WeSolve+ reads the whole document and writes the questions for you
Upload your PDF, photograph your notebook, or point the camera. WeSolve+ writes questions from that material, explains why each answer is right, reads the chapter back to you as a podcast, and remembers every item you missed until you own it.
The tool below is a small browser-only tool and it is not WeSolve+: paste a few lines and text rules turn them into cards on the spot. The real app, the one that uses AI, is behind the link above.
Passage in, comprehension questions out
This is a browser-only tool, and that is all it isIt splits the text you paste by rule, and nothing else. WeSolve+ is a different thing entirely: it reads your whole PDF with AI, writes the reasoning behind every question, speaks the chapter back to you, and remembers what you missed so it can return it. Try the real app now, free!
This tool uses text rules, not AI. Question lines keep their answers, "term: definition" lines become vocabulary checks, and plain statements lose their most distinctive word so the reader must supply it from the passage. It drafts from what you paste; deciding whether a question tests the passage or mere memory of trivia stays your judgement.
The ladder: four kinds of comprehension question
Literal questions check what the text states; a reader can point to the line. Inference questions ask what must be true though no line says it, motives, causes, what happens next. Vocabulary in context asks what a word does in this sentence, not what a dictionary says. Author's purpose asks why the piece exists and how its choices serve that. A set that never leaves the first rung tests attention, not comprehension; a set that skips it floats free of the text.
Stems that keep questions anchored to the passage
Every stem should fail if the reader has not read: "according to the passage", "which line supports", "what does the author mean by". Stems that a well read student can answer without the text, general knowledge in costume, measure the wrong thing. The cleanest check is evidence pairing: ask the question, then ask which sentence proves the answer. If no sentence does, the question does not belong to this passage.
Passage length and where questions should land
A useful rule of thumb: one question per meaty paragraph, plus one inference and one vocabulary item per passage, keeps density honest without strip mining the text. Spread the landing spots, opening claim, pivot, conclusion, because clustering questions on one paragraph lets a reader skim the rest unpunished. Passages of two hundred to five hundred words carry a ten question set comfortably; longer texts deserve sectioned sets.
Grading comprehension without grading vocabulary luck
Wrong answers split into misreadings, which the passage can correct, and missing background, which it cannot. Mark them differently: a reader who inferred sensibly from a misread pronoun needs a rereading habit, not a content lecture. For vocabulary items accept any phrasing that captures the in context meaning; demanding the dictionary's wording turns a comprehension check into a memory test of the wrong book.
How the generator fits this page
Paste the passage, or passage plus your own question lines, and the tool drafts in the browser: your questions keep their answers, definition lines become vocabulary checks, and key statements become supply the word items. Nothing uploads and nothing is stored. It cannot judge inference quality, rules cannot, so treat its output as a first pass you prune with the evidence pairing test above.
Where the free tool ends and WeSolve+ begins
The tool reads one pasted passage; the app reads the whole reading. Upload a PDF chapter and WeSolve+ generates comprehension sets with reasoning behind each answer, reads the chapter aloud as an audio recap, and returns the questions you missed on a schedule until they stick. Paste here for today's passage; bring the book to the app.
Sources used on this page
- Reading comprehension
- Inference
- Close reading
- Cloze test
- Readability
- Flesch-Kincaid readability tests
- Vocabulary
- Context (language use)
- Main idea
- Reading (process)
- Literacy
- SQ3R
- Skimming (reading)
- Author
- Paragraph
- Testing effect
- Formative assessment
- Educational assessment
- Multiple choice
- Metacognition
- Working memory
- Cognitive load
- Text (literary theory)
- Lexile
- Phonics
- Fluency
- Standardized test
- Evidence
| Rung | What it asks | The tell of a good item |
|---|---|---|
| Literal | What the text states | A line can be pointed to |
| Inference | What must be true | No line says it, several imply it |
| Vocabulary in context | What the word does here | Dictionary answer is not enough |
| Author's purpose | Why the piece exists | Choices tie to effect |
| Evidence pairing | Which sentence proves it | Answer and proof travel together |
| Main idea | What holds it together | Distractors are true but partial |
What kinds of questions does this generate?
Drafts of literal, vocabulary and supply the word items from your pasted text, plus your own question lines with answers kept. Inference items remain your job to write and judge.
Does it use AI?
No. It applies text rules in your browser and uploads nothing. That is why it is instant, private and free, and why it drafts rather than judges.
How long should a passage be?
Two hundred to five hundred words carries a ten question set comfortably. Longer texts belong in sectioned sets with questions spread across sections.
How many questions should I ask per passage?
About one per substantial paragraph plus one inference and one vocabulary item. This page's tool caps at ten so density stays honest.
What makes a comprehension question bad?
It can be answered without the passage. If general knowledge or a skim suffices, the item measures the wrong thing; anchor stems to the text and pair answers with evidence.
What does the WeSolve+ app add over this tool?
Whole PDF reading sets with per answer reasoning, audio recaps of chapters, and spaced return of missed questions until they hold.
Last updated: 2026-08-15