01

Derivation and verification

Problem
Long calculations hide conventions, sign choices and intermediate identities.
Workflow
Equation extraction, dependency mapping, symbolic reconstruction, limiting-case tests and mismatch logging.
Human judgment
The researcher decides which assumptions are legitimate and whether agreement is physically meaningful.
Output
A reproducible derivation note with assumptions, verified steps and unresolved points separated.
Safeguards
  • No automatic trust in source conclusions
  • Derived and assumed claims remain distinct
  • Independent checks where possible
02

Literature and manuscript intelligence

Problem
Claims, notation, citations and reviewer requests drift across manuscript versions.
Workflow
Claim-to-source tracing, notation checks, version comparison, bibliography validation and overclaim review.
Human judgment
Automation finds inconsistencies; authors retain responsibility for scientific claims and responses.
Output
An audit record that links each finding to a source location and a review status.
Safeguards
  • Source spans and version hashes
  • Unresolved claims block a clean verdict
  • Private manuscripts never enter public demos
03

Computational and visual prototyping

Problem
A continuum claim needs a numerical model, convergence evidence and a figure that reveals the structure without overstating it.
Workflow
Model specification, discretization, convergence tests, continuum comparison and figure generation.
Human judgment
The model, regulator and observable are fixed before visual polish begins.
Output
A self-contained Mathematica or Python record with explicit errors and reusable figures.
Safeguards
  • Convergence before interpretation
  • No synthetic data presented as evidence
  • Figures carry provenance and alt text