Google Analytics, Vercel Web Analytics, Leadsy and the TikTok Pixel stay off until you accept. The help chat starts once you have chosen. The scheduling button starts once you have chosen. Read our Privacy Policy.

Skip to content
StellarFirmStellarFirm
Mission manual
Esc

Type a word to search every page. Try , or .

Module 03 · AI Agent Assistants

Scientist

Scientist searches the literature with checked sources, tests conjectures, checks derivations and numbers, drafts proofs, and writes papers in LaTeX.

View as Markdown
On this page

Scientist is the assistant for research in mathematics, physics, computer science and engineering. It turns a question into a research brief, searches the literature and checks every source, tests a conjecture and looks for counterexamples, checks derivations symbolically and numerically, drafts proofs, keeps analyses reproducible, and writes notes and papers in LaTeX.

What it does#

  • Turn a research question into a one page brief with what is known and what is open.
  • Search the literature in the databases that fit your field, and check every reference.
  • Read a paper and write notes on its claims, evidence and assumptions.
  • Turn a question into hypotheses and an experiment or simulation plan.
  • Test a conjecture on many cases and search for counterexamples before calling it plausible.
  • Check algebra and calculus symbolically, and check numerical results for convergence.
  • Draft a proof and check it step by step.
  • Make an analysis reproducible, with scripts, pinned versions and fixed seeds saved next to the results.
  • Write research notes, derivations, reports and papers in LaTeX, which you preview and edit beside the chat.

You can give Scientist one or more fields: mathematics, physics, computer science, engineering, data and statistics, structural biology, or drug discovery. Each field adds its own skills. With no field, Scientist uses every skill.

Skills#

SkillWhat it does, in plain words
Research briefThe first win. Turns your question into a one page brief: what is known from checked sources, each claim with its status, and the next steps.
Literature searchSearches and checks the literature for a question, follows references forward and back, and lists only sources it verified.
Paper reading notesReads a paper in three passes and writes notes on its claims, evidence, assumptions and open questions.
Hypothesis and experiment planTurns a question into hypotheses that can be refuted and a plan with variables, controls and predictions.
Generate and verifyWrites a checker first, then tests candidate results on small, random and edge cases, and records what failed.
Symbolic checkChecks algebra and calculus by computer, substituting solutions back and spot checking at random points.
Numerical convergence checkChecks a numerical result by refining the grid or time step and comparing against the method's expected order.
Proof draft and checkRestates the claim, tests small cases, outlines lemmas, writes the proof and checks each step.
Reproducible analysisSets up an analysis with a project folder, pinned versions, fixed seeds and scripts that rebuild every result.
LaTeX notesWrites research notes, a derivation or a technical report as one LaTeX file you can preview and edit.
LaTeX paperDrafts or restructures a paper in LaTeX, with every claim labelled and citations only from a checked bibliography.
Referee reportDrafts a referee report for a paper you were asked to review, with major and minor issues and a reproducibility check.
Research logKeeps a dated log of what was tried and every result, negative ones included.
Field skillsMethods for each field, such as counterexample search and formal proofs for mathematics, unit and limiting case checks for physics, algorithm analysis and benchmark design for computer science, design calculations, trade studies and failure modes reviews for engineering, statistical analysis plans and figure checks for data, and structure and target checks for biology and drug discovery.

Integrations#

IntegrationUsed for
Google DriveFinding papers and data, and saving drafts
GmailDrafting messages to collaborators
NotionLab notes and project pages
Firecrawl, Exa, Tavily, JinaFinding and reading sources on the web
Hugging FaceModels, datasets and papers

Example goals#

  • Know what is already known about a question before you start.
  • Check a derivation before it goes into a paper.
  • Find a counterexample, or gain confidence that there is none.
  • Turn a set of notes and results into a paper draft.

Prompts#

PromptWrite a research brief

Scientist, write a one page research brief on [question]. Use checked sources only, label every claim, and list what is still open.

PromptSearch the literature

Scientist, find the key papers on [topic] since [year]. Check each reference and tell me in a sentence what each one shows.

PromptTest a conjecture

Scientist, I think [statement] holds for all [cases]. Test it on small and random cases and search for a counterexample. Tell me what you checked.

PromptCheck a derivation

Scientist, check this derivation step by step, symbolically and with a numerical spot check. Mark any step that does not hold. [attach or paste derivation]

PromptDraft a proof

Scientist, draft a proof that [claim]. Test small cases first, outline the lemmas, and check each step. Say clearly if it is not yet proved.

PromptMake an analysis reproducible

Scientist, set up this analysis so anyone can rerun it: a project folder, pinned versions, fixed seeds, and a script for every figure. [attach data and notes]

PromptDraft a paper

Scientist, turn these notes and results into a paper draft in LaTeX. Cite only from this bibliography, and label each claim by how it was established. [attach notes, results, bibliography]

PromptWrite a referee report

Scientist, draft a referee report on this paper: a summary of its claims, the major and minor issues, and whether the results can be reproduced. [attach paper]

What it never does#

When a claim has no source yet, Scientist marks it as needing one instead of filling the gap.