Consensus vs Gemini Notebook (NotebookLM)

Agent access

1. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to Consensus
   Consensus~partialclaimed4/10

   Consensus offers an API for integrating its search into custom workflows and running automated searches (consensus-docs-1, consensus-docs-15), which implies some programmatic/headless usability. However, there is no explicit documentation of CI integration, headless execution modes, CLI tooling, or automation pipeline examples. Missing for 10: CI/CD integration examples, headless mode documentation, CLI or SDK for automation, and independent evidence of running in automated pipelines.

   • [claimed-docs] “Connect the Consensus API within your project to seamlessly integrate up-to-date peer-reviewed citations into your own custom workflow.”
   • [claimed-docs] “Save your team hours of manual discovery research and run automated searches with our API to quickly and easily find the most relevant and r…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence of an API, CLI, or headless/automation mode for NotebookLM/Gemini Notebook; all documented usage is through the interactive web/app UI, and community comments even complain about lacking programmatic source ingestion.

   • [claimed-docs] “Easily upload PDFs, websites, YouTube videos, audio files, Google Docs, or Google Slides or discover new sources.”
   • [community] “My problem with NotebookLM was that you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them int…”

   proof ↗⚑ flag

2. ai-native userUse an official CLI

   weight 2 · round drawn
   Consensus—none0/10

   The evidence pack documents a REST API and an MCP server (consensus-docs-16) but no official command-line interface is mentioned anywhere in the docs or probes. Missing for 10: any mention of a CLI tool, CLI installation instructions, or CLI command reference.

   • [claimed-docs] “a REST API and an MCP server expose the same retrieval and synthesis surface that powers the web app”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence of an official CLI for Gemini Notebook; all documentation describes a web/app UI with no command-line interface mentioned.

   ⚑ flag

3. ai-native userDrive the product through a documented public API

   weight 3 · round to Consensus
   Consensus~partialprobed5/10

   Consensus advertises a documented API for integrating citations and running automated searches into custom workflows, and its site provides an llms.txt for AI-agent discovery, showing basic public-API and agent-friendliness. However, the evidence pack only shows marketing/landing pages, not actual API reference documentation, authentication, endpoints, or example requests/responses, and there's no independent or hands-on corroboration that the API works as described. Missing for 10: full API reference/spec details, code/SDK examples, and independent verification of API usage.

   • [claimed-docs] “Connect the Consensus API within your project to seamlessly integrate up-to-date peer-reviewed citations into your own custom workflow.”
   • [claimed-docs] “Save your team hours of manual discovery research and run automated searches with our API to quickly and easily find the most relevant and r…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://consensus.app/llms.txt # Consensus > Consensus is an AI-powered scientific search engine that finds, ra…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence pack item mentions a documented public API, SDK, or programmatic access method for Gemini Notebook; all evidence describes UI-driven features (sources, chat, audio/video overviews, sharing) and community commentary about workflow limitations, not API access.

   ⚑ flag

4. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Consensus—none0/10

   Consensus documents an API for integration (consensus-docs-1, consensus-docs-15) but no evidence pack item mentions official SDKs (Python, JS, etc.) or client libraries for AI-native development — only the raw API and llms.txt discovery file are shown.

   • [claimed-docs] “Connect the Consensus API within your project to seamlessly integrate up-to-date peer-reviewed citations into your own custom workflow.”
   • [claimed-docs] “Save your team hours of manual discovery research and run automated searches with our API to quickly and easily find the most relevant and r…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://consensus.app/llms.txt # Consensus > Consensus is an AI-powered scientific search engine that finds, ra…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence of an official SDK, API, or developer library for building against Gemini Notebook; all evidence describes end-user features (uploading sources, chat, audio/video overviews, notes) rather than programmatic/developer access.

   ⚑ flag

5. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Consensus—none0/10

   No evidence anywhere in the pack mentions webhooks or event subscriptions; Consensus's API/MCP surface is described only as REST retrieval/synthesis, not event-driven push notifications.

   ⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence of any webhook subscription, API event, or outbound notification capability in Gemini Notebook's docs or community feedback; the product is a research/notebook tool with no mentioned event-driven integration surface.

   ⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round drawn
   Consensus✓fullclaimed8/10

   Consensus generates AI-driven synthesis, summaries, the Consensus Meter, PICO extraction, and literature review synthesis directly from the papers in its corpus/library, with citations tracing insights back to sources. This is core native functionality (not a bolt-on), covering search, synthesis, and structured insight generation. Missing for 10: independent/hands-on third-party verification of insight quality beyond vendor docs.

   • [claimed-docs] “It searches over 200 million academic papers and uses language models to help you find, understand, and synthesize the literature faster.”
   • [claimed-docs] “Every response includes citations, so you can trace each insight back to the original source.”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”
   • [claimed-docs] “Extracted population, intervention, comparator, and outcome (PICO) where applicable”
   • [claimed-docs] “Consensus is an AI-powered research engine built to speed up literature reviews. Search, screen, extract, and synthesize evidence faster—whi…”
   • [claimed-docs] “The Consensus Library brings your entire research library into one searchable, AI-powered workspace.”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)✓fullcommunity8/10

   NotebookLM generates summaries, insights, mind maps, briefing documents, AI-suggested report types, and answers with grounded citations directly from uploaded sources, and community feedback confirms real-world use for research insight extraction (e.g., audio overviews, code walkthroughs). Missing for 10: independent benchmarking of insight quality/accuracy and evidence of more proactive/agentic suggestion behavior beyond user-initiated Q&A.

   • [claimed-docs] “Chat with your notebook to get grounded information based on your sources with clear in-line citations for accuracy, transparency, and trust…”
   • [claimed-docs] “Find an auto-generated summary of the entire source in the Source Guide.”
   • [claimed-docs] “Create your own, or choose from FAQ, study guide, briefing document, or an AI suggested report type.”
   • [claimed-docs] “Get insights in the moment by asking questions about your sources.”
   • [claimed-docs] “Mind Maps in Gemini Notebook visually summarize your uploaded sources, showing main topics and related ideas as a branching diagram.”
   • [community] “NotebookLM is genuinely useful for structured research workflows. My concern is not the name. It's whether the "notebook" metaphor survives …”
   • [community] “I used it to listen to a high level walkthrough of interesting and entertaining code while driving to work... Hearing it talk about Ken Thom…”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round drawn
   Consensus—none0/10

   Consensus is a research search/synthesis engine with an API and MCP server for on-demand retrieval, but there is no evidence of scheduled or event-triggered automations that run autonomously in the background without user invocation. Missing for 10: any scheduling/trigger mechanism, background job execution, or autonomous recurring workflow capability.

   ⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence of scheduling, triggers, or autonomous background automations in NotebookLM's documented features; all capabilities (chat, source summarization, audio/video overviews, notes) are user-initiated within a session.

   ⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Consensus
   Consensus✓fullprobed7/10

   Consensus ships a built-in "Research Agent" that chains citation crawling, DOI lookup, author search and similar-paper discovery on top of its search engine, and its core AI assistant performs search, screen, extract, and synthesize workflows with cited answers — this is essentially delegating research tasks to an in-product AI assistant. missing for 10: independent/hands-on validation of the agent's autonomy and reliability, and more detail on the scope/limits of delegable tasks beyond literature discovery.

   • [claimed-docs] “Citation crawling, DOI lookup, author search, similar papers, and more - chained together on top of the worlds best academic search engine.”
   • [claimed-docs] “Search, screen, extract, and synthesize evidence faster—while keeping full transparency and scholarly rigor.”
   • [claimed-docs] “Consensus is an AI-powered research engine built to speed up literature reviews. Search, screen, extract, and synthesize evidence faster—whi…”
   • [claimed-docs] “It searches over 200 million academic papers and uses language models to help you find, understand, and synthesize the literature faster.”
   • [claimed-docs] “Every response includes citations, so you can trace each insight back to the original source.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://consensus.app/llms.txt # Consensus > Consensus is an AI-powered scientific search engine that finds, ra…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)~partialcommunity4/10

   NotebookLM lets users chat with sources and generate transformed outputs (summaries, audio/video overviews, study guides, slide decks), which is a form of task delegation, but there is no evidence of an agentic assistant that can take autonomous multi-step actions, use tools, browse/search independently, or execute tasks beyond source-grounded Q&A and content transformation; community feedback even notes it can't search for docs on its own (notebooklm-comm-4). missing for 10: autonomous multi-step task execution, tool/agent orchestration, independent web search/retrieval, evidence of true delegation beyond content generation.

   • [claimed-docs] “Chat with your notebook to get grounded information based on your sources with clear in-line citations for accuracy, transparency, and trust…”
   • [claimed-docs] “Transform your sources into approachable formats such as study guides, briefings, audio overviews, mind maps, and more.”
   • [claimed-docs] “Audio Overviews are deep-dive discussions between AI hosts that provide in-depth summaries of the key topics in your uploaded sources.”
   • [claimed-docs] “Transform your sources into a polished presentation by generating a Slide Deck, perfect for sharing or reviewing key concepts.”
   • [community] “My problem with NotebookLM was that you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them int…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to Consensus
   Consensus✓fullclaimed7/10

   Consensus's core interaction model is natural-language research queries (search, synthesize, Consensus Meter for yes/no questions) rather than rigid query syntax, and it exposes this same NL-driven retrieval/synthesis surface via an MCP server and REST API for programmatic/agentic use. Missing for 10: independent hands-on evidence of natural-language command execution quality, and no detailed example transcripts showing complex multi-step NL commands being interpreted.

   • [claimed-docs] “It searches over 200 million academic papers and uses language models to help you find, understand, and synthesize the literature faster.”
   • [claimed-docs] “a REST API and an MCP server expose the same retrieval and synthesis surface that powers the web app”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”
   • [claimed-docs] “Think of Consensus as an AI-native alternative to Google Scholar with a more-refined corpus.”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)~partialcommunity6/10

   NotebookLM lets users interact via natural-language chat to query sources, request custom conversational styles/roles, and ask questions (notebooklm-docs-2, notebooklm-docs-7, notebooklm-docs-28), which is a genuine natural-language interface. However, many core actions (uploading sources, converting notes, generating mind maps/slide decks/audio overviews) are triggered via UI menus/buttons rather than free-form commands, and community feedback notes limits like being unable to have it search for and incorporate new sources on its own (notebooklm-comm-4). Missing for 10: evidence of natural-language commands driving broader agentic actions (e.g., source discovery, format generation, sharing) rather than just chat Q&A and style prompts, and independent confirmation of command robustness.

   • [claimed-docs] “Chat with your notebook to get grounded information based on your sources with clear in-line citations for accuracy, transparency, and trust…”
   • [claimed-docs] “Custom: Best for choosing a specific style ("Respond like a PhD student") or suggesting a role ("Pretend to be a role-playing game host.").”
   • [claimed-docs] “Get insights in the moment by asking questions about your sources.”
   • [community] “My problem with NotebookLM was that you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them int…”

   proof ↗⚑ flag

Api quality

1. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round drawn
   Consensus—none0/10

   Consensus documents a REST API and MCP server (consensus-docs-15, consensus-docs-16) but no evidence pack item mentions an OpenAPI spec, Swagger file, or any downloadable machine-readable API schema; the llms.txt probe returns a plain-text description, not an API spec. missing for 10: OpenAPI/Swagger file, machine-readable schema download link, independent confirmation of spec availability.

   • [claimed-docs] “Save your team hours of manual discovery research and run automated searches with our API to quickly and easily find the most relevant and r…”
   • [claimed-docs] “a REST API and an MCP server expose the same retrieval and synthesis surface that powers the web app”
   • [probe] “PROBE llms.txt: HTTP 200 at https://consensus.app/llms.txt # Consensus > Consensus is an AI-powered scientific search engine that finds, ra…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence anywhere in the pack of an OpenAPI spec, API documentation, or any machine-readable API for Gemini Notebook; all evidence covers UI features (sources, notes, audio/video overviews, sharing). missing for 10: any mention of a public API, OpenAPI/Swagger spec, or SDK.

   ⚑ flag

2. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Consensus—none0/10

   There's an API and MCP server mentioned, but no evidence of API versioning scheme or a documented deprecation policy anywhere in the pack. missing for 10: versioning scheme documentation, deprecation policy, changelog/migration guides.

   • [claimed-docs] “a REST API and an MCP server expose the same retrieval and synthesis surface that powers the web app”
   • [claimed-docs] “Save your team hours of manual discovery research and run automated searches with our API to quickly and easily find the most relevant and r…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence of a versioned public API for NotebookLM/Gemini Notebook, let alone a documented deprecation policy; all evidence covers end-user features (uploads, summaries, audio/video overviews) not developer API access. Missing for 10: any mention of an API, versioning scheme, or deprecation/support-lifecycle policy.

   ⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Consensus
   Consensus~partialclaimed6/10

   Docs show bulk-style capabilities: one-click import of thousands of papers into a library, an API/MCP server for automated bulk searches, and Deep Searches across many studies — supporting bulk operations for an AI-native/automation persona. missing for 10: independent/hands-on verification of bulk API throughput or rate limits, explicit batch-processing endpoints (e.g., bulk extract/export across many items in one call), and any third-party confirmation of scale performance.

   • [claimed-docs] “Import thousands of papers in one click - then search, find gaps, and put your collection to work.”
   • [claimed-docs] “Turn your library into a research engine. Import thousands of papers in one click - then search, find gaps, and put your collection to work.”
   • [claimed-docs] “Save your team hours of manual discovery research and run automated searches with our API to quickly and easily find the most relevant and r…”
   • [claimed-docs] “a REST API and an MCP server expose the same retrieval and synthesis surface that powers the web app”
   • [claimed-docs] “Deep Searches (more comprehensive Lit Reviews across many studies)”
   • [claimed-docs] “Import from Zotero ... or import from BibTex, PDF, or RIS”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   The evidence only shows per-source actions (uploading individual sources, converting a single note to a source, generating one summary or audio overview at a time) with no mention of bulk/batch operations across many sources, notebooks, or items simultaneously. There is no documented bulk-select, bulk-delete, bulk-export, or batch-processing capability anywhere in the docs or community feedback.

   • [claimed-docs] “Easily upload PDFs, websites, YouTube videos, audio files, Google Docs, or Google Slides or discover new sources.”
   • [claimed-docs] “To convert a single note to a source: Open the note. Select Convert to source.”
   • [claimed-docs] “Each source can contain up to 500,000 words or up to 200MB for uploaded files.”

   proof ↗⚑ flag

2. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Consensus—none0/10

   No evidence in the pack mentions scheduling, recurring jobs, alerts, or automated re-running of searches/workflows over time; the API and MCP server are described as on-demand retrieval/synthesis interfaces, not schedulable automation. missing for 10: any scheduling/cron feature, recurring alert or saved-search re-run capability, or workflow automation trigger.

   • [claimed-docs] “Save your team hours of manual discovery research and run automated searches with our API to quickly and easily find the most relevant and r…”
   • [claimed-docs] “a REST API and an MCP server expose the same retrieval and synthesis surface that powers the web app”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence anywhere in the pack of scheduling, recurring jobs, triggers, or automated workflow execution; NotebookLM is a research/notebook tool driven by manual source uploads and on-demand queries.

   ⚑ flag

Sharing

1. analystShare a research session or report with collaborators who can view or build on it

   weight 2 · round to Gemini Notebook (NotebookLM)
   Consensus—none0/10

   No evidence pack items mention sharing sessions, reports, collaborators, team accounts, or collaborative viewing/editing features—only individual research, library import, and API/agent capabilities are documented. missing for 10: any mention of sharing links, collaborator invites, team workspaces, or comment/build-on functionality.

   ⚑ flag

   Gemini Notebook (NotebookLM)~partialclaimed7/10

   Docs confirm notebooks can be made public via shareable link, that Workspace admins now treat Gemini Notebook as a core service (implying org-level sharing), and that notes/slide decks/reports can be exported to Google Docs/Sheets or PDF so collaborators can view and continue working on them. However, evidence only describes public link sharing and analytics, not granular collaborator invite/edit permissions typical of collaborative docs, and there's no independent/hands-on account of real-world collaboration workflows. Missing for 10: explicit collaborator role/permission controls (view vs edit), independent corroboration of multi-user collaboration in practice.

   • [claimed-docs] “You can make your notebook public and share a link with anyone with a Google account.”
   • [claimed-docs] “Owners of public notebooks with paid subscriptions can view usage analytics in the analytics tab.”
   • [claimed-docs] “You can export your notes to Google Docs or Google Sheets.”
   • [claimed-docs] “For Workspace and Workspace for Education users, Gemini Notebook is now a core service (like Gmail, Google Calendar, and Docs).”
   • [claimed-docs] “Transform your sources into a polished presentation by generating a Slide Deck, perfect for sharing or reviewing key concepts. Present your …”

   proof ↗⚑ flag

Alerts

1. researcherSet up standing searches or alerts that surface new relevant sources as they appear

   weight 1 · round drawn
   Consensus—none0/10

   No evidence of standing searches, saved-search alerts, or notification features when new relevant papers appear; the evidence pack covers search, library import, citation graph, API/MCP retrieval, and literature review synthesis but nothing about recurring/alert-based monitoring of new sources.

   ⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence of any standing-search/alert capability that surfaces new relevant sources automatically; sources must be manually uploaded or discovered by the user. Community feedback explicitly confirms this gap: 'you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them into your research' ([notebooklm-comm-4]).

   • [community] “My problem with NotebookLM was that you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them int…”
   • [claimed-docs] “Easily upload PDFs, websites, YouTube videos, audio files, Google Docs, or Google Slides or discover new sources.”

   proof ↗⚑ flag

Corpus

1. researcherUpload my own PDFs or corpus and have the agent research over them

   weight 2 · round to Gemini Notebook (NotebookLM)
   Consensus~partialclaimed6/10

   Consensus's Library feature explicitly supports importing PDFs, BibTeX, RIS, and Zotero corpora and turns them into a 'searchable, AI-powered workspace' for finding gaps and using the collection, which matches the story's upload+research intent. However, evidence doesn't detail how deeply the AI synthesis/agent features (Meter, PICO extraction, literature review synthesis) operate specifically over a user's uploaded corpus versus the general 200M-paper index. Missing for 10: explicit documentation of agent-style synthesis/Q&A running directly over an uploaded private corpus, and independent/hands-on confirmation of this workflow.

   • [claimed-docs] “Import thousands of papers in one click - then search, find gaps, and put your collection to work.”
   • [claimed-docs] “Turn your library into a research engine. Import thousands of papers in one click - then search, find gaps, and put your collection to work.”
   • [claimed-docs] “Import from Zotero ... or import from BibTex, PDF, or RIS”
   • [claimed-docs] “The Consensus Library brings your entire research library into one searchable, AI-powered workspace.”
   • [claimed-docs] “Reference managers are great at saving papers — not so great at helping you use them. The Consensus Library brings your entire research libr…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)✓fullcommunity8/10

   Docs confirm PDF/document upload (up to 500k words/200MB per source), grounded Q&A with inline citations navigable to source location, source guide summaries, and note-taking over uploaded corpora—directly matching the story. Community evidence corroborates real-world use for structured research and studying, though one comment notes it can't proactively search for and pull in new docs beyond what's uploaded. Missing for 10: independent benchmarking of research quality/accuracy across large multi-PDF corpora, and confirmation of robust handling of very large or messy academic corpora at scale.

   • [claimed-docs] “Easily upload PDFs, websites, YouTube videos, audio files, Google Docs, or Google Slides or discover new sources.”
   • [claimed-docs] “Chat with your notebook to get grounded information based on your sources with clear in-line citations for accuracy, transparency, and trust…”
   • [claimed-docs] “Each source can contain up to 500,000 words or up to 200MB for uploaded files.”
   • [claimed-docs] “Find an auto-generated summary of the entire source in the Source Guide.”
   • [claimed-docs] “You can hover over any citation to get the full quoted text right away.”
   • [claimed-docs] “If you select a citation, Gemini Notebook automatically navigates to the location of the quote, so you can easily view it in context.”
   • [claimed-docs] “You can use notes to capture and organize information, identify key insights and interpretations from your sources, and add your own thought…”
   • [community] “NotebookLM is genuinely useful for structured research workflows. My concern is not the name. It's whether the "notebook" metaphor survives …”
   • [community] “My problem with NotebookLM was that you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them int…”

   proof ↗⚑ flag

Reviews

1. researcherRun a systematic screening and extraction workflow across many papers with consistent criteria

   weight 2 · round to Consensus
   Consensus~partialclaimed6/10

   Consensus offers literature-review features (search, screen, extract, synthesize per docs-8/12), library import at scale, PICO extraction, and filters by study type/year/discipline that support systematic screening with consistent criteria. However, there is no evidence of documented inter-rater reliability, exportable screening decision logs, or PRISMA-style workflow tracking that a systematic review would require. missing for 10: evidence of structured screening criteria configuration/audit trail, PRISMA-compliant workflow support, independent validation of extraction consistency across large paper sets.

   • [claimed-docs] “Search, screen, extract, and synthesize evidence faster—while keeping full transparency and scholarly rigor.”
   • [claimed-docs] “Consensus is an AI-powered research engine built to speed up literature reviews. Search, screen, extract, and synthesize evidence faster—whi…”
   • [claimed-docs] “Turn your library into a research engine. Import thousands of papers in one click - then search, find gaps, and put your collection to work.”
   • [claimed-docs] “Filters allow narrowing by study type (RCT, meta-analysis, systematic review, observational), publication year, journal, open-access status,…”
   • [claimed-docs] “Extracted population, intervention, comparator, and outcome (PICO) where applicable”
   • [claimed-docs] “Deep Searches (more comprehensive Lit Reviews across many studies)”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)~partialcommunity3/10

   NotebookLM supports uploading many sources into one notebook and chatting with grounded, cited answers, which could be used ad hoc to ask the same question across sources, but there is no evidence of a systematic screening/extraction feature (e.g., structured criteria templates, per-paper data tables, PRISMA-style tracking, or bulk batch processing) needed for a repeatable literature review workflow. Community feedback also notes the product cannot auto-search/pull in new sources itself, requiring manual curation, which undercuts a large-scale systematic workflow. Missing for 10: structured extraction templates/tables applied consistently across many papers, evidence of handling large paper sets with defined screening criteria, and confirmation this scales beyond source-count limits.

   • [claimed-docs] “Chat with your notebook to get grounded information based on your sources with clear in-line citations for accuracy, transparency, and trust…”
   • [claimed-docs] “You can hover over any citation to get the full quoted text right away.”
   • [claimed-docs] “Get insights in the moment by asking questions about your sources.”
   • [community] “My problem with NotebookLM was that you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them int…”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Consensus
   Consensus~partialclaimed6/10

   The API/MCP server is documented to expose 'the same retrieval and synthesis surface that powers the web app' (consensus-docs-16), and supports automated search (consensus-docs-15), suggesting broad parity for core search/synthesis. However, UI-specific workflows like Library import/reference management (Zotero/BibTeX/RIS import), Citation Graph, and Consensus Meter visualizations are not explicitly confirmed as API-accessible endpoints. Missing for 10: explicit API documentation confirming library management, citation graph, and meter features are callable via API, plus independent/hands-on verification of claimed parity.

   • [claimed-docs] “a REST API and an MCP server expose the same retrieval and synthesis surface that powers the web app”
   • [claimed-docs] “Save your team hours of manual discovery research and run automated searches with our API to quickly and easily find the most relevant and r…”
   • [claimed-docs] “The Consensus Library brings your entire research library into one searchable, AI-powered workspace.”
   • [claimed-docs] “Import from Zotero ... or import from BibTex, PDF, or RIS”
   • [claimed-docs] “The Consensus Citation Graph turns a single seed paper into a complete map of the work that built it, the work it inspired, and the studies …”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence pack items mention any public API, developer SDK, or programmatic access to Gemini Notebook features; all evidence describes UI-only workflows (upload, chat, generate audio/video/slides, notes, sharing). Community comments only discuss UI limitations, not API availability. missing for 10: any mention of a public API, SDK, or programmatic endpoints; documentation of API parity with UI features; developer access/authentication details.

   ⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Gemini Notebook (NotebookLM)
   Consensus—none0/10

   Evidence shows only import capabilities (Zotero, BibTeX, PDF, RIS) into the Consensus Library, with no mention of exporting a user's library, annotations, or account data back out in open formats. Data portability/export is a fair axis for a reference-manager-style product, but no evidence supports it.

   • [claimed-docs] “Import from Zotero ... or import from BibTex, PDF, or RIS”
   • [claimed-docs] “Import from Zotero”
   • [claimed-docs] “The Consensus Library brings your entire research library into one searchable, AI-powered workspace.”
   • [claimed-docs] “Turn your library into a research engine. Import thousands of papers in one click - then search, find gaps, and put your collection to work.”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)~partialclaimed3/10

   Docs show only piecemeal export options—notes to Google Docs/Sheets, audio overview downloads, and slide decks as PDF—but no evidence of a full data export (sources, chat history, citations, mind maps) or a genuine 'leave the platform' workflow in open, portable formats. Missing for 10: bulk/full-notebook export, open-format guarantees (vs Google Docs/Sheets lock-in), and any documentation or community confirmation of a complete account data export/exit path.

   • [claimed-docs] “You can export your notes to Google Docs or Google Sheets.”
   • [claimed-docs] “Listen to Audio Overviews on the go and download them for offline playback.”
   • [claimed-docs] “Transform your sources into a polished presentation by generating a Slide Deck, perfect for sharing or reviewing key concepts. Present your …”

   proof ↗⚑ flag

Pricing

1. researcherTry the product meaningfully on a free tier or trial

   weight 1 · round to Gemini Notebook (NotebookLM)
   Consensus—none0/10

   The evidence pack references a pricing page (consensus-docs-17) but only quotes a single line about 'Deep Searches' feature tiering; there is no description of a free tier, trial period, usage caps, or sign-up-free access that a researcher could evaluate. No first-party or independent evidence confirms Consensus offers a meaningful free/trial experience.

   • [claimed-docs] “Deep Searches (more comprehensive Lit Reviews across many studies)”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)~partialcommunity4/10

   Evidence confirms a paid subscription tier exists (analytics for paid users) implying a separate free tier, and community comments describe hands-on use (audio overviews, code walkthroughs) without mention of payment, suggesting meaningful free access. However, no doc explicitly states free-tier quotas, source limits, or trial duration for researchers. Missing for 10: explicit free-tier usage caps/limits documentation, direct confirmation of no-cost access, and independent confirmation of research-scale usability without upgrading.

   • [claimed-docs] “Owners of public notebooks with paid subscriptions can view usage analytics in the analytics tab.”
   • [community] “I used it to listen to a high level walkthrough of interesting and entertaining code while driving to work... Hearing it talk about Ken Thom…”
   • [community] “Much better name for this well-designed product. I do wish they made it easier to pull in emails. I had to use gyb and mhonarc to retrieve e…”

   proof ↗⚑ flag

2. researcherUnderstand plan pricing and usage limits before committing

   weight 2 · round to Gemini Notebook (NotebookLM)
   Consensus—none0/10

   No evidence pack items mention pricing plans, tiers, free/paid limits, or usage quotas — the pack is entirely about product features (citation graph, library, API capabilities). Absence of any pricing/limits documentation for an applicable axis yields none.

   ⚑ flag

   Gemini Notebook (NotebookLM)~partialclaimed3/10

   Docs mention some usage limits (500,000 words/200MB per source) and note that usage analytics require a paid subscription and Workspace inclusion, but there is no comprehensive pricing page, tier comparison, or explicit usage caps (e.g., number of notebooks, audio overviews per day) that a researcher would need to fully evaluate cost before committing. Missing for 10: full pricing tier breakdown, free vs paid feature/usage limits, and independent confirmation of these limits.

   • [claimed-docs] “Each source can contain up to 500,000 words or up to 200MB for uploaded files.”
   • [claimed-docs] “Owners of public notebooks with paid subscriptions can view usage analytics in the analytics tab.”
   • [claimed-docs] “For Workspace and Workspace for Education users, Gemini Notebook is now a core service (like Gmail, Google Calendar, and Docs).”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Consensus—none0/10

   No evidence in the pack mentions data residency, regional storage options, or any data-location controls for Consensus; all evidence concerns search, citation, and library features. Missing for 10: any mention of region selection, data residency policy, or storage location controls.

   ⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence in the pack mentions data residency, region selection, or storage location controls for Gemini Notebook; the docs cover features like sources, audio/video overviews, and sharing but say nothing about where data is stored or user control over it.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Consensus—none0/10

   No evidence pack item addresses data-training opt-out, privacy controls, or AI training data policies for Consensus; all citations concern search, library, and API features. missing for 10: any privacy policy statement, opt-out mechanism, or data usage/training disclosure.

   ⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence in the pack addresses data-training opt-out, privacy policy, or data usage controls for Gemini Notebook; all citations concern features (sources, summaries, audio/video overviews) rather than training-data privacy posture.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Consensus—none0/10

   No evidence in the pack addresses data retention policies, deletion controls, or privacy settings for user data/library content; all citations focus on search, citation, library, and API features. Missing for 10: any documentation on data retention windows, user-initiated deletion, export/erasure workflows, or privacy policy specifics.

   ⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence in the pack addresses data retention controls, deletion policies, or user ability to manage/export/delete stored data and sources beyond basic note export; the axis clearly applies to an AI-native privacy-conscious user but no documentation or community mention covers retention/deletion controls.

   ⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Consensus—none0/10

   No evidence in the pack mentions telemetry, usage tracking, or any opt-out/privacy settings for Consensus; all citations are about search, citation, and library features unrelated to telemetry controls.

   ⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence pack item mentions telemetry, usage-tracking opt-out, privacy controls, or data-collection settings; only feature docs and general community commentary are present.

   ⚑ flag

Reports

1. researcherExport results to common formats, including documents, spreadsheets, and reference-manager files

   weight 1 · round to Gemini Notebook (NotebookLM)
   Consensus—none0/10

   Evidence only documents importing papers into Consensus (from Zotero, BibTeX, PDF, RIS) but contains no mention of exporting results to documents, spreadsheets, or reference-manager formats. Missing for 10: any export-to-Word/PDF, export-to-CSV/spreadsheet, or export-to-Zotero/EndNote/BibTeX functionality.

   • [claimed-docs] “Import from Zotero ... or import from BibTex, PDF, or RIS”
   • [claimed-docs] “Reference managers are great at saving papers — not so great at helping you use them. The Consensus Library brings your entire research libr…”
   • [claimed-docs] “Import from Zotero”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)~partialclaimed5/10

   NotebookLM supports exporting notes to Google Docs or Google Sheets and can generate a Slide Deck exportable as PDF, covering document/spreadsheet-style outputs, but there is no evidence of export to reference-manager formats (e.g., BibTeX, RIS, EndNote) which the story explicitly requires. missing for 10: reference-manager file export, independent corroboration of export fidelity.

   • [claimed-docs] “You can export your notes to Google Docs or Google Sheets.”
   • [claimed-docs] “Transform your sources into a polished presentation by generating a Slide Deck, perfect for sharing or reviewing key concepts. Present your …”

   proof ↗⚑ flag

2. analystGet a structured report with sections, tables, and a summary that I can share with stakeholders

   weight 3 · round to Gemini Notebook (NotebookLM)
   Consensus~partialclaimed5/10

   Consensus offers 'Literature Review' and 'Deep Search' features that synthesize evidence across papers, extract structured fields like PICO, and provide citations—suggesting output with some structure and sourcing suitable for sharing. However, there's no explicit evidence of a polished 'report' format with distinct sections, tables, and an executive summary designed for stakeholder sharing (e.g., export to PDF/Word, formatted report templates). Missing for 10: explicit documentation of report formatting/export (sections, tables, summary), evidence of stakeholder-sharing features like PDF export or presentation-ready output, and independent confirmation of report quality.

   • [claimed-docs] “Search, screen, extract, and synthesize evidence faster—while keeping full transparency and scholarly rigor.”
   • [claimed-docs] “Consensus is an AI-powered research engine built to speed up literature reviews. Search, screen, extract, and synthesize evidence faster—whi…”
   • [claimed-docs] “Deep Searches (more comprehensive Lit Reviews across many studies)”
   • [claimed-docs] “Extracted population, intervention, comparator, and outcome (PICO) where applicable”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)~partialclaimed6/10

   NotebookLM supports Reports with FAQ/study guide/briefing document/custom formats and auto-generated source summaries, plus export of notes to Google Docs/Sheets and Slide Deck generation for sharing, which together cover structured, shareable outputs. However, evidence doesn't confirm native table generation within reports or a single unified 'report' combining sections+tables+summary in one export artifact. missing for 10: explicit table support in generated reports, a single cohesive exportable report format (vs separate docs/sheets/slides), independent/hands-on validation of report quality for stakeholder sharing.

   • [claimed-docs] “Create your own, or choose from FAQ, study guide, briefing document, or an AI suggested report type.”
   • [claimed-docs] “Find an auto-generated summary of the entire source in the Source Guide.”
   • [claimed-docs] “You can export your notes to Google Docs or Google Sheets.”
   • [claimed-docs] “Transform your sources into a polished presentation by generating a Slide Deck, perfect for sharing or reviewing key concepts.”
   • [claimed-docs] “Transform your sources into a polished presentation by generating a Slide Deck, perfect for sharing or reviewing key concepts. Present your …”

   proof ↗⚑ flag

Agent runs

1. researcherPose a research question and get an autonomous multi-step investigation, not just a single-pass summary

   weight 3 · round to Consensus
   Consensus~partialclaimed5/10

   Consensus advertises a 'Research Agent' that chains citation crawling, DOI lookup, author search, and similar-papers search on top of its search engine, plus a literature-review feature that searches, screens, extracts, and synthesizes evidence — both suggesting multi-step, not single-pass, investigation. However, evidence is limited to marketing feature pages with no walkthrough, example transcript, or independent corroboration of true autonomous multi-step reasoning over a posed question. Missing for 10: a documented end-to-end example of the agent autonomously chaining steps for a specific question, independent/hands-on verification, and detail on how far it goes without user intervention.

   • [claimed-docs] “Citation crawling, DOI lookup, author search, similar papers, and more - chained together on top of the worlds best academic search engine.”
   • [claimed-docs] “Search, screen, extract, and synthesize evidence faster—while keeping full transparency and scholarly rigor.”
   • [claimed-docs] “Consensus is an AI-powered research engine built to speed up literature reviews. Search, screen, extract, and synthesize evidence faster—whi…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   All evidence describes NotebookLM as a source-grounded chat/summarization tool: users upload sources, ask questions, and get single-pass answers, summaries, or generated formats (audio overviews, mind maps, slide decks) — there is no evidence of an autonomous multi-step investigation loop that iteratively searches, plans, or expands beyond the provided sources. A community report explicitly notes it cannot autonomously search for and incorporate new documents into research, reinforcing that it is single-pass/source-bound rather than agentic.

   • [claimed-docs] “Chat with your notebook to get grounded information based on your sources with clear in-line citations for accuracy, transparency, and trust…”
   • [claimed-docs] “Find an auto-generated summary of the entire source in the Source Guide.”
   • [claimed-docs] “Create your own, or choose from FAQ, study guide, briefing document, or an AI suggested report type.”
   • [community] “My problem with NotebookLM was that you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them int…”

   proof ↗⚑ flag

2. analystStart a long research job that keeps working unattended and notifies me when the result is ready

   weight 2 · round drawn
   Consensus—none0/10

   Evidence shows Deep Searches/Lit Reviews and a research agent chaining searches, but there is no mention of async job submission, background/unattended execution, or notification when a long-running job completes.

   ⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   No evidence in the pack describes an asynchronous/background 'long research job' mode with completion notifications; all cited capabilities (chat, summaries, audio/video overviews, flashcards, etc.) are generated within an active session, not unattended long-running jobs with alerts. Missing for 10: any documented async job queue, background processing status, or notification/alert mechanism when a task completes.

   ⚑ flag

3. researcherSteer the depth, effort, and scope of a research run before or while it executes

   weight 1 · round to Gemini Notebook (NotebookLM)
   Consensus—none0/10

   The evidence pack describes search, citation graph, library, and research-agent features but nowhere mentions controls for adjusting depth, effort, or scope of a research run before or during execution — no parameters, modes, or configuration options are documented.

   ⚑ flag

   Gemini Notebook (NotebookLM)~partialclaimed4/10

   NotebookLM lets users pick conversational style/persona (Default, Custom "PhD student" etc.) and choose report/output formats (FAQ, briefing, study guide), which offers some steering of scope and tone, but there is no evidence of controlling depth/effort (e.g., reasoning length, source breadth, iteration count) or adjusting a run mid-execution — outputs like Audio/Video Overviews are generated as fixed artifacts rather than steerable in-progress runs. missing for 10: mid-run steering controls, explicit depth/effort sliders or parameters, ability to expand/narrow scope during execution, independent evidence of these controls working as intended.

   • [claimed-docs] “Custom: Best for choosing a specific style ("Respond like a PhD student") or suggesting a role ("Pretend to be a role-playing game host.").”
   • [claimed-docs] “Select a conversational style. Default: Best for general purpose research and brainstorming tasks.”
   • [claimed-docs] “Create your own, or choose from FAQ, study guide, briefing document, or an AI suggested report type.”
   • [claimed-docs] “Choose a format. Deep Dive (default) for an in-depth conversation. Two hosts unpack and connect topics from your sources in a lively convers…”

   proof ↗⚑ flag

Citations

1. researcherSee citations for every substantive claim so I can verify it against the underlying source

   weight 3 · round to Gemini Notebook (NotebookLM)
   Consensus✓fullclaimed8/10

   Consensus documents that every AI-generated response includes citations tracing back to the original source paper, and features like the Consensus Meter classify individual papers (supporting/refuting) with traceable provenance, directly matching the researcher's need to verify claims against sources. Missing for 10: independent/hands-on verification of citation accuracy and completeness beyond vendor docs.

   • [claimed-docs] “Every response includes citations, so you can trace each insight back to the original source.”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”
   • [claimed-docs] “It searches over 200 million academic papers and uses language models to help you find, understand, and synthesize the literature faster.”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)✓fullclaimed9/10

   Docs confirm grounded chat responses come with clear in-line citations, hovering shows the exact quoted text, and clicking a citation navigates directly to the source location for verification — directly matching the story's requirement to verify claims against underlying sources. Community evidence corroborates general usefulness but doesn't specifically contest citation accuracy. Missing for 10: independent hands-on verification of citation accuracy/completeness across diverse source types.

   • [claimed-docs] “Chat with your notebook to get grounded information based on your sources with clear in-line citations for accuracy, transparency, and trust…”
   • [claimed-docs] “You can hover over any citation to get the full quoted text right away.”
   • [claimed-docs] “If you select a citation, Gemini Notebook automatically navigates to the location of the quote, so you can easily view it in context.”

   proof ↗⚑ flag

Corpus

1. researcherSearch scholarly literature and primary sources, not just the open web

   weight 2 · round to Consensus
   Consensus✓fullprobed9/10

   Consensus is explicitly built as a scholarly-search engine over 200M+ academic papers, including full-text and paywalled content, positioned as an AI-native alternative to Google Scholar, with citation tracing back to original sources. Missing for 10: independent third-party verification of corpus quality/coverage beyond vendor claims.

   • [claimed-docs] “Consensus analyzes the full text, including paywalled papers from major publishers, so you can find the most relevant papers.”
   • [claimed-docs] “Think of Consensus as an AI-native alternative to Google Scholar with a more-refined corpus.”
   • [claimed-docs] “It searches over 200 million academic papers and uses language models to help you find, understand, and synthesize the literature faster.”
   • [claimed-docs] “Every response includes citations, so you can trace each insight back to the original source.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://consensus.app/llms.txt # Consensus > Consensus is an AI-powered scientific search engine that finds, ra…”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)!disputedcontradicted3/10

   Docs vaguely mention users can 'discover new sources' (notebooklm-docs-1), but there is no evidence of integration with scholarly databases (e.g., PubMed, JSTOR, Google Scholar) for searching primary literature, and a hands-on community report explicitly states you cannot have NotebookLM search for and incorporate sources itself—you must supply URLs or docs yourself (notebooklm-comm-4). This directly contradicts the implied 'discover' capability, making it a disputed claim rather than a confirmed feature. missing for 10: evidence of any scholarly/primary-source search integration, first-party documentation describing how 'discover sources' actually searches literature, and independent confirmation that discovery works as claimed.

   • [claimed-docs] “Easily upload PDFs, websites, YouTube videos, audio files, Google Docs, or Google Slides or discover new sources.”
   • [community] “My problem with NotebookLM was that you had to give it URLs or docs, you couldn't just have it search for docs and then incorporate them int…”

   proof ↗⚑ flag

Synthesis

1. analystSee where sources agree and disagree instead of a single unqualified answer

   weight 2 · round to Consensus
   Consensus✓fullclaimed8/10

   The Consensus Meter explicitly classifies each relevant paper as supporting, refuting, or mixed/inconclusive on a given question and displays the distribution, directly surfacing agreement/disagreement across sources rather than a single answer, and every response includes citations back to originals. Missing for 10: independent/hands-on corroboration of the Meter's accuracy and no worked example showing disagreement handling in practice.

   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”
   • [claimed-docs] “The Consensus Meter is a visual aggregator that, for a yes/no/possibly question, classifies each relevant paper as supporting, refuting, or …”
   • [claimed-docs] “Every response includes citations, so you can trace each insight back to the original source.”

   proof ↗⚑ flag

   Gemini Notebook (NotebookLM)—none0/10

   The evidence describes grounded chat with citations, summaries, mind maps, and study aids, but nothing about explicitly surfacing agreement or contradiction across multiple sources. This is a fair capability to expect from a multi-source research tool, but no docs or community evidence mention comparative or conflict-detection analysis between sources.

   ⚑ flag