vs Elicit
vs Consensus
vs FutureHouse Platform
vs Undermind
vs Sakana MarlinProducts
Google, product by product →Google ships more than one product — each judged line competes in its own arena on the same stories as everyone else.
| Line | Arena | Rank | PA Score | Agent-ready |
|---|---|---|---|---|
| Gemini | AI Assistants | #7/9 | 17/100 | 9/100 |
| Antigravity | AI Coding Agents | #5/13 | 37/100 | 55/100 |
| Gemini CLI | AI Coding Agents | #12/13 | 21/100 | 38/100 |
| Gemini Notebook (NotebookLM)this page | AI Research Agents | #6/6 | 7/100 | 0/100 |
| Jules | Software Factory | #7/9 | 23/100 | 29/100 |
| Agent Development Kit | Agent Frameworks & SDKs | #4/9 | 35/100 | 46/100 |
| Firebase | Backend as a Service | #3/4 | 35/100 | 43/100 |
| Angular | Frontend Frameworks | #3/5 | 28/100 | 12/100 |
Not yet judged (4 — no arena where they compete): Google AI Studio · Flow · Gemini in Chrome · Gemini Code Assist
Try itExperimental
See what an agent can do with Gemini Notebook (NotebookLM) before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$curl -sL 'https://support.google.com/gemininotebook/answer/16322204?hl=en' | grep -oiE 'public notebooks?' | sort | uniq -crecorded session — replayed, not liveVerified integrations
No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.
By theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Collaboration sharing — stories about collaboration sharing in this arenaCollaboration sharingevidence →
Stories about collaboration sharing in this arena
Literature workflow — stories about literature workflow in this arenaLiterature workflowevidence →
Stories about literature workflow in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limitsevidence →
Free-tier ceilings, usage caps, and rate limits before you have to pay
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Report output — stories about report output in this arenaReport outputevidence →
Stories about report output in this arena
Research depth — stories about research depth in this arenaResearch depthevidence →
Stories about research depth in this arena
Source quality — stories about source quality in this arenaSource qualityevidence →
Stories about source quality in this arena
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where Gemini Notebook (NotebookLM) stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
—–
Subscribe to events via webhooks
—–
Build against official SDKs
—–
Issue scoped/least-privilege API credentials for an agent
n/an/a
Connect an agent via an official MCP server
n/an/a
Download a machine-readable API spec (OpenAPI or equivalent)
—–
Rely on versioned APIs with a documented deprecation policy
—–
Test against a sandbox environment without touching production data
n/an/a
Explore an interactive API reference with runnable examples
n/an/a
Docs for agents
Point an agent at llms.txt or agent-oriented docs
n/an/a
Agentic features
Delegate tasks to a built-in AI assistant inside the product
~4/10
unlocks → MCP client
Operate the product with natural-language commands
~6/10
unlocks → Autonomous automations
Plug MCP servers into this product so it can use their tools
—0/10
Get AI-generated insights and suggestions from my data inside the product
✓8/10
Set up automations that run autonomously in the background
—–
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Collaboration sharing — stories about collaboration sharing in this arenaCollaboration sharing
Stories about collaboration sharing in this arena
Literature workflow — stories about literature workflow in this arenaLiterature workflow
Stories about literature workflow in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits
Free-tier ceilings, usage caps, and rate limits before you have to pay
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Report output — stories about report output in this arenaReport output
Stories about report output in this arena
Research depth — stories about research depth in this arenaResearch depth
Stories about research depth in this arena
Agent runs
Source quality — stories about source quality in this arenaSource quality
Stories about source quality in this arena
Sorted by importance (agentic first) (high → low) · 43/43 stories · click a row’s chevron for the rationale and evidence
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 4/10 | Xcommunity | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ||
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | n/a | untested | none yet | |
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | untested | none yet | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Xcommunity | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Xcommunity | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | n/a | untested | none yet | |
See citations for every substantive claim so I can verify it against the underlying source C Citations | researcher | Source quality — stories about source quality in this arenaSource quality | 3 | full | 9/10 | Cclaimed | |
Get a structured report with sections, tables, and a summary that I can share with stakeholders C Reports | analyst | Report output — stories about report output in this arenaReport output | 3 | partial | 6/10 | Cclaimed | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | partial | 3/10 | Cclaimed | |
Pose a research question and get an autonomous multi-step investigation, not just a single-pass summary C Agent runs | researcher | Research depth — stories about research depth in this arenaResearch depth | 3 | none | 0/10 | ||
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | none | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | n/a | untested | none yet | |
Upload my own PDFs or corpus and have the agent research over them C Corpus | researcher | Literature workflow — stories about literature workflow in this arenaLiterature workflow | 2 | full | 8/10 | Xcommunity | |
Share a research session or report with collaborators who can view or build on it C Sharing | analyst | Collaboration sharing — stories about collaboration sharing in this arenaCollaboration sharing | 2 | partial | 7/10 | Cclaimed | |
Run a systematic screening and extraction workflow across many papers with consistent criteria C Reviews | researcher | Literature workflow — stories about literature workflow in this arenaLiterature workflow | 2 | partial | 3/10 | Xcommunity | |
Search scholarly literature and primary sources, not just the open web C Corpus | researcher | Source quality — stories about source quality in this arenaSource quality | 2 | disputed | 3/10 | Dcontradicted | |
Understand plan pricing and usage limits before committing G Pricing | researcher | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | partial | 3/10 | Cclaimed | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | 0/10 | ||
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | n/a | 0/10 | ||
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
See where sources agree and disagree instead of a single unqualified answer C Synthesis | analyst | Source quality — stories about source quality in this arenaSource quality | 2 | none | untested | none yet | |
Start a long research job that keeps working unattended and notifies me when the result is ready C Agent runs | analyst | Research depth — stories about research depth in this arenaResearch depth | 2 | none | untested | none yet | |
Export results to common formats, including documents, spreadsheets, and reference-manager files G Reports | researcher | Report output — stories about report output in this arenaReport output | 1 | partial | 5/10 | Cclaimed | |
Steer the depth, effort, and scope of a research run before or while it executes C Agent runs | researcher | Research depth — stories about research depth in this arenaResearch depth | 1 | partial | 4/10 | Cclaimed | |
Try the product meaningfully on a free tier or trial G Pricing | researcher | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 1 | partial | 4/10 | Xcommunity | |
Set up standing searches or alerts that surface new relevant sources as they appear C Alerts | researcher | Literature workflow — stories about literature workflow in this arenaLiterature workflow | 1 | none | 0/10 | ||
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | n/a | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 31 stories with headroom
What would move Gemini Notebook (NotebookLM)’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
Missing: any mention of MCP support, tool/plugin ecosystem, or extensibility API.
Agenticness — how well agents can access and operate the productDrive the product through a documented public API
nonemoves agent-readyimpact 45
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.
Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events
nonemoves PA Scoreimpact 30
No evidence of any rule-based or event-triggered automation (e.g., 'when X happens, do Y') in NotebookLM; the product is a research/synthesis tool that responds to manual user prompts and generates static outputs like summaries, audio/video overviews, and study guides, not automated event-driven actions.
Research depth — stories about research depth in this arenaPose a research question and get an autonomous multi-step investigation, not just a single-pass summary
nonemoves PA Scoreimpact 30
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.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
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.
Agenticness — how well agents can access and operate the productSet up automations that run autonomously in the background
nonemoves Built-in AIimpact 30
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.
Agenticness — how well agents can access and operate the productRun the product headlessly / in CI for automation
nonemoves agent-readyimpact 30
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.
Agenticness — how well agents can access and operate the productUse an official CLI
nonemoves agent-readyimpact 30
No evidence of an official CLI for Gemini Notebook; all documentation describes a web/app UI with no command-line interface mentioned.
Showing the top 8 of 31 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map2 surfaces · 14 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
Gemininotebook docs14 stories
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Share a research session or report with collaborators who can view or build on it
- Upload my own PDFs or corpus and have the agent research over them
- Run a systematic screening and extraction workflow across many papers with consistent criteria
- Export all of my data in open formats and leave
- Try the product meaningfully on a free tier or trial
- Understand plan pricing and usage limits before committing
- Export results to common formats, including documents, spreadsheets, and reference-manager files
- Get a structured report with sections, tables, and a summary that I can share with stakeholders
- Steer the depth, effort, and scope of a research run before or while it executes
- See citations for every substantive claim so I can verify it against the underlying source
- Search scholarly literature and primary sources, not just the open web
Hacker News7 stories
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Upload my own PDFs or corpus and have the agent research over them
- Run a systematic screening and extraction workflow across many papers with consistent criteria
- Try the product meaningfully on a free tier or trial
- Search scholarly literature and primary sources, not just the open web
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$curl -sL 'https://support.google.com/gemininotebook/answer/16322204?hl=en' | grep -oiE 'public notebooks?' | sort | uniq -creproduced$ curl -sL 'https://support.google.com/gemininotebook/answer/16322204?hl=en' | grep -oiE 'public notebooks?' | sort | uniq -c 1 Public Notebook 4 public notebook 9 public notebooks
$curl -sL 'https://support.google.com/gemininotebook/answer/16215270?hl=en' | grep -oiE 'Deep Research|Fast Research|sources for your notebook' | sort | uniq -creproduced$ curl -sL 'https://support.google.com/gemininotebook/answer/16215270?hl=en' | grep -oiE 'Deep Research|Fast Research|sources for your notebook' | sort | uniq -c 7 Deep Research 2 Fast Research 5 sources for your notebook
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
1 of 5 testable claims verified · 0 contradicted → integrity 20/100
20 distinct capability claims found in Gemini Notebook (NotebookLM)’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
1
Verified
4
Unverified
0
Contradicted
8
Undersold
Verified (1)
“Upload PDFs, websites, YouTube videos, audio files, Google Docs, or Slides as sources, or discover new ones”
Upload my own PDFs or corpus and have the agent research over themfullproof ↗
Unverified (5)
“Chat with a notebook to get answers grounded in your sources with inline citations”
See citations for every substantive claim so I can verify it against the underlying sourcefullproof ↗
“Hover over a citation to instantly see the full quoted source text”
See citations for every substantive claim so I can verify it against the underlying sourcefullproof ↗
“Make a notebook public and share it via link with any Google account holder”
Share a research session or report with collaborators who can view or build on itpartialproof ↗
“Export notes to Google Docs or Google Sheets”
Export results to common formats, including documents, spreadsheets, and reference-manager filespartialproof ↗
“Generate a polished slide deck presentation from notebook sources”
Get a structured report with sections, tables, and a summary that I can share with stakeholderspartialproof ↗
Undersold (8)
Get AI-generated insights and suggestions from my data inside the productfullproof ↗
Delegate tasks to a built-in AI assistant inside the productpartialproof ↗
Operate the product with natural-language commandspartialproof ↗
Run a systematic screening and extraction workflow across many papers with consistent criteriapartialproof ↗
Export all of my data in open formats and leavepartialproof ↗
Try the product meaningfully on a free tier or trialpartialproof ↗
Understand plan pricing and usage limits before committingpartialproof ↗
Steer the depth, effort, and scope of a research run before or while it executespartialproof ↗
Claims outside our story set (14)
Real capability claims found in Gemini Notebook (NotebookLM)’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Transform sources into study guides, briefings, audio overviews, mind maps, and other formats”
source ↗“Each source supports up to 500,000 words or 200MB per uploaded file”
source ↗“Auto-generated summary of an entire source available in the Source Guide”
source ↗“Customize response style or persona (e.g. respond like a PhD student or role-play a host)”
source ↗“Paid subscribers who own public notebooks can view usage analytics”
source ↗“Listen to Audio Overviews on the go and download them for offline playback”
source ↗“Share a website, PDF, or YouTube video directly into a notebook from your device”
source ↗“Convert a saved note into a usable source within the notebook”
source ↗“Generate mind maps that visually branch out main topics and related ideas from sources”
source ↗“Generate a Deep Dive audio overview where two AI hosts discuss and connect topics from sources”
source ↗“Generate Video Overviews that turn notebook sources into an engaging video”
source ↗“Generate flashcards or quizzes as interactive study aids from source material”
source ↗“Generate infographics that visually summarize complex source information”
source ↗“Gemini Notebook is included as a core Google Workspace / Education service”
source ↗
Business model
Free with notebook and source limits; Google AI Pro/Ultra subscriptions raise limits and unlock premium features like higher source caps and research options.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents