APPLICATION
Research plan · Draft
Before generation, it shows the exact account fields, sources, and uses. Only the confirmed snapshot is used to frame the one-sentence question and identify what still needs filling in.
If you choose a lab, the tool checks connections to the professor's public academic material; otherwise it drafts a general research plan. References get format and search-keyword guidance only — never fabricated citations.
Stage one generates 3 title candidates and a 6-part outline for you to edit and confirm — revising structure is far cheaper than revising prose. Only then does stage two write the full text.
It outputs a draft you can copy section by section, plus a personalization map, follow-up questions, and a fact-check list. An explicit handoff can pass the saved run to the review studio.
Loading your preference…
Start with an interest, a topic, or an old draft. Sort out the research question, method, and target-supervisor fit, then generate the title and outline.
Many applicants turn the research plan into a book report — piling on passion and grand vision, yet never pinning down the research question, never engaging prior work, never offering a feasible method. That emptiness is spotted instantly at outreach, interviews, and faculty review, where it becomes the hardest barrier. A draft that holds up narrows the intent into one concrete question, then grounds it in the professor’s recent research direction.
do not expand until problem, method, and contribution hold.
a plan continues a conversation, it does not open one.
deriving the gap beats counting references.
sources, samples, and two years decide it.
skip generic praise of the university.
length, sections, and references vary.