Knowing which failure you have decides which tool helps. WeSolve+ is best for the scheduling side, applied to material you already own. The tool below is the free entry to it.
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.
Notes to memory cues
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. It turns a line into a cue whose answer is hidden, which is the scheduling side of remembering. It cannot invent a mnemonic for you, because a good mnemonic connects to something only you already know. Your text stays in the browser and is never sent anywhere.
The two failures, and how to tell them apart
Ask what happens when you see the answer. If it feels obvious and you are annoyed at yourself, the item was encoded and the interval was too long, which is a scheduling problem. If it feels unfamiliar and you would not have produced it in an hour, encoding failed and no schedule will rescue it, because a scheduler can only bring back something that went in. Most people apply the scheduling fix to both and then conclude that their memory is bad. The distinction sits at the centre of how long term memory is studied, and it takes about five seconds to make.
What a scheduler is actually doing
It is exploiting a measured curve. Ebbinghaus described the shape of forgetting in 1885, and the practical consequence is that a review placed just as an item is about to become unavailable is worth far more than one placed while it is still easy. Modern spaced repetition software estimates that moment and puts the card there. The evidence base is unusually strong: the review by Cepeda and colleagues pooled 254 experiments and found spacing beating massing consistently. What a scheduler cannot do is make an item memorable, which is the other half of this page.
Mnemonics, and the cost nobody mentions
A mnemonic works by attaching arbitrary material to something already structured in your head, which is why the method of loci uses a building you know and the major system maps digits to consonants. These are genuinely powerful and they are what memory competitors use. The cost is that building one takes several minutes per item and the result is fragile if somebody else builds it for you, since the connection has to be to your associations. That makes them worth it for a short list you must have exactly, and a poor trade for two hundred cards.
Where the real gains are, and they are unglamorous
Two mechanisms do most of the work and neither needs a system. Chunking reduces the number of separate things you are holding, which is why a phone number is grouped and why a formula you understand is one item rather than nine symbols. Elaborative encoding is connecting new material to what you already know, and it is the reason asking why a fact is true remembers better than repeating that it is. Both are things you do while first meeting the material, which is exactly when most people are trying to get through it rather than into it.
What to distrust in this category
Brain training that promises general improvement is the main one: the transfer from a trained task to anything else is consistently weak, and the training makes you better at the training. Streak counters are a subtler problem, because a long streak is a measure of showing up rather than of remembering, and it invites the judgment of learning failure where confidence rises without recall. The honest metric in any app of this kind is how many items you produced correctly after a delay, and it is worth checking whether the app shows you that or shows you a number that only goes up.
The scheduling side, done from your own material
Upload a PDF, a photograph of a page or a camera shot and WeSolve+ writes the cues, keeps each one attached to the page it came from, and brings them back on a schedule rather than when you happen to think of them. Items you miss collect in their own list, so the next session opens with what failed rather than with what already works. That is the scheduling half; the encoding half stays yours, and the section above says what actually helps with it. At wesolveapp.com in any browser and on the App Store for iPhone and iPad, free to begin. Figures on pricing, and the intervals on spaced repetition.
Sources used on this page
- Memory
- Long-term memory
- Method of loci
- Mnemonic major system
- Memory sport
- Chunking (psychology)
- Elaborative encoding
- Forgetting curve
- Levels-of-processing effect
- Encoding specificity principle
- Judgment of learning
- Spaced repetition software
- Spaced repetition
- Active recall
- Testing effect
- Desirable difficulty
- Cepeda et al., distributed practice meta analysis (2006)
- Cepeda et al., spacing and the optimal retention interval (2008)
- Roediger and Karpicke, Test-Enhanced Learning (2006)
- Karpicke and Roediger, the critical importance of retrieval (2008)
- Kornell and Bjork, is spacing the enemy of induction (2008)
- Dunlosky et al., improving students' learning (2013)
- What Works Clearinghouse, organizing instruction and study
- The Learning Scientists, retrieval practice
- Retrieval Practice, the research library
- Cloze test
- MDN, the details element
- MDN, the textarea element
- WeSolve+ on the App Store
- Mnemonic
| What happened | Which failure | The fix |
|---|---|---|
| Obvious once you see it | Interval was too long | A scheduler, and shorter intervals for that item |
| Unfamiliar when you see it | Encoding never happened | Elaborate on it, or build a mnemonic |
| You know it but cannot say it fast | Retrieval is weak | More attempts, not more reading |
| You mix it up with a neighbour | The two were never separated | One cue that distinguishes them |
| You only know it in one context | Encoding was too specific | Vary the cue and where you practise |
Do memory apps work?
The scheduling ones do, for material that was encoded in the first place. They cannot make an item memorable, which is a different failure with a different fix.
How do I know which failure I have?
Look at how it feels when you see the answer. Obvious and annoying means the interval was too long. Unfamiliar means it never went in, and no schedule will rescue that.
Are mnemonics worth building?
For a short list you must have exactly, yes. For two hundred cards, no: they take minutes each and are fragile unless the connection is to your own associations.
Does brain training help?
Not in the way it is sold. Transfer from a trained task to anything else is consistently weak, so you mostly get better at the training.
Why is a streak a bad metric?
Because it measures showing up rather than remembering, and a rising number invites confidence that recall has not earned. Ask instead how many items you produced correctly after a delay.
Does this tool store anything?
No. It runs in your browser and keeps nothing, so copy the output before closing the tab.
Last updated: 2026-08-15