Consensus vs Undermind

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to Consensus
   Consensus✓fullprobed8/10

   A live probe confirms Consensus serves an llms.txt file at its root (HTTP 200) with a structured summary of the product, directly enabling agents to be pointed at agent-oriented docs. Missing for 10: broader agent-oriented doc formats (e.g. .md endpoints) return 404, and no independent third-party confirmation of llms.txt usage exists.

   • [probe] “PROBE llms.txt: HTTP 200 at https://consensus.app/llms.txt # Consensus > Consensus is an AI-powered scientific search engine that finds, ra…”
   • [probe] “PROBE docs-md: HTTP 404 at https://consensus.app/home/resources/how-consensus-works/.md”

   proof ↗⚑ flag

   Undermind—none0/10

   Direct probes show no llms.txt, no docs.md, and no openapi spec (all 404), meaning there is no agent-consumable documentation file for a generic AI agent to fetch. The only agent-oriented artifact is the MCP server page itself, which is a different integration mechanism, not llms.txt-style docs.

   • [probe] “PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”

   proof ↗⚑ flag

2. 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

   Undermind~partialprobed2/10

   Undermind's enterprise page claims 'programmatic queries via API' and integration into 'other tools and workflows,' hinting at automatable/headless use, but there is no CLI, no published API reference, and probes for OpenAPI/API docs all returned 404s. The only concretely documented automation path is the MCP server, which is designed for interactive agent clients (Cursor, VS Code, Claude) rather than headless CI pipelines. Missing for 10: documented API/CLI with auth and examples, evidence of CI/automation usage, and confirmation the enterprise API is publicly accessible rather than bespoke.

   • [claimed-docs] “Integrate Undermind's deep literature research capabilities directly into your other tools and workflows.”
   • [claimed-docs] “Programmatic queries via API”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”

   proof ↗⚑ flag

3. ai-native userConnect an agent via an official MCP server

   weight 3 · round to Undermind
   Consensus—none0/10

   Consensus is not an agent product itself, so the MCP-server axis applies as an ecosystem/API capability, but evidence only shows a REST API and llms.txt file — no mention of an official MCP server for connecting agents. missing for 10: any documented MCP server endpoint, MCP spec compliance, or third-party confirmation of MCP support.

   • [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

   Undermind✓fullprobed8/10

   Undermind publishes an official hosted MCP server (mcp.undermind.ai/mcp) with documented setup instructions for Cursor, VS Code, Claude, and any MCP-compatible client, plus specific tool capabilities (literature review, PDF Q&A, notes, curation). This is first-party documentation with concrete transport/endpoint details, confirmed by probe evidence of the docs page existing. Missing for 10: independent/hands-on community confirmation specifically of MCP connectivity (community evidence only covers the web search product, not MCP usage) and no public API schema (openapi probes 404).

   • [claimed-docs] “This adds Undermind directly to Cursor”
   • [claimed-docs] “Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata D…”
   • [claimed-docs] “This adds Undermind to VS Code as an MCP server.”
   • [claimed-docs] “claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
   • [claimed-docs] “Point the client at `https://mcp.undermind.ai/mcp`”
   • [claimed-docs] “Undermind works with any MCP-compatible client.”
   • [probe] “official MCP server documented at https://undermind.ai/mcp”

   proof ↗⚑ flag

4. 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

   Undermind—none0/10

   Evidence shows an MCP server, API access, and web/ChatGPT app integrations, but there is no mention of an official CLI tool for Undermind anywhere in the docs or probes; llms.txt, docs-md, and openapi probes all 404, and no CLI is documented.

   • [claimed-docs] “claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
   • [probe] “PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Undermind~partialprobed5/10

   Undermind documents a public MCP server (mcp.undermind.ai) with clear tool definitions for search, PDF Q&A, and workspace notes, which does let an AI agent drive the product programmatically (undermind-docs-3,4,5,13,14,15,19). However, a general documented REST/OpenAPI-style public API is only vaguely alluded to ('Programmatic queries via API' under Enterprise) and probes for llms.txt, docs.md, and openapi/swagger specs all return 404s, indicating no broadly published API reference. Missing for 10: a public OpenAPI/Swagger spec or REST API docs, and confirmation that the enterprise API is self-serve rather than sales-gated.

   • [claimed-docs] “Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata D…”
   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “This adds Undermind to VS Code as an MCP server.”
   • [claimed-docs] “claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
   • [claimed-docs] “Point the client at `https://mcp.undermind.ai/mcp`”
   • [claimed-docs] “Programmatic queries via API”
   • [probe] “PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”
   • [probe] “official MCP server documented at https://undermind.ai/mcp”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round drawn
   Consensus—none0/10

   Evidence shows an API and MCP server exist, but there is no mention of scoped or least-privilege API keys, permission scopes, or credential management for agents — just generic API access. missing for 10: scoped/least-privilege credential issuance, API key permission controls, agent-specific auth documentation.

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

   proof ↗⚑ flag

   Undermind—none0/10

   No evidence of scoped/least-privilege API credential issuance for agents; the API is only mentioned generically ('Programmatic queries via API') with no docs on credential scoping, permissions, or key management, and OpenAPI probes returned 404s.

   • [claimed-docs] “Programmatic queries via API”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”

   proof ↗⚑ flag

7. 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

   Undermind—none0/10

   Evidence only mentions a vague 'Programmatic queries via API' for enterprise customers and an MCP server, but no official SDKs (client libraries, language bindings) are documented; probes for OpenAPI specs and docs (llms.txt, mcp.md, openapi.json) all return 404, indicating no public developer SDK resources exist.

   • [claimed-docs] “Programmatic queries via API”
   • [probe] “PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”

   proof ↗⚑ flag

8. 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

   Undermind—none0/10

   The evidence mentions a notification feature for new papers (undermind-docs-9) but nothing indicates this is delivered via webhooks or any programmatic subscription mechanism; no webhook API, endpoint, or docs are present, and probes for API/openapi specs all 404.

   • [claimed-docs] “Get notified whenever relevant papers are published.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”

   proof ↗⚑ 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

   Undermind✓fullcommunity8/10

   Undermind's core capability is AI-generated synthesis and insight extraction from literature data: it runs deep research plans, produces ranked papers with written synthesis, answers cross-paper questions from PDFs, traces citations, and proactively notifies users of new relevant papers—all generated from the user's research data within the product. Community reviews corroborate that these AI-derived insights are often more useful than manual search (undermind-comm-2, undermind-comm-6, undermind-comm-15, undermind-comm-16), though some found gaps in coverage (undermind-comm-1, undermind-comm-4). Missing for 10: independent verification of insight/synthesis accuracy at scale and clearer support for arbitrary user-uploaded (non-literature) datasets.

   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
   • [claimed-docs] “Creates and edits Markdown notes, syntheses, and reports in the workspace. Citations link back to the source papers, and files stay availabl…”
   • [claimed-docs] “Get notified whenever relevant papers are published.”
   • [claimed-docs] “Trace any statement by following in-line citations back to the source paper”
   • [community] “I actually was able to find at least 4 new informative papers... in less than six minutes, your search engine was able to give me more relev…”
   • [community] “These are the best results that I've gotten from an AI research assistant. I really don't mind the long latency... The 'Discovery Progress a…”

   proof ↗⚑ flag

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

   weight 2 · round to Undermind
   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

   Undermind~partialclaimed3/10

   The only evidence of background automation is a single line about being notified when relevant papers are published, with no detail on how such alerts are configured, scheduled, or run autonomously as multi-step agent workflows. missing for 10: documentation of automation/scheduling setup, evidence of autonomous multi-step background agent tasks, and any hands-on confirmation of the notification feature working.

   • [claimed-docs] “Get notified whenever relevant papers are published.”

   proof ↗⚑ 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

   Undermind—none0/10

   Undermind is positioned as an MCP server/tool that other AI clients (Cursor, Claude, ChatGPT) connect to, not as a product with its own built-in AI assistant that users delegate tasks to within Undermind itself; evidence describes it being added to external agent tools rather than an in-product assistant. missing for 10: any evidence of a native, built-in AI assistant/chat agent inside Undermind's own UI that a user can delegate tasks to.

   • [claimed-docs] “This adds Undermind directly to Cursor”
   • [claimed-docs] “Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata D…”
   • [claimed-docs] “Undermind is available as a published ChatGPT app.”

   proof ↗⚑ flag

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

   weight 2 · round to Undermind
   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

   Undermind✓fullprobed8/10

   Undermind ships an official MCP server (Cursor, VS Code, Claude, ChatGPT app) that lets users issue open-ended natural-language research goals which the tool autonomously plans, searches, and synthesizes into reports, fitting the ai-native/agentic story well. Missing for 10: independent hands-on confirmation of the MCP natural-language workflow specifically (community evidence covers the web search UI, not the MCP NL commands) and any public usage examples/logs.

   • [claimed-docs] “Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata D…”
   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “This adds Undermind to VS Code as an MCP server.”
   • [claimed-docs] “claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
   • [claimed-docs] “Undermind is available as a published ChatGPT app.”
   • [probe] “official MCP server documented at https://undermind.ai/mcp”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round drawn
   Consensus—none0/10

   Evidence confirms Consensus offers a REST API and MCP server (consensus-docs-1, consensus-docs-15, consensus-docs-16), but there is no mention of an interactive API reference, sandbox, or runnable code examples anywhere in the pack.

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

   proof ↗⚑ flag

   Undermind—none0/10

   There is no evidence of an interactive API reference or runnable examples; probes explicitly show no OpenAPI/Swagger spec and no docs.md/llms.txt exist. The 'Programmatic queries via API' mention is a bare feature claim with no interactive reference or runnable examples provided.

   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”
   • [probe] “PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
   • [probe] “PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
   • [claimed-docs] “Programmatic queries via API”

   proof ↗⚑ flag

2. 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

   Undermind—none0/10

   Undermind mentions 'Programmatic queries via API' for enterprise but there is no evidence of a downloadable OpenAPI/Swagger spec; direct probes for openapi.json, swagger.json, and llms.txt all returned 404. Missing for 10: any published machine-readable API spec, documented API schema, or discoverable spec endpoint.

   • [claimed-docs] “Programmatic queries via API”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”

   proof ↗⚑ flag

3. 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

   Undermind—none0/10

   There is a mention of a 'Programmatic queries via API' for enterprise, but no evidence of versioning or a documented deprecation policy; probes for OpenAPI/docs all returned 404s. Missing for 10: any API versioning scheme, changelog, or deprecation policy documentation.

   • [claimed-docs] “Programmatic queries via API”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Undermind~partialclaimed6/10

   Undermind's MCP tools explicitly support bulk-style operations: reading full-text PDFs in parallel and answering questions across many papers at once, and running a deep literature review that autonomously searches and synthesizes across large numbers of papers. Enterprise API access also enables programmatic bulk queries. However, there is no evidence of bulk editing/tagging/exporting or batch management operations across items (e.g., bulk-star, bulk-move to folders) — missing for 10: documented batch update/edit/export APIs, evidence of bulk actions beyond reading/analysis, independent verification of parallel-processing claims.

   • [claimed-docs] “Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Programmatic queries via API”
   • [claimed-docs] “Curate papers into a folder for long-term use.”
   • [claimed-docs] “Star important papers across the workspace.”

   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

   Undermind—none0/10

   There's a notification feature for new papers (undermind-docs-9) but no evidence of scheduling recurring jobs/workflows, cron-like automation, or configurable recurring tasks; the product focuses on on-demand deep research via MCP tools rather than persistent scheduled automation.

   • [claimed-docs] “Get notified whenever relevant papers are published.”

   proof ↗⚑ flag

Sharing

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

   weight 2 · round drawn
   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

   Undermind—none0/10

   Evidence covers workspace files, folders, and note creation but never mentions sharing sessions/reports with collaborators, multi-user access, or permission controls. missing for 10: any mention of sharing/collaboration features, invite/permission mechanisms, or multi-user workspace access.

   ⚑ flag

Alerts

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

   weight 1 · round to Undermind
   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

   Undermind~partialclaimed6/10

   Undermind explicitly offers a 'Get notified whenever relevant papers are published' alert feature, which directly matches the standing-search/alert story, plus curated folders and starred papers for ongoing tracking. However, there is no independent/hands-on evidence of how the alert system works in practice (frequency, delivery channel, reliability), and community discussion focuses on one-off search quality rather than alerting. Missing for 10: independent corroboration of alert functionality, details on alert configuration/frequency, and hands-on user reports of ongoing alerts working as described.

   • [claimed-docs] “Get notified whenever relevant papers are published.”
   • [claimed-docs] “Curate papers into a folder for long-term use.”
   • [claimed-docs] “Star important papers across the workspace.”

   proof ↗⚑ flag

Corpus

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

   weight 2 · round to Consensus
   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

   Undermind—none0/10

   Evidence shows Undermind reads full-text PDFs and lets users curate/star papers discovered via its own search engine, but nothing indicates a feature to upload arbitrary personal PDFs or a private corpus for the agent to research over — all workflows described start from Undermind's own literature search rather than user-supplied documents.

   • [claimed-docs] “Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
   • [claimed-docs] “Curate papers into a folder for long-term use.”
   • [claimed-docs] “Star important papers across the workspace.”

   proof ↗⚑ flag

Reviews

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

   weight 2 · round drawn
   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

   Undermind~partialcommunity6/10

   Undermind's MCP tools support open-ended literature review with ranked results, full-text PDF question-answering across many papers, and note/synthesis creation, which covers much of a screening-and-extraction workflow (undermind-docs-4, undermind-docs-5, undermind-docs-6, undermind-docs-7). However, there is no evidence of formal criteria-based screening (e.g., inclusion/exclusion rules) or structured, consistent extraction fields across a batch of papers, and community feedback notes gaps in coverage (missed gray literature/theses) that could undermine consistency (undermind-comm-1, undermind-comm-4). Missing for 10: explicit support for defined screening criteria, structured/consistent extraction schema, and independent validation of consistency at scale.

   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
   • [claimed-docs] “Creates and edits Markdown notes, syntheses, and reports in the workspace. Citations link back to the source papers, and files stay availabl…”
   • [claimed-docs] “Curate papers into a folder for long-term use.”
   • [community] “OK, I'm both impressed and disappointed. It seems to rely too much on citation count, and I don't see much dissertations/theses in the resul…”
   • [community] “Overall, I am impressed, and I can easily imagine my lab paying for this... but it seems to have missed a lot of the gray literature, partic…”

   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

   Undermind~partialprobed5/10

   Undermind exposes core research capabilities (deep literature search, PDF Q&A, note creation, curation, starring) via an official MCP server, and separately claims 'Programmatic queries via API' for enterprise customers, showing some AI-native parity. However, there is no public API/OpenAPI documentation (all probes 404), no evidence that UI-only features like notifications/alerts or workspace management are exposed programmatically, and the API claim is a single unelaborated enterprise line rather than a documented full-parity API. Missing for 10: public API docs/OpenAPI spec, confirmation that all UI features (alerts, workspace/library management) are API-accessible, and independent verification of API completeness.

   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
   • [claimed-docs] “Creates and edits Markdown notes, syntheses, and reports in the workspace. Citations link back to the source papers, and files stay availabl…”
   • [claimed-docs] “Curate papers into a folder for long-term use.”
   • [claimed-docs] “Star important papers across the workspace.”
   • [claimed-docs] “Programmatic queries via API”
   • [claimed-docs] “Get notified whenever relevant papers are published.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/opena…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Undermind—none0/10

   No evidence of any data export feature or open-format export capability for user data/papers/workspaces; probes for docs/API endpoints also 404. The evidence covers MCP integration and search quality, not data portability or export/leave capability.

   ⚑ flag

Pricing

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

   weight 1 · round to Undermind
   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

   Undermind!disputedcontradicted4/10

   Docs imply a tiered system (e.g. '10x higher usage limits' for paid vs default) suggesting a free/limited tier exists, but community evidence shows a hard institutional/company email requirement blocking sign-up, with an independent researcher explicitly reporting they 'can't get in' and another calling the requirement 'obnoxious' and a 'roadblock' — concretely contradicting the ability for many researchers to try it meaningfully for free. Missing for 10: explicit vendor documentation of a free tier or trial with stated limits, and confirmation the email gate has been removed or has an exception path for independent researchers.

   • [claimed-docs] “Deepest analysis of full texts 10x higher usage limits Unlimited workspaces, files, and paper libraries”
   • [community] “Independent researcher without academic address; can't get in. Best of luck.”
   • [community] “'Please use a valid institutional or company email address.' This is obnoxious. Please remove this unnecessary roadblock.”

   proof ↗⚑ flag

2. researcherUnderstand plan pricing and usage limits before committing

   weight 2 · round drawn
   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

   Undermind—none0/10

   Evidence includes only a fragmentary marketing snippet ('10x higher usage limits, unlimited workspaces...') with no actual price points, plan names, or explicit usage caps, and no dedicated pricing page is cited. A researcher cannot compare plans or understand limits before committing from this evidence alone.

   • [claimed-docs] “Deepest analysis of full texts 10x higher usage limits Unlimited workspaces, files, and paper libraries”

   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

   Undermind—none0/10

   No evidence in the pack mentions data residency, regional storage options, or any data-location controls for Undermind. missing for 10: any mention of region selection, data residency policy, or storage location controls.

   ⚑ 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

   Undermind—none0/10

   No evidence in the pack addresses data privacy, opt-out of AI training, or data usage policies for Undermind; nothing here confirms or denies such a control exists.

   ⚑ 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

   Undermind—none0/10

   No evidence in the pack addresses data retention policies, deletion controls, or privacy/data-handling settings for Undermind; all evidence concerns search quality, MCP integration, and product features. This axis applies to any AI-native product handling user data/queries, but there is no documented capability for controlling or deleting stored data.

   ⚑ 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

   Undermind—none0/10

   No evidence in the pack mentions telemetry, usage tracking, opt-out settings, or privacy controls for Undermind; all evidence covers product features, MCP integration, and general reception.

   ⚑ flag

Reports

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

   weight 1 · round drawn
   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

   Undermind—none0/10

   Evidence shows Undermind creates/edits Markdown notes and reports with citations, and can curate/star papers, but there is no mention of exporting to common document formats (e.g., Word/PDF), spreadsheets (e.g., CSV/Excel), or reference-manager formats (e.g., BibTeX, RIS, EndNote).

   ⚑ flag

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

   weight 3 · round drawn
   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

   Undermind~partialclaimed5/10

   Undermind produces a ranked list of papers with a written synthesis and can create/edit Markdown notes, syntheses, and reports with citations linking back to sources, which supports shareable structured output. However, there is no evidence of built-in tables, formal 'sections' structuring, or a dedicated stakeholder-facing report/export format beyond Markdown notes. Missing for 10: explicit table generation, multi-section report templates, and export/sharing formats (PDF/Word) for stakeholders beyond in-workspace Markdown.

   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Creates and edits Markdown notes, syntheses, and reports in the workspace. Citations link back to the source papers, and files stay availabl…”
   • [claimed-docs] “Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”

   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 Undermind
   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

   Undermind✓fullcommunity8/10

   Docs explicitly describe an autonomous multi-step deep literature review agent that plans its own searches, follows citations and key authors, reads full-text PDFs in parallel, and stops only when new searches stop finding relevant papers — not a single-pass summary. Community reviews corroborate multi-minute, iterative search behavior yielding comprehensive results beyond a simple query-response. Missing for 10: independent technical breakdown of the multi-step planning/agentic loop and more recent hands-on validation of the 'stops when exhausted' claim.

   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Plans its own searches, follows citations and key authors, and stops only when new searches stop finding relevant papers.”
   • [claimed-docs] “Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
   • [community] “Been using Undermind for several months now and it's honestly been a lifesaver in getting a comprehensive understanding of a research topic.”
   • [community] “These are the best results that I've gotten from an AI research assistant. I really don't mind the long latency... The 'Discovery Progress a…”
   • [community] “I actually was able to find at least 4 new informative papers... in less than six minutes, your search engine was able to give me more relev…”

   proof ↗⚑ flag

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

   weight 2 · round to Undermind
   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

   Undermind~partialcommunity5/10

   Undermind's deep literature review runs autonomously, planning its own searches and stopping only when exhausted (undermind-docs-4/16), and it has a notification feature for relevant papers (undermind-docs-9), suggesting async, unattended operation. However, the notification feature is documented as an ongoing 'new paper published' alert rather than a 'job complete, come see results' notification, and community reports describe run times of minutes (3-6 min) rather than long unattended background jobs (undermind-comm-14/15/16). Missing for 10: explicit documentation that a single research job can run for extended/unattended periods (hours+) and trigger a completion notification, plus independent confirmation of this exact workflow.

   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Plans its own searches, follows citations and key authors, and stops only when new searches stop finding relevant papers.”
   • [claimed-docs] “Get notified whenever relevant papers are published.”
   • [community] “Hmm, does this just use traditional term frequency search under the hood with query expansion? Using GPT4 as a cross encoder seems really wa…”
   • [community] “I actually was able to find at least 4 new informative papers... in less than six minutes, your search engine was able to give me more relev…”
   • [community] “These are the best results that I've gotten from an AI research assistant. I really don't mind the long latency... The 'Discovery Progress a…”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   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

   Undermind—none0/10

   Undermind's research runs are described as fully autonomous — it 'plans its own searches... and stops only when new searches stop finding relevant papers' (undermind-docs-4, undermind-docs-16), with no documented controls for setting depth, effort, or scope before or during a run. A user comment notes confusion about the 'Discovery Progress and Exhaustiveness' indicator (undermind-comm-16), suggesting only passive visibility, not steering. No evidence of parameters, sliders, or mid-run adjustments exists in the pack.

   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Plans its own searches, follows citations and key authors, and stops only when new searches stop finding relevant papers.”
   • [community] “These are the best results that I've gotten from an AI research assistant. I really don't mind the long latency... The 'Discovery Progress a…”

   proof ↗⚑ flag

Citations

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

   weight 3 · round to Consensus
   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

   Undermind✓fullcommunity7/10

   Undermind's docs explicitly claim in-line citations traceable to source papers ([undermind-docs-12], [undermind-docs-6]) and community reviews corroborate it reliably surfaces cited references (e.g. [undermind-comm-8] notes it 'solves' the reference-provision problem unlike a chatbot). However, no independent hands-on verification of citation accuracy/completeness at the claim level is present, and some reviewers note gaps in coverage (missing gray literature/theses) which could affect verifiability of some claims. Missing for 10: independent audit of citation accuracy per-claim, and confirmation citations withstand scrutiny across all source types.

   • [claimed-docs] “Trace any statement by following in-line citations back to the source paper”
   • [claimed-docs] “Creates and edits Markdown notes, syntheses, and reports in the workspace. Citations link back to the source papers, and files stay availabl…”
   • [community] “Compared roughly similar research questions using Claude 3.5 Sonnet and Undermind. Claude is reluctant to provide references, but Undermind …”
   • [community] “OK, I'm both impressed and disappointed. It seems to rely too much on citation count, and I don't see much dissertations/theses in the resul…”
   • [community] “Overall, I am impressed, and I can easily imagine my lab paying for this... but it seems to have missed a lot of the gray literature, partic…”

   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

   Undermind✓fullcommunity8/10

   Undermind is purpose-built for scholarly literature search: it runs deep literature reviews over papers, reads full-text PDFs including figures/tables/equations, and traces claims back to source papers via citations, with independent community reports confirming it surfaces relevant academic papers beyond Google Scholar. Some community feedback notes gaps in coverage (dissertations, gray literature), which tempers but doesn't negate the core capability. Missing for 10: no independent benchmark on primary-source/preprint coverage breadth, and some users report missed gray literature/theses.

   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”
   • [claimed-docs] “Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
   • [claimed-docs] “Trace any statement by following in-line citations back to the source paper”
   • [claimed-docs] “Undermind's v1 search engine delivered 10x better results than Google Scholar”
   • [community] “This is a nice search engine. I found it to be more effective than crawling with Google Scholar. Good work guys!”
   • [community] “As a CS academic, the top 10 results contained two items I really ought to have found myself... overall I'm very impressed with this.”
   • [community] “I actually was able to find at least 4 new informative papers... in less than six minutes, your search engine was able to give me more relev…”
   • [community] “OK, I'm both impressed and disappointed. It seems to rely too much on citation count, and I don't see much dissertations/theses in the resul…”
   • [community] “Overall, I am impressed, and I can easily imagine my lab paying for this... but it seems to have missed a lot of the gray literature, partic…”

   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

   Undermind—none0/10

   The evidence pack describes literature search, synthesis, citation tracing, and PDF Q&A features, but nowhere does it mention surfacing conflicting findings, agreement/disagreement across sources, or qualifying claims by consensus vs. dispute. Citation tracing (docs-12) only supports tracing a single claim to its source, not comparing multiple sources' stances. Missing for 10: any feature or documentation showing detection/display of cross-source agreement or contradiction, any UI element flagging conflicting conclusions, community evidence of this behavior.

   • [claimed-docs] “Trace any statement by following in-line citations back to the source paper”
   • [claimed-docs] “Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own …”

   proof ↗⚑ flag