sign in at, and we'll find its course site. Sign in with your school ID and password, the way you always do. If your school asks for a code or an approval, you finish that step there too. Your ID and password are used only to sign in to your school, and kept encrypted only if you choose to.

Pick your courses We find your courses and how many files each one has. Choose the ones to sync — you can change this later. You can leave the page while we look.

Your files stay up to date Each course gets its own folder in AI Drive, and new files your school posts keep coming in. Ask AI about your lecture materials right where they are.

More schools than before Canvas schools can still connect with an access token, and many other school sites now work with a school sign-in. If yours doesn't yet, request support and we'll email you when it does.


Meet Slide Maker

Meet Slide Maker

Just drop in your materials PDFs, Word docs, slides, spreadsheets, images, your own notes — add what you have and one line about what the deck is for. Files already in AI Drive are one click away.

You see the outline first Fix the order and the wording while it's still a few lines of text, not twenty finished slides. If you already use a format, upload that PPTX or PDF as a template and your slides come back in the same look. When it's right, hit Generate slides.

Ask for changes, or make them yourself "Shorten slide 4", "turn this paragraph into a chart" — the chat beside your deck edits it in place. Or click any text to rewrite it and add charts, diagrams, tables, equations, and images yourself.

When it's done Present straight from GPAI, or download it as PPTX or PDF.


Meet AI Drive

Meet AI Drive

Everything you study, in one place You can now keep your lecture notes, PDFs, and assignments inside GPAI instead of digging through your downloads folder every time. Drag in files or whole folders, paste a YouTube link, and sort it all into folders you name yourself. Move, rename, and delete the way you would anywhere else, switch between grid and list, sort by name or size or date added, and pull a whole folder back down as a single file when you need it. The bar in the sidebar tells you how much room you have left.

Open a file and read it right there Click any file and it opens inside GPAI — PDFs, slides, Word documents, spreadsheets, images, video, and code. Search a PDF for a term, fit it to the width of your screen, or scrub a YouTube video and read the transcript beside it. Nothing downloads, and nothing sends you to another app.

Ask about what’s on your screen Open the chat panel next to your files and just ask. It already knows which file you have open and which page you’re on, so “explain this part” works without pasting anything in. Tick a few files to ask about them together, or drag across a sentence — or a spreadsheet cell — to quote it straight into your question. It can tidy up for you too: ask it to make a folder, rename a file, or move things around, and it shows you exactly what it’s about to do before anything changes.

Upload once, use it everywhere Every file in AI Drive is available to the rest of GPAI. Wherever you’d normally upload — Solver, the Twin Problem Generator, the Visualizer, AI Chat — there’s now a Choose from AI Drive option next to the upload button.


Now generate variations for multiple problems

Now generate variations for multiple problems

One upload, a variation for every problem You can now hand over a whole worksheet at once instead of one problem at a time. GPAI finds each problem inside the file and writes a matching variation for every one of them.

Upload a PDF, a DOCX, or a few photos, and the generator marks every problem it detects — just check the ones you want a variation for. Then pick a variation strategy problem by problem, or set one and hit “Apply to all”. The variations fill in one at a time on the set page, each one sitting right next to its original, so a full practice set comes back from a single upload.

You can also

  • Generate several versions of the same problem, each with a different variation strategy
  • Export the whole set as one file — PDF, DOCX, LaTeX (with Open in Overleaf), or PNG — laid out as an exam paper or grouped problem by problem

Choose the visuals in your Solver answers

You can now control the Figures Solver adds to your solutions.

Pick a level from the new Visuals selector before you solve:

  • None — no Figures, for the fastest answer.
  • Standard — Figures that work great for most problems.
  • Premium — higher-quality visuals for complex Figures (uses significantly more credits).

Premium visuals are available on paid plans.


A new editor for your Figures

You can now edit your Figures in a dedicated editor.

Open a Figure and a new editing dialog appears, where you can:

  • See the source code — switch between the rendered image and the exact code that created it, with syntax highlighting.
  • Edit by chatting — describe the change you want and the Figure is regenerated for you.
  • Browse every version you've made and pick the one you want.

No need to start over from scratch — just tell it what to change.


GPT-5.6 is here — Sol, Terra, and Luna

Four new models just landed.

  • GPT-5.6 Sol — OpenAI's most capable of the three tiers. In Solver, AI Chat, and chemistry figures in Visualizer.
  • GPT-5.6 Terra — the balanced tier. In Solver, AI Chat, and chemistry figures in Visualizer.
  • GPT-5.6 Luna — the fast, light tier. In Solver and AI Chat.
  • Grok 4.5 — xAI's latest. In Solver and AI Chat.

Open the model list and pick the one that fits.


Meet the Twin Problem Generator

Meet the Twin Problem Generator

Problem variation is here You can now turn one problem into a brand-new problem on the same concept, automatically. When you've just solved something and want one more like it, it's the fastest way to keep practicing.

Upload a photo of the problem and pick how you want it varied — the generator writes a fresh problem with the same structure, redrawing any figures too. Every variation comes with its answer and a step-by-step solution, right next to the original.

You can also

  • See at a glance what changed between the original and the variation
  • Copy the variation as text, or export just the parts you want

Introducing Figure Generator

Introducing Figure Generator

Make STEM visuals faster and simpler Create science visuals in less time — see all your generated images at a glance, and keep following the ones you've edited.

See the agent at work Some images show how they're built. While one is loading, tap it to follow the creation process and check the intermediate steps.

AI Chat now finds and verifies real research papers

You can now ask AI Chat to find and verify academic papers.

When you ask for papers, it brings back real ones. Give it a paper title or DOI and it checks that the paper actually exists before citing it, and warns you when something doesn't match.

You get grounded, citable references — no more made-up papers or fake citations.


Meet Problems, Visuals, and Chat — GPAI, rebuilt around its core

A few weeks ago we told you we were going all-in on three things. Now they each have their own name and identity: gpai problems, gpai visuals, and gpai chat — and the whole app is built around them.

We reworked the entire interface to be faster and easier to use. You can switch between the three from a single switcher at the top, and each one opens on its own home screen so you can get started right away.

Problems

  • The result page is redesigned around your answer.
  • Ask a follow-up question right under the solution, without leaving the page.
  • Highlight any part of the answer and tap "Ask GPAI" to dig deeper.

Visuals

  • We've upgraded the rendering engine, so everything from circuit and math diagrams to chemical structures comes out far more accurately.
  • Watch it revise in real time as it refines your visual.

Chat

  • Code execution is more reliable, with clearer recovery when something goes wrong.
  • PDF files are read more accurately, so answers stay grounded in your documents.

Meet the Visualizer's new image editor

Meet the Visualizer's new image editor

The Visualizer now has a full image editor built right in. Generate an image, select it, and hit Edit Image — it opens with two ways to work.

Chat to edit In the Chat tab, just describe what you want — "make the sky darker", "remove the background", "upscale this" — and it updates the image while keeping the parts you didn't touch.

Or fine-tune in the Edit tab Prefer hands-on control? The Edit tab lets you adjust the prompt behind the image, edit individual objects it detected (tap one and change just that), erase a part by painting over it, remove the background, upscale, or draw a box and leave a note for a precise edit. Hit Apply when you're ready.

Build it up on the canvas Every edit lands as a new version you can compare, and you can add any result back to your canvas to keep working. It all works on images you generate, images you upload, and illustrations from the library — and on desktop, you can even turn a flat image into editable vectors.

AI Chat can now run code and make files for you

Two upgrades to AI Chat this release.

It runs your code now, not just writes it Until now AI Chat could only write code for you to run yourself. Now it actually runs it. Ask it to plot a dataset, clean up a messy CSV, or work through a calculation, and it runs Python or shell commands behind the scenes and shows you the result right in the chat. Any charts or files it makes come back attached to the message.

Preview and download what it makes Files AI Chat creates now open in a side panel next to the chat — code, Office documents, and web pages all show up right there, each with a download button. See exactly what was made, then save it.

New models: GPT-5.5, MiniMax M3 & DeepSeek V4

Four new models just landed across AI Chat and Solver. Open the model picker and you'll find:

  • GPT-5.5 — OpenAI's newest model. In AI Chat and Solver.
  • DeepSeek V4 Flash — fast and light on credits, great for quick back-and-forth. In AI Chat and Solver.
  • MiniMax M3 — a strong all-rounder for everyday questions. In AI Chat.
  • DeepSeek V4 Pro — DeepSeek's most capable model for harder reasoning. In AI Chat.

Just open the model picker and choose the one you want.


Claude Opus 4.8 is here

Claude Opus has been upgraded to 4.8 everywhere you already use it.

Open the model picker in Solver, Visualizer, or AI Chat and you'll find Claude Opus 4.8 right where 4.7 used to be.

It's Anthropic's newest flagship — just pick Claude Opus 4.8 and go. Available on Plus and Pro plans.



Try Gemini 3.5 Flash in Solver and Chat

You can now pick Gemini 3.5 Flash in Solver and AI Chat.

Open the model picker in either Solver or AI Chat. Gemini 3.5 Flash now sits next to Gemini 3.1 Pro and the rest of the Claude, GPT, and Grok lineup, with a 1M-token context window for long inputs.

Faster runs than the heavier Pro models, on the same Gemini 3 generation. Available on Plus and Pro plans.


Pick your model in Visualizer

You can now choose which AI model draws your visualizations.

Tap Style / AI model in the Visualizer input bar. Pick a style — Illustration, Graph, Flowchart, Diagram, Circuit, Chemistry, or Logic — and you'll see the models available for it (Nano Banana, GPT Image, Gemini, Claude, Grok), with a Best tag on the recommended one. Select up to a few at a time and Visualizer renders them side by side so you can compare.

Stick with Auto if you don't care which model runs, or tune the lineup per style to dial in the look you want. Paid plans unlock the full set of models.


Meet a smarter AI Chat

Meet a smarter AI Chat

Live web search

You can now get answers backed by fresh information from the web. When a question depends on recent info — news, prices, schedules, ongoing events — AI Chat searches the web, reads the top results, and cites the sources right alongside its answer. Just ask normally; the search kicks in when current info is needed.

Images alongside answers

You can now get visual references right inside the chat. Ask about a person, a place, a labeled diagram, or any visual subject, and AI Chat pulls relevant images directly into the conversation instead of describing them in words. The picture arrives with the explanation — no more switching tabs to see what it's talking about.

Diagrams, plots, and circuits — drawn on the fly

You can now ask for a chart, a diagram, or a circuit, and AI Chat draws it for you. It picks the right format — plots for data, flowcharts and UML for systems, circuit diagrams for electronics, timing graphs for signals — and embeds the result right in the conversation. The picture lives next to the explanation, so you can see the concept and read the reasoning side by side.


Why we built it: STEM questions often need more than a paragraph of text — they need fresh sources, visual references, and proper diagrams. We rebuilt AI Chat around an extensible tool system so it can pick the right kind of answer on its own, and so we can plug in new tools as we go.


And that's not all

  • Reads links and files you share — paste a URL or attach a file, and AI Chat extracts and reads it before answering.
  • Asks when it's unsure — if your question is ambiguous, it pops a short form to clarify instead of guessing.
  • Chains tools in one turn — search → read → draw — AI Chat strings the steps together without asking you what to do next.

Release notes are here

You can now see every update we ship at GPAI.

Each new feature, improvement, and fix lands on the release notes page the moment it goes live, with a short note on what changed and why we shipped it.

You'll always know what's new — no need to ask, no need to guess.