Study Plan Builder — by an AI council
Build a study plan that fits your time and how memory works. Four rival AIs debate it and hand back: A realistic study schedule using retrieval, spacing and the right priorities.
A realistic study schedule using retrieval, spacing and the right priorities.
Signed off by an independent Final QA audit — with a “verify before you rely on this” list, never a black box.
Why this team
Study plans fail through comfortable methods and fantasy schedules, so the seats attack both: the Educator prescribes what the evidence supports — retrieval practice, spacing, interleaving — over the re-reading and highlighting that feel productive, and the Behavioural Economist designs around the avoidance patterns every studier has, especially the flight from hard topics. The Data Skeptic audits the self-assessment (“I know that chapter” usually means “I recognise it”), and the Pragmatist builds the timetable against real, tired hours rather than aspirational ones.
Each seat runs on a different frontier model — GPT, Claude, Gemini, Grok — so it’s a genuine cross-model review, not one AI in costumes. How a run works →
What the debate sounds like
An illustrative excerpt — A working professional has eight weeks to prepare for a financial certification exam, studies mainly by re-reading the official manual, and keeps postponing the derivatives section she finds hardest.
The method is the first problem: re-reading a manual produces recognition, and the exam tests recall under time pressure — different memory systems. The switch that changes the result: practice questions from day one, closed book, before feeling ready. Wrongness in week one is diagnostic gold; the same wrongness discovered in week seven is a crisis. Feeling less fluent is the evidence it is working.
The derivatives avoidance follows a law: aversive topics migrate to the end of every session, where fatigue guarantees they go badly, which deepens the aversion. Break the loop structurally, not with resolve — derivatives goes first in every session while she is fresh, in twenty-five minute blocks with a defined stop. The stop matters: knowing it ends is what makes starting possible.
Before the schedule is drawn, audit the confidence map: “I know the regulation chapters” is based on having read them twice, which is exactly how the illusion of knowing works. One timed diagnostic across all sections, this week, replaces feelings with data — and in my experience the map redraws substantially. Hours should follow the diagnostic, not the anxiety.
Questions
Why do practice questions beat re-reading — the manual is the syllabus?
Because the exam does not ask you to recognise the manual; it asks you to retrieve and apply it under time pressure, and retrieval is a skill built only by retrieving. Testing yourself is not assessment of learning — it is the learning. The manual becomes the reference you consult after getting questions wrong, which is its highest use.
How does the plan handle the topics I keep avoiding?
Structurally, not motivationally: avoided topics get scheduled first in each session, in short bounded blocks, while you are fresh — and the diagnostic reveals whether the fear is even calibrated. Avoidance is treated as a design input like any other constraint, because willpower-based plans fail on exactly this point.
Eight weeks, four weeks, two — does the method change with the runway?
The proportions change, the method does not: shorter runways shift the mix harder toward past-paper practice on the highest-mark topics and cut the completeness instinct sooner. State your real date and hours in the brief — the plan is built backwards from the exam, including the final week of full timed mocks.
Your material is used only to run your review — never to train public models. Encrypted in transit and at rest. Security & privacy →
Want full control — pick your own minds, set the depth? Open the full council →