CATO Quick Reference
Production · July 2026
Quick Reference
A printable map of the current CATO workflow
Core Workflow
- Create one project per study or research boundary.
- Add source data in Database or connect Google Drive.
- Inspect schema, metadata, warnings, units, and identifiers.
- Select exact files, artifact versions, or literature.
- Ask in Chat; use Plan mode for consequential methods.
- Follow durable response or background-job status.
- Validate files, figures, code, citations, and provenance in Workspace.
Chat Modes
| Standard | Balanced everyday research |
| Fast | Low-latency questions and edits |
| Research | Deep, extended analysis |
/standard · /fast · /research · /profile
Prompt Template
- Objective: decision or estimand
- Evidence: @files and exact versions
- Population: subset and exclusions
- Method: model and assumption checks
- Outputs: files, figures, notebook, report
- Guardrail: when CATO must stop and ask
Keyboard
| Ctrl/Cmd+K | Command palette |
| Ctrl/Cmd+/ | Toggle project sidebar |
| Ctrl/Cmd+1 / +2 | Database / Chat |
| Ctrl/Cmd+U | Upload |
| Shift+Tab | Plan mode |
| Enter / Shift+Enter | Send / new line |
| Ctrl/Cmd+Enter | Run focused notebook/query tool |
| Arrow Up | Edit last prompt when input is empty |
Workspace
- Files: preview, edit, versions, provenance
- Figures: viewers, SVG editing, visual QA, export
- Notebooks: Python/R, persistent kernels, output
- Manuscripts: Markdown/LaTeX, preview, citations
- Readers: PDF/HTML/transcript annotations
- Review: findings linked to evidence/artifacts
- Runtime: logs and environment information
Data and Uploads
Common families:
Tables/statistics; PDF/JSON/code; images; HDF5; genomics; single-cell; molecular; medical imaging; proteomics; graph, MATLAB, and NumPy data; ZIP/TAR archives.
| Standard | 100 MB/file |
| Enterprise | 500 MB/file |
| Pay as you go | 1 GB/file |
Archives: 500 MB compressed / 2 GB extracted safety limits.
Literature
- Deep Search queries 18 open scholarly sources in parallel.
- ClinicalTrials.gov and patents are specialized connectors.
- Use study filters, deduplication, Library, collections, watches, evidence, and networks.
- Open available full text in Workspace; otherwise CATO uses available metadata/abstracts.
- Send selected works to Chat as bounded context.
- Verify every citation and full-text-supported claim.
Memory
- Project: study-specific stable context
- Global: durable personal preferences
- Edit, pin, or delete entries.
- Control recall, auto-learning, and cross-project use.
- Never treat memory as scientific evidence.
If a Run Appears Stuck
- Reopen the same conversation and allow reconnection.
- Check the response or background-job status card.
- Cancel once if the task is no longer valid.
- Check Settings → Billing for usage boundaries.
- Retry only after confirming no active duplicate exists.
- Send support IDs, time, and redacted errors—not data or secrets.
Validation Checklist
- Correct source and artifact versions
- Expected rows, variables, units, and exclusions
- Code, dependencies, seed, and environment
- Assumptions, diagnostics, uncertainty, sensitivity
- Figure data, labels, scales, and accessibility
- Citation identity and claim support
- Export fidelity and reproducibility
Documentation: /docs · Troubleshooting: /help/troubleshooting · Support: /help/contact · Updated July 2026