Is NotebookLM a direct replacement for Kosmico?
Not generally. Their overlap is source-grounded AI work, but their primary workflow and project scope differ.
Scope comparison
Both can discover and synthesize sources. The decision depends on whether the task is primarily a source-grounded notebook or an end-to-end project that continues into executable and editable research artifacts.
NotebookLM is a natural candidate for grounded questions, synthesis, study guides, briefings, and media outputs around a notebook's sources. It can also discover sources through current research features; formats and limits remain subject to Google's documentation.
Kosmico is intended for work that must continue from discovery into a project library, Knowledge Graph, analysis, editable files, bibliography, manuscript, and team review.
| Criterion | Kosmico | NotebookLM |
|---|---|---|
| Starting point | A research question or existing project with connected artifacts | A notebook built around uploaded, imported, or discovered sources |
| Literature discovery | Declared academic databases and the explicit stages of Deep Research | Fast Research or Gemini Deep Research can discover sources for a notebook |
| Execution surfaces | Project files, writing, references, analysis, and agent tools | Source-grounded chat, study materials, and media artifacts |
| Team workflow | Shared project context, roles, artifacts, and review | Verify current sharing and collaboration features in Google's official documentation |
First-party sources reviewed
Official source
Kosmo can chain many steps on its own, but only with the tools of the active mode: a tool outside the mode is refused. Every run has a fixed budget of tool turns, from 10 to 50 depending on where Kosmo runs (20 in the desktop chat, 50 on the web), and ends with a written answer when the budget runs out. Helper sub-agents are read-only and get 5 to 8 turns.
Citation identity
Every citation comes from a record fetched from one of the databases, and you can open it. The review may cite only papers found in the run: a section with an unknown reference, or a substantive paragraph without a citation, is rejected and rewritten. An optional pass also resolves each reference by DOI, arXiv ID, PubMed ID or title and flags the ones it cannot confirm.
Claim-to-evidence validation
A claim taken from a paper's full text is kept only if its quoted passage appears on the cited page; claims without a matching quote are dropped. Each section is written from the evidence of the papers it cites, but no model checks that every sentence of the review is supported, so check the sources of anything you are about to publish.
Not generally. Their overlap is source-grounded AI work, but their primary workflow and project scope differ.
Yes. Papers you add are part of the project context, and Deep Research can also find and connect more literature from the academic databases it searches.