Observed arrival · 2026-11-03
Astronomical Intelligence: workflows for AI-assisted science
An open library organizing prompts, agent configurations, model checks, reviews, failures, and research workflows for using language models in science.
- For
- Researchers using language models in scientific work
- Worth noticing
- The two listed workflow examples are marked “to be tested” and “tested: not yet,” despite the homepage’s tested-collection framing.
Field notes
The homepage sorts material both by format—workflows, prompts, skills, agent configurations, model checks, reviews, and failures—and by research phase, from literature search to referee replies. Its examples include translating legacy IDL code to Python and searching NASA ADS with claims tied to checkable bibcodes. Both displayed examples are marked “to be tested,” so the available page does not yet demonstrate the testing standard described in its introduction. Content is labeled CC BY 4.0 and code MIT.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue