Revision Super Agent
Omi's specialised co-pilot for revision super work
I review your entire analysis end-to-end — catch errors, suggest improvements, polish figures, ensure reproducibility, and give you peer-review-style feedback before reviewers do. Think of me as a friendly senior co-author doing one last careful pass over everything you ran.
What I can do for you
I retrace every step of your Omi session — QC, normalization, integration, clustering, annotation, downstream analyses — and flag anything that looks fragile, inconsistent, or hard to defend in review.
I improve your figures: better color palettes, readable fonts, consistent legends, panel layouts that fit a Nature/Cell figure grid, and alt-text suggestions for accessibility.
I check reproducibility — software versions, seeds, parameter choices, missing citations — and produce a clean checklist so your analysis can be re-run by a reviewer or collaborator without surprises.
I generate peer-review-style feedback: the questions Reviewer 2 will almost certainly ask, suggested rebuttal points, and concrete experiments or extra analyses that would make your story bullet-proof.
Examples of what you can ask me
Copy any of these straight into the demo, or adapt them to your data.
- 1"Review my whole analysis and tell me what a reviewer would criticize."
- 2"Improve all my figures for a Nature submission — colors, fonts, layout."
- 3"Check the reproducibility of my pipeline and list anything missing."
- 4"Suggest 3 extra analyses that would strengthen my main conclusion."
- 5"Find inconsistencies between my Methods text and what I actually ran."
- 6"Give me a peer-review-style report on my single-cell paper draft."
How I work
I run real Scanpy (Python) or Seurat (R) code on the secure MCP server — no hallucinations, no made-up gene lists. Every result comes with the exact code I executed and the parameters I used, so your analysis is fully reproducible and ready for the Methods section.
Best for
First authors finalising a paper, postdocs prepping a revision, PIs doing a last quality check before submission, and anyone who wants a thorough second pair of eyes on their full single-cell analysis.
References
- Scanpy (Wolf et al., 2018) – Genome Biology
- Seurat (Hao et al., 2021) – Nature Biotechnology
- Cell2Sentence (Levine et al., 2024) – Nature Machine Intelligence
- FAIR principles (Wilkinson et al., 2016) – Scientific Data
Try Revision Super now
Jump into the demo with a starter prompt already loaded. Upload your data, or play with our example dataset first.