Skip to content
Demonstrator · items marked Example are invented · what exists today
E2ER

External pipelines · RISE project catalogue

Prism

OpenAI's free AI-native LaTeX workspace for scientific writing and collaboration, launched late January 2026 on Crixet, a cloud LaTeX platform OpenAI acquired. GPT-5.2 (upgraded to GPT-5.3 with Codex CLI in March 2026) operates inside the document with access to the paper's structure, equations, citations, and figures, covering drafting, revision, real-time collaboration, arXiv-backed referencing, and publication prep. Sits in the writing layer of the RISE pipeline — the manuscript-workspace counterpart to workbench products like Claude Science.

Indexed in RISE · activeConformance with the standard plannedProject site

What it does

First big-lab product to make the manuscript itself the AI-native surface: the model is embedded in the LaTeX project rather than bolted on as a chat sidecar, and the workspace is free with unlimited projects and collaborators on a personal ChatGPT account. Converts whiteboard/handwritten sketches to LaTeX, auto-finds and formats arXiv references, and — since the March 2026 Codex integration — runs Python/R in-workspace with compile-check-revise self-repair loops for LaTeX errors.

Focus
drafting
Inputs
latex-project, natural-language-instructions, whiteboard-sketches, data-files
Outputs
latex-manuscripts, formatted-bibliographies, figures, compiled-pdfs
Architecture
single-llm, tool-use, iterative-loop
Maintained by
OpenAI
Started
2026

Description

Data model
Discipline
General
Method family
not specified
Design
not specified
Research stage
Literature discoveryData analysisCode generationDraftingRevision and editingDissemination
Contributors
OpenAI
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:prism · JSON

Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.

Bring it into the standard

A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.