Core concepts
The workspace is organized around a research session. Each surface either adds context, generates output, or helps continue the work.
Sessions
Each chat session keeps the conversation, attachments, generated artifacts, and analysis runs together.
Artifacts
Briefs, presentations, charts, structures, formulas, and citations render inline when the agent produces them.
Library context
Files can be attached to a single session or saved for reuse when the same source material matters later.
Agent memory
Follow-up prompts can refer to prior responses and experiment outputs without asking you to paste everything again.
Experiments
Experiment cells are for executable analysis. Use them when you need data preparation, statistical checks, chart generation, or a training pipeline handoff. Later cells can see earlier code, output summaries, and shared libraries so the analysis can continue naturally.
Normalize cohort baseline
Experiment 1 · Python
Output
›Loaded 412 rows · dropped 17 with missing age/biomarker
›Saved figure → baseline.png
Naming experiments
Rename cells to match the analysis intent, such as “Normalize RNA-seq counts” or “Prepare training split.” Titles persist once the session can associate the cell with its saved analysis run.
Split panes
Split panes are designed as session-isolated views. Opening the same session twice will show the same saved state after refresh, but live keystroke-level collaboration is intentionally out of scope until the product adds real-time sync.