Product
Meet Pip.
Ask Pip to write it, plan it, debug it, or argue with your thesis. And under the courses sits a floor of lessons written ahead of time, not improvised by a model.
An assistant you can hold to its word
- Write, plan, code & research
- Deep research cites its sources
- Admits when it isn't sure
- No ads, ever
- Authored courses for 12 exams
Capabilities
What Pip does today.
One section per capability, each with a link to the doc that explains how it works and where its limits are. Under each picture, one line says whether it is the real app with sample data or a drawing.
Chat
One cockpit, 4 models.
Auto answers every question with GPT-5.6, and appears once your plan has two or more models. Or pick a model yourself: the cockpit says what each one is for and roughly what a reply costs.
Answer style set to Understand, and the model rows on the Free plan: the free model picked, the other two locked.
Research
Sources you can open.
Thorough deep research reads real pages and pins citations to the claims they support, so you can open what it read.
An answer with two numbered citations, and the list of its two sources, open.
Images
From sentence to image.
Describe what you want, pick a style, refine the picture you like. Each style adds a short art direction to your words.
An image card drawing "A labelled diagram of a plant cell".
Code
Code that runs, not just reads.
On a computer, the code workspace writes a small web app, runs it in a live preview and shows every error it throws, word for word, so you can paste it back to Pip and fix it together. In chat, attach your source files, in dozens of languages, and Pip reads your actual code rather than a paraphrase of it.
A six-line code sample in a code block with a copy button.
Study
And then there's the part nobody else has.
Most assistants improvise school. chud ships 12 courses (the SAT, the ACT and 10 AP exams): 471 topics, each with a lesson written ahead of time, not generated the moment you ask, and key terms you can save as flashcards. Here is the whole ledger, counted from the shipped curriculum:
Counted from the shipped curriculum, not typed into the page. If a course ever ships unfinished, this table says so on its own.
Memory
It remembers you, on the record.
Pip carries what matters between sessions: your classes, your goals, how you like things explained. What it stores is a list you can read, and every entry can be deleted on its own: memory you can audit, not a vibe you have to trust.
Three things chud remembers: Taking AP Biology this year; Likes a worked example before the answer; Unit 3 test is on Friday.
Install
The app is the download.
chud ships a web app manifest and a service worker, so a browser that supports installation can add it to a home screen or dock and open it without browser chrome. There is no app store listing to wait on and nothing to update by hand.
What you get
Four things it does properly.
One assistant, every lane
Write, plan, debug, argue with your thesis. One thread, one model picker, no app-switching.
How chat worksBring your own files
Attach a syllabus, a lab sheet or a chapter as text or a photo. It reads it and answers from it.
Working with filesYour week, with dates on it
Add your classes and test dates once. Today shows what's next and how many days until each test.
How Study worksIt ends up where you work
Google Docs and PDF: a document leaves the chat as a real file. Grades and quiz history go to Google Sheets.
How exporting worksIllustration of what chud does, not a screenshot.
Models
The roster, on the record.
This list is read from the same catalog the in-app picker renders, engine names included, so what is advertised here is what you get. Auto answers every question with GPT-5.6; the engine names below are exactly what runs, and an ordinary reply names the engine that answered it under More. On the pricing page, Pip Lite is GPT-4o mini and Pip is GPT-5.6.
No per-message prices are printed here: every reply is charged from the tokens it actually used, at least 0.8 of a token and up to 64 tokens for one reply (deep research and images keep their own prices), so the cost depends on how long the answer is. Monthly allotments live with the plans.
Sends every question to GPT-5.6.
from Student
The fastest, lightest tier. Streams answers instantly for quick questions.
from Free128K context
OpenAI's current reasoning model — plans before it answers, and thinks harder as the question gets harder.
from Student400K context
Also available, your explicit pick
from Pro400K context
from Pro500K context
chud is in beta. Things ship most weeks, some of them break, and when they do we say so rather than quietly patching it. Read what changed.
Pricing
Free is a real tier.
Free
120 tokens a month
Real chat, and deep research that shows its sources. No card, ever.
What counts as a token?Pro
1,440 tokens a month
Every model, the code workspace, and the design canvas.
What counts as a token?