vault.batch
Run multiple questions against a NotebookLM notebook and save each answer as markdown and JSON files with cited sources for building a searchable vault.
Instructions
Run a list of questions against a notebook and persist each answer to disk as two artifacts: {slug}.md (markdown with YAML frontmatter, answer body and cited source excerpts) and {slug}.json (structured payload conforming to the nblm-answer-v1 schema). Designed for one-shot ingestion of a notebook into a searchable markdown vault (e.g. for indexing with RTFM) — every answer keeps titles + highlighted excerpts, so repeat queries no longer need to round-trip through NotebookLM.
Reuses the same browser/session as ask_question — no HTTP server required. Pass sleep_between_ms (1500–3000ms) for batches above ~20 questions to avoid hammering NotebookLM.
Returns per-question file paths, success flags, citation counts and the resolved session id. See the RTFM integration guide for the recommended workflow.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| questions | Yes | Non-empty array of question strings to ask sequentially. | |
| vault_dir | Yes | Destination directory (absolute or relative). Created with mkdir -p if missing. | |
| notebook_id | No | Optional library notebook id to query. Falls back to the active notebook. | |
| notebook_url | No | Optional NotebookLM URL (overrides notebook_id). Use for ad-hoc notebooks. | |
| slug_prefix | No | Optional filename prefix (e.g. "sota", "market-2026q2"). Default: "". | |
| source_format | No | Citation extraction mode. "json" (default) preserves titles + excerpts in the sidecar. | |
| sleep_between_ms | No | Pause between questions in ms. 1500–3000 is sane for batches above ~20. | |
| session_id | No | Optional session id to reuse for context continuity across the batch. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| success | Yes | Whether the tool call succeeded. | |
| data | No | The tool payload on success. The exact shape depends on the tool. | |
| error | No | Human-readable error message, present only when success is false. |