Claude vs Perplexity

Agent access

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

   weight 2 · round to Perplexity
   Claude✓fullprobed7/10

   A probe confirms Claude's support site serves a working llms.txt (HTTP 200) listing topic links, and numerous individual documentation pages are available in clean .md format (e.g. claude-docs-1 through 63 all resolve as .md URLs), making the docs directly consumable by an agent. Missing for 10: confirmation that llms.txt/agent-readable docs exist on the main claude.com domain (only support.claude.com was probed), and independent/community evidence that agents actually consume these successfully rather than just first-party doc structure.

   • [probe] “PROBE llms.txt: HTTP 200 at https://support.claude.com/llms.txt # Claude Help Center > Search for answers or browse by topic ## English #…”
   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.claude.com/en/.md”

   proof ↗⚑ flag

   Perplexity✓fullprobed9/10

   Perplexity's docs site directly serves an llms.txt file (HTTP 200) plus per-page .md variants that explicitly point agents to the llms.txt index for full documentation, confirming a genuine agent-oriented docs surface; this is corroborated by an OpenAPI spec, official MCP server, and CLI docs also structured for agent consumption. Missing for 10: independent third-party confirmation that agents actually consume this llms.txt successfully in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.perplexity.ai/llms.txt # Perplexity > Perplexity API documentation for building with the Agent API…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.perplexity.ai/docs/getting-started/overview.md > ## Documentation Index > Fetch the complete documen…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [claimed-docs] “The pplx CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and co…”

   proof ↗⚑ flag

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

   weight 2 · round to Perplexity
   Claude—none0/10

   The evidence describes Claude Code as a terminal tool and mentions CLI/print output structure, but there is no documentation or claim of headless/non-interactive execution, CI pipeline integration, or scriptable automation mode for Claude products.

   • [claimed-docs] “Build with Claude Code in your terminal, then deploy to a URL Claude can reach”
   • [claimed-docs] “The screen reader mode brings Claude Code back to the basic terminal experience: plain, sequential text with added labels and cues”
   • [community] “src/cli/print.ts is the single worst function in the codebase by every metric: 3,167 lines long, 12 levels of nesting at its deepest, ~486 b…”

   proof ↗⚑ flag

   Perplexity✓fullprobed7/10

   Perplexity provides an OpenAI-compatible Agent API with structured JSON output, model fallback, sandboxed code execution, and reusable profiles, plus a dedicated `pplx` CLI explicitly designed for shell pipelines and coding agents that need current web results — all suitable for headless/CI automation. missing for 10: no independent/hands-on report confirming real-world CI pipeline usage, and no documented rate-limit/quota guidance specifically for automated batch workloads.

   • [claimed-docs] “The pplx CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and co…”
   • [claimed-docs] “The `pplx` CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and …”
   • [claimed-docs] “The `pplx` CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and …”
   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer”
   • [claimed-docs] “Structured output makes the model return JSON that conforms to a schema you define, so you can deserialize it directly.”
   • [claimed-docs] “Model fallback enables specifying multiple models in a `models` array. The API tries each model in order until one succeeds, providing autom…”
   • [claimed-docs] “A profile is a reusable, versioned configuration that you save and manage.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [probe] “official CLI documented at https://docs.perplexity.ai/docs/cli/overview”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to Claude
   Claude✓fullprobed9/10

   Claude documents connecting to both remote MCP servers via custom connectors and installing local MCP servers on Claude Desktop as easily as browser extensions, plus a unified directory for finding/installing connectors, letting Claude use their tools. Missing for 10: independent/hands-on verification of MCP tool usage reliability beyond vendor docs.

   • [claimed-docs] “Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “You can: Connect Claude to existing remote MCP servers. Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “You can: - Connect Claude to existing remote MCP servers. - Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “installing and managing local MCP servers has become significantly easier... install local MCP servers on your computer as easily as browser…”
   • [claimed-docs] “you can now install local MCP servers on your computer as easily as browser extensions”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [probe] “official MCP server documented at https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp”

   proof ↗⚑ flag

   Perplexity—none0/10

   All MCP evidence describes Perplexity acting as an MCP *server* (Computer MCP server, Perplexity MCP Server) that other AI assistants can connect to, not Perplexity itself consuming external MCP servers as a client to gain new tools. There is no documentation of a settings/config surface where a user adds arbitrary third-party MCP servers for Perplexity to call.

   • [claimed-docs] “Through the Model Context Protocol, your MCP client can delegate complex, multi-step work to Computer and receive structured results.”
   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “**Connect to 400+ services** through a managed connector framework with one-click OAuth”
   • [claimed-docs] “Browser Control Computer includes a full cloud browser for tasks that go beyond search.”
   • [claimed-docs] “The Perplexity MCP Server enables AI assistants to access Perplexity's powerful search and reasoning capabilities directly within their work…”
   • [claimed-docs] “Give AI assistants the ability to complete real-world tasks using Perplexity Computer through the Model Context Protocol (MCP).”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to Perplexity
   Claude!disputedcontradicted6/10

   Anthropic ships an official CLI, Claude Code, well documented for terminal-based coding, deployment, debugging, and even screen-reader accessibility (claude-docs-8, claude-docs-23, claude-docs-52, claude-docs-65). However, a hands-on community report describes it as an 'empty unresponsive terminal' upon first use, contradicting the polished experience implied by docs, and another notes serious code-quality issues in the CLI's own codebase (claude-comm-13, claude-comm-15). missing for 10: broader independent corroboration of reliable day-to-day CLI usage, resolution of reported unresponsiveness, and evidence the code-quality issues have been fixed.

   • [claimed-docs] “Build with Claude Code in your terminal, then deploy to a URL Claude can reach. Test and verify in the browser with the Chrome extension. De…”
   • [claimed-docs] “Build with Claude Code in your terminal, then deploy to a URL Claude can reach. Test and verify in the browser with the Chrome extension.”
   • [claimed-docs] “Build with Claude Code in your terminal, then deploy to a URL Claude can reach”
   • [claimed-docs] “It was built with and for screen reader users, and it's useful to anyone who wants plain output for braille displays, slow connections, or t…”
   • [community] “Tried claude code, and have an empty unresponsive terminal. Looks cool in the demo though, but not sure this is going to perform better than…”
   • [community] “src/cli/print.ts is the single worst function in the codebase by every metric: 3,167 lines long, 12 levels of nesting at its deepest, ~486 b…”

   proof ↗⚑ flag

   Perplexity✓fullprobed8/10

   Perplexity documents an official `pplx` CLI that returns structured JSON from the Search API, explicitly designed for shell pipelines, terminal work, and coding agents, with an independent probe confirming the docs page exists. Missing for 10: independent hands-on community review of the CLI itself (evidence is entirely first-party docs/probe) and detail on install/auth flows.

   • [claimed-docs] “The pplx CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and co…”
   • [claimed-docs] “The `pplx` CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and …”
   • [claimed-docs] “The `pplx` CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and …”
   • [claimed-docs] “The `pplx` CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and …”
   • [probe] “official CLI documented at https://docs.perplexity.ai/docs/cli/overview”

   proof ↗⚑ flag

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

   weight 3 · round to Perplexity
   Claude~partialprobed3/10

   Evidence only hints at API-like surfaces (an Enterprise Compliance API for audit/chat data access, and references to using the Claude API/Console to power products) but never surfaces the actual general-purpose public API documentation for driving Claude's core capabilities; automated probes for an OpenAPI/swagger spec on the docs site returned 404s. Missing for 10: direct citation of the main Claude API reference docs, authentication/quickstart guides, and confirmation of comprehensive public API coverage beyond compliance/audit data.

   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access.”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”
   • [claimed-docs] “You can use the prompt improver in the Claude Console to automatically adapt prompts that were originally written for other AI models.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

   Perplexity✓fullprobed9/10

   Perplexity publishes a documented public API (Agent API, Search API, embeddings) with an OpenAPI spec, supports structured output, model fallback, sandbox tool use, and profiles, plus a CLI and MCP integrations for programmatic/agentic access, confirmed by both docs and live probes returning valid OpenAPI/docs endpoints. Missing for 10: independent third-party developer corroboration of API reliability/robustness in production use.

   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer”
   • [claimed-docs] “Structured output makes the model return JSON that conforms to a schema you define, so you can deserialize it directly.”
   • [claimed-docs] “Model fallback enables specifying multiple models in a `models` array. The API tries each model in order until one succeeds, providing autom…”
   • [claimed-docs] “A profile is a reusable, versioned configuration that you save and manage.”
   • [claimed-docs] “The pplx CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and co…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.perplexity.ai/llms.txt # Perplexity > Perplexity API documentation for building with the Agent API…”
   • [probe] “official CLI documented at https://docs.perplexity.ai/docs/cli/overview”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   No evidence describes scoped or least-privilege API credential issuance for agents; enterprise features mention audit logs and compliance API access but nothing about creating scoped/restricted API keys or credentials for agent use. Missing for 10: any documentation of API key scoping, permission tiers, or least-privilege credential management for agents.

   ⚑ flag

   Perplexity—none0/10

   The evidence pack covers API endpoints, MCP servers, CLI, and browser/app features, but contains no mention of API key scoping, granular permissions, or least-privilege credential issuance for agents. This is a fair capability to expect from an API platform, so absence of evidence means 'none' rather than 'na'.

   ⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to Perplexity
   Claude—none0/10

   The evidence pack covers Claude's consumer/enterprise features (Cowork, Projects, connectors, MCP, Chrome extension, file handling) but contains no documentation of official language SDKs (e.g., Python/TypeScript client libraries) for building applications against the Claude API. Missing for 10: any first-party SDK docs, API reference, or code samples showing programmatic API usage.

   ⚑ flag

   Perplexity~partialprobed4/10

   Perplexity documents a REST-based Agent API with an OpenAI-compatible endpoint and publishes an openapi.json spec, which supports SDK-style integration, but there is no explicit evidence of first-party official SDK libraries (e.g., a Perplexity Python/Node/Go client package) in the pack. missing for 10: explicit official SDK packages/libraries, language-specific SDK docs, independent developer corroboration of SDK usage.

   • [claimed-docs] “Unified access to open-weight models hosted by Perplexity through one OpenAI-compatible endpoint.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Claude—none0/10

   No evidence pack item describes webhooks or event subscription mechanisms for Claude; the closest agentic integrations are MCP connectors and scheduled tasks, which are not webhook-based event subscriptions.

   ⚑ flag

   Perplexity—none0/10

   No evidence anywhere in the pack of a webhook subscription mechanism for events (e.g., completed jobs, search results, agent tasks); documentation covers APIs, CLI, MCP servers, and apps but no event-driven webhook system.

   ⚑ flag

Agentic features

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

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude can ingest user data (files, connectors to Gmail/Drive/Calendar, Projects knowledge bases) and generate AI-driven insights, analysis, visualizations, and reports directly from that data, including agentic multi-step research that synthesizes findings with citations. This is well documented across file analysis, Research mode, Cowork task automation, and artifact/document generation features. Missing for 10: independent hands-on benchmarking specifically validating insight quality/accuracy from user data (community evidence is mixed/general rather than about this specific data-insight capability).

   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”

   proof ↗⚑ flag

   Perplexity~partialcommunity4/10

   Perplexity's Assistant (drafting emails, scheduling, booking) and the browser extension's 'Contextual Understanding' (answers tied to current page/domain) and 'Your Library' (curation of past discoveries) show the product surfacing suggestions tied to a user's own activity/context, but there's no explicit feature for uploading or connecting personal datasets (docs, CRM, files) and generating proactive analytical insights from them — the core product is web search/answers, not user-data analytics. missing for 10: dedicated personal-data ingestion/analysis capability, proactive insight-generation dashboards, independent evidence these 'insights' features work well in practice (community reports flag research features stalling and answer quality issues).

   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “Your Library: More than search history, it's a curation of your discoveries.”
   • [claimed-docs] “Contextual Understanding: Get answers relevant to your current page or even specific to your current domain.”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

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

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork's scheduled tasks let users describe a task once and have Claude execute it autonomously on a recurring or on-demand basis, delivering finished outputs like reports and briefings without further user input, which directly matches background automation. Missing for 10: independent/hands-on verification of scheduled task reliability and no detail on failure handling or notification mechanisms.

   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “brings Claude Code's agentic capabilities to knowledge work beyond coding”

   proof ↗⚑ flag

   Perplexity—none0/10

   The evidence describes on-demand features (Assistant drafting emails/booking, Computer/MCP multi-step delegation, Agent API) that execute when invoked, but nothing documents scheduled, recurring, or persistent background automations that run autonomously without a user actively initiating each session. Missing for 10: any documented scheduling/trigger mechanism, recurring task execution, or evidence of an automation running unattended over time.

   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “Browser Control Computer includes a full cloud browser for tasks that go beyond search.”
   • [claimed-docs] “Give AI assistants the ability to complete real-world tasks using Perplexity Computer through the Model Context Protocol (MCP).”

   proof ↗⚑ flag

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

   weight 3 · round to Claude
   Claude✓fullclaimed9/10

   Claude's built-in Cowork feature explicitly lets users delegate multi-step tasks ('describe an outcome, step away, come back to finished work'), with agentic execution including browser/computer use, scheduling, and research that autonomously plans next steps. This is well-documented first-party functionality directly matching task delegation to a built-in assistant. Missing for 10: independent hands-on verification of Cowork's delegation reliability (community evidence covers Claude Code/coding use more than Cowork specifically).

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “brings Claude Code's agentic capabilities to knowledge work beyond coding”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”

   proof ↗⚑ flag

   Perplexity!disputedcontradicted5/10

   Perplexity ships a built-in 'Assistant' and 'Computer' agent that can draft emails, book reservations, browse the web, run code, and connect to 400+ services (perplexity-docs-9, -17, -19, -29, -30, -38), which is a genuine in-product delegation capability. However, hands-on community reports say the Computer/agentic research feature 'often fails to trigger via the UI, and when it does work, sessions frequently stall without returning an answer' (perplexity-comm-7), directly contradicting the vendor's smooth-delegation claims. Missing for 10: independent corroboration that the assistant reliably completes delegated multi-step tasks, and resolution of the reported stalling/failure-to-trigger issue.

   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “**Connect to 400+ services** through a managed connector framework with one-click OAuth”
   • [claimed-docs] “Browser Control Computer includes a full cloud browser for tasks that go beyond search.”
   • [claimed-docs] “When a task requires interacting with a website, filling forms, or accessing login-gated content, Computer launches a browser session automa…”
   • [claimed-docs] “Give AI assistants the ability to complete real-world tasks using Perplexity Computer through the Model Context Protocol (MCP).”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

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

   weight 2 · round to Claude
   Claude✓fullcommunity9/10

   Claude's entire interface is natural-language chat/voice, and documentation shows this extends to agentic actions—generating files, browsing/clicking the web, using the computer, scheduling recurring tasks, and building artifacts—all triggered by describing the desired outcome in plain language (claude-docs-4,6,7,15,37,38,54). Community evidence corroborates real-world agentic use (claude-comm-1,10,12), though some report friction with CLI usability. Missing for 10: independent benchmark of NL command reliability across all surfaces, and no rebuttal to the CLI unresponsiveness anecdote being addressed.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “build tools, visualizations, and experiences by simply describing what you need”
   • [community] “I've been running Opus 4.8 for agentic coding and I don't see it being significantly better than Sonnet 4.5. I find that pairing Google Gemi…”
   • [community] “Anecdotal, but it 1 shot fixed a UI bug that neither Opus 4.5/Codex 5.2-high could fix.”
   • [community] “Claude is significantly better than other models at code assistant tasks, or at least in the way I use it.”

   proof ↗⚑ flag

   Perplexity!disputedcontradicted6/10

   Perplexity's core product is a natural-language chat/search interface (voice and text queries, cited answers) and its 'Assistant'/Computer agent claims to handle draft emails, scheduling, and multi-step web tasks purely via NL commands. However, hands-on community reports say the agentic 'Computer' research feature frequently fails to trigger via the UI and stalls without returning results, directly contradicting the docs' claims of reliable NL-driven task execution. missing for 10: independent verification that the Assistant reliably completes booking/scheduling tasks, and resolution of the reported reliability failures.

   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “**Connect to 400+ services** through a managed connector framework with one-click OAuth”
   • [claimed-docs] “· Voice: Instant, up-to-date answers whether you type or say it.”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round to Perplexity
   Claude—none0/10

   This evidence pack is entirely about Claude's consumer/product features (Cowork, connectors, memory, artifacts, etc.); there is no evidence of an interactive API reference with runnable examples. The probe explicitly found no OpenAPI spec at the checked endpoints, and no docs page describing an interactive API playground is present.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.claude.com/en/.md”

   proof ↗⚑ flag

   Perplexity~partialprobed4/10

   Perplexity publishes a machine-readable OpenAPI spec (openapi.json) and structured API docs (quickstart, building-agents guides) that would typically power an interactive reference, but the evidence pack never explicitly shows a 'try it' playground or runnable code examples within the docs UI. missing for 10: explicit interactive 'try it now' console screenshots/docs, confirmation of runnable code snippets executed in-browser, independent user report of using the interactive reference.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.perplexity.ai/llms.txt # Perplexity > Perplexity API documentation for building with the Agent API…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.perplexity.ai/docs/getting-started/overview.md > ## Documentation Index > Fetch the complete documen…”

   proof ↗⚑ flag

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

   weight 2 · round to Perplexity
   Claude—none0/10

   The evidence pack includes explicit probes checking for a machine-readable API spec (openapi.json, swagger.json, etc.) on Claude's support domain, all returning 404, and no docs item anywhere references an OpenAPI/Swagger spec or downloadable schema for the Claude API. Nothing in the docs list an API reference format for AI-native consumption.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.claude.com/en/.md”

   proof ↗⚑ flag

   Perplexity✓fullprobed9/10

   A probe confirms a live, machine-readable OpenAPI spec at https://docs.perplexity.ai/openapi.json returning HTTP 200 with an 'openapi' key, alongside an llms.txt documentation index, directly satisfying the story. Missing for 10: independent/community confirmation of the spec's completeness or usage in the wild.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.perplexity.ai/llms.txt # Perplexity > Perplexity API documentation for building with the Agent API…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.perplexity.ai/docs/getting-started/overview.md > ## Documentation Index > Fetch the complete documen…”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round drawn
   Claude—none0/10

   The evidence pack shows Claude's connectors, Cowork, computer use, and browser automation acting directly on real accounts (Gmail, Drive, live websites) with no mention of a sandbox, staging, or test-mode environment that isolates actions from production data.

   ⚑ flag

   Perplexity—none0/10

   Evidence only shows a code-execution sandbox (isolated Linux container) used by Perplexity's agent/Computer tools for running code within an answer, not a separate staging/test environment that lets a developer exercise the Perplexity API or product without touching live production data or billing. No mention of test API keys, staging endpoints, or a sandbox mode for the platform itself.

   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer”
   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “Computer can: **Search and browse** the web for real-time information, including login-gated pages * **Write and execute code** in an intera…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack covers Claude's consumer features, connectors, Cowork, and MCP integrations, but contains no mention of API versioning schemes or a documented deprecation policy for any Claude/Anthropic API. Since Claude does expose developer-facing APIs (e.g., for Console, Claude Code, MCP), this axis is applicable, but no evidence supports it.

   ⚑ flag

   Perplexity—none0/10

   Evidence shows Perplexity has an API with an OpenAPI spec and 'versioned' profiles for agent configurations, but nothing documents API version numbering or a deprecation/sunset policy for endpoints or models. Missing for 10: explicit API versioning scheme (e.g., v1/v2 paths), documented deprecation/sunset timeline, and any changelog or migration guide referenced in the evidence pack.

   • [claimed-docs] “A profile is a reusable, versioned configuration that you save and manage.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.perplexity.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

Agent mode

1. power-userDelegate a multi-step task that the assistant works on autonomously in the background and returns for my review

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork is documented as letting users describe a multi-step outcome, step away, and return to finished work, with scheduled/recurring tasks and background agentic execution (browser/computer use, file generation) explicitly designed for delegation and later review. Missing for 10: independent hands-on validation of Cowork's reliability/quality for complex delegated tasks and clearer detail on review/approval workflow beyond docs.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “This article explains how to use Claude Cowork, which brings Claude Code's agentic capabilities to knowledge work beyond coding.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”

   proof ↗⚑ flag

   Perplexity!disputedcontradicted5/10

   Perplexity's 'Computer' (Labs/Assistant) is documented as an autonomous background agent that can browse the web, execute code, use 400+ connectors, and complete tasks like drafting emails or booking reservations, returning structured results — matching the delegate-and-review story (perplexity-docs-9,10,17-19,29,30,38). However, a hands-on community report says the Computer/research feature 'often fails to trigger via the UI, and when it does work, sessions frequently stall without returning an answer,' directly contradicting reliable autonomous completion (perplexity-comm-7). missing for 10: independent corroboration that Computer reliably completes tasks and returns results, resolution of the reported stalling/failure-to-trigger issue.

   • [claimed-docs] “Through the Model Context Protocol, your MCP client can delegate complex, multi-step work to Computer and receive structured results.”
   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “Perplexity Labs: Bring your reports and projects to life faster than ever before.”
   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “**Connect to 400+ services** through a managed connector framework with one-click OAuth”
   • [claimed-docs] “Browser Control Computer includes a full cloud browser for tasks that go beyond search.”
   • [claimed-docs] “When a task requires interacting with a website, filling forms, or accessing login-gated content, Computer launches a browser session automa…”
   • [claimed-docs] “Give AI assistants the ability to complete real-world tasks using Perplexity Computer through the Model Context Protocol (MCP).”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

2. power-userHave the assistant operate a web browser on my behalf to research and complete tasks on websites

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude has multiple documented browser-control capabilities: the built-in browser in Cowork that opens sites, reads pages, clicks, types, and fills forms autonomously (claude-docs-6/67), the Claude in Chrome extension that reads/clicks/navigates websites (claude-docs-63), and computer-use navigation for on-screen actions (claude-docs-7/22/59), enabling research and task completion on websites. Missing for 10: independent hands-on validation of browser-task success rates and reliability under real-world site complexity.

   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to swit”
   • [claimed-docs] “Claude in Chrome is a browser extension that allows Claude to read, click, and navigate websites alongside you.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Perplexity!disputedcontradicted5/10

   Perplexity documents a 'Computer' agent with a full cloud browser that can search, browse, fill forms, and access login-gated pages, launched automatically for such tasks and accessible via MCP (perplexity-docs-17, -29, -30, -38) — squarely matching the story. However, hands-on community reporting says this same 'Computer' feature 'often fails to trigger via the UI, and when it does work, sessions frequently stall without returning an answer' (perplexity-comm-7), directly contradicting reliable operation. missing for 10: independent corroboration that browser automation completes tasks reliably, and no rebuttal to the stall/failure reports.

   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “Browser Control Computer includes a full cloud browser for tasks that go beyond search.”
   • [claimed-docs] “When a task requires interacting with a website, filling forms, or accessing login-gated content, Computer launches a browser session automa…”
   • [claimed-docs] “Give AI assistants the ability to complete real-world tasks using Perplexity Computer through the Model Context Protocol (MCP).”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

3. power-userLet the assistant see and operate applications on my computer to complete work

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork/computer use lets Claude navigate directly to the user's screen—clicking, typing, opening apps, filling forms—while the user watches, plus a built-in browser for opening sites and interacting with pages, directly matching the story of operating applications to complete work. Community evidence corroborates agentic coding/task use though notes mixed quality perceptions unrelated to this specific capability. Missing for 10: independent hands-on verification of computer-use reliability/accuracy and broader third-party benchmarking beyond vendor docs.

   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to swit”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Claude in Chrome is a browser extension that allows Claude to read, click, and navigate websites alongside you.”

   proof ↗⚑ flag

   Perplexity!disputedcontradicted4/10

   Perplexity's 'Computer' (via MCP) and Assistant app claim to browse the web, execute code in a sandbox, connect to 400+ services, and perform tasks like booking/scheduling — a form of 'operate applications' — but this is a cloud browser/sandbox, not literal control of apps on the user's own computer, and community hands-on reports say the Computer research feature 'often fails to trigger via the UI, and when it does work, sessions frequently stall without returning an answer.' This directly contradicts the vendor's claims of reliable task completion. missing for 10: evidence of actually operating local desktop applications (not just cloud browser/sandbox), reliability data contradicting the stalling reports, independent success case studies.

   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “Computer can: **Search and browse** the web for real-time information, including login-gated pages * **Write and execute code** in an intera…”
   • [claimed-docs] “**Connect to 400+ services** through a managed connector framework with one-click OAuth”
   • [claimed-docs] “Browser Control Computer includes a full cloud browser for tasks that go beyond search.”
   • [claimed-docs] “When a task requires interacting with a website, filling forms, or accessing login-gated content, Computer launches a browser session automa…”
   • [claimed-docs] “Give AI assistants the ability to complete real-world tasks using Perplexity Computer through the Model Context Protocol (MCP).”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

Tasks

1. power-userSchedule recurring or one-off tasks that run automatically and come back to me with results

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork explicitly supports scheduled tasks that run on a recurring or one-off basis and deliver finished outputs like reports and summaries back to the user, matching the story closely. Missing for 10: independent/hands-on validation of scheduling reliability and no detail on notification/delivery mechanisms beyond docs.

   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Perplexity—none0/10

   Evidence shows search, Q&A, Computer/MCP agent capabilities, and an Assistant that can draft emails or book reservations, but nothing describes a mechanism for scheduling recurring or one-off tasks that run automatically in the background and return results later. Community evidence even notes the 'Computer' research feature often fails to trigger or stalls without returning an answer, but there's no documented scheduling/task-runner feature at all.

   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “Browser Control Computer includes a full cloud browser for tasks that go beyond search.”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

Apps

1. power-userUse an official desktop app with OS-level shortcuts and access to what is on my screen

   weight 2 · round to Claude
   Claude~partialclaimed5/10

   Claude ships an official desktop app (Mac, Windows, Linux via apt) and a Cowork/computer-use feature that lets Claude 'navigate to your screen directly—clicking, typing, and opening apps' while the user watches, which shows real screen access. However there is no evidence of dedicated OS-level keyboard shortcuts (e.g., a global hotkey to invoke Claude with current screen context) — the screen access described is agentic task automation rather than a power-user shortcut workflow. Missing for 10: documented OS-level global shortcuts/hotkeys, and evidence that a user can quickly summon Claude to see the current screen via keypress rather than launching a Cowork/computer-use task.

   • [claimed-docs] “you can install Claude Desktop from Anthropic's apt repository rather than as a downloaded .deb file so that updates arrive through your sys…”
   • [claimed-docs] “The Claude desktop apps bring Claude's capabilities directly to your computer, allowing for seamless integration with your workflow.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “This article explains how to use Claude Cowork, which brings Claude Code's agentic capabilities to knowledge work beyond coding.”

   proof ↗⚑ flag

   Perplexity—none0/10

   The evidence pack only documents Perplexity's mobile apps (iOS/Android), a Chrome browser extension, a CLI, and MCP/API integrations — none describe an official desktop app with OS-level keyboard shortcuts or screen-content access.

   • [claimed-docs] “Perplexity Pro Search & Deep Research: Guided AI search for deeper exploration.”
   • [claimed-docs] “Instant Page Summaries: Make sense of any article or webpage at a glance.”
   • [claimed-docs] “This free app syncs across devices and leverages the power of the top AI models from OpenAI, Anthropic, Meta, and more.”
   • [claimed-docs] “The pplx CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and co…”

   proof ↗⚑ flag

2. knowledge-workerUse full-featured official mobile apps for iOS and Android

   weight 2 · round drawn
   Claude✓fullclaimed8/10

   Official iOS and Android apps are documented (App Store install instructions, Chrome/mobile chat parity across web/iOS/Android/desktop, voice mode explicitly available on Claude Mobile), indicating full-featured mobile apps rather than a bare wrapper. Missing for 10: no independent hands-on review of mobile app feature parity/quality, and no detail on which advanced features (Cowork, computer use) are available on mobile vs desktop-only.

   • [claimed-docs] “You can install the Claude app onto your iOS device by navigating to the App Store and searching for “Claude by Anthropic””
   • [claimed-docs] “You can install the Claude app onto your iOS device by navigating to the App Store and searching for "Claude by Anthropic"”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop ... Memory across conversations”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop”
   • [claimed-docs] “Voice mode is a beta feature available to all plans (Free, Pro, Max, Team, and Enterprise) on Claude Mobile (iOS and Android), Claude Deskto…”

   proof ↗⚑ flag

   Perplexity✓fullclaimed8/10

   Perplexity has official iOS and Android apps (App Store and Play Store listings) with a broad feature set: Pro Search/Deep Research, Assistant tasks, voice, citations, library/history sync across devices, and cross-model access — indicating full-featured rather than bare-bones apps. Missing for 10: independent hands-on app-store review/rating evidence and no direct community commentary specifically on mobile app quality (community feedback cited is about the web/desktop product and Computer feature, not mobile apps specifically).

   • [claimed-docs] “Perplexity Pro Search & Deep Research: Guided AI search for deeper exploration.”
   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “Perplexity Labs: Bring your reports and projects to life faster than ever before.”
   • [claimed-docs] “Voice: Instant, up-to-date answers whether you type or say it.”
   • [claimed-docs] “Trust Built In: Cited sources for every answer.”
   • [claimed-docs] “Your Library: More than search history, it's a curation of your discoveries.”
   • [claimed-docs] “Discover: Learn new things from the community.”
   • [claimed-docs] “This free app syncs across devices and leverages the power of the top AI models from OpenAI, Anthropic, Meta, and more.”
   • [claimed-docs] “Cut through the clutter and get straight to credible, up-to-date answers.”
   • [claimed-docs] “Thread Follow-Ups: Keep the conversation going for a deeper understanding.”

   proof ↗⚑ flag

Custom bots

1. power-userBuild and share custom assistants with their own instructions and knowledge

   weight 2 · round to Claude
   Claude~partialclaimed6/10

   Claude supports Projects (self-contained workspaces with custom knowledge bases/files) and Skills (teach Claude repeatable instructions like brand guidelines), which together let a power-user build a persona-like assistant with instructions and knowledge; Projects can be shared with team members. However, there's no dedicated 'custom GPT'-style public sharing/marketplace for assistants, and no independent evidence of end-to-end sharing outside an org. missing for 10: evidence of public/marketplace sharing of custom assistants, explicit persona/system-instruction configuration UI, and independent hands-on confirmation of building and sharing such assistants.

   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows”
   • [claimed-docs] “Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelin…”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”

   proof ↗⚑ flag

   Perplexity—none0/10

   The evidence pack covers Perplexity's search products, apps, CLI, MCP servers, and Agent API (including 'profiles' as reusable API configs), but nothing describes a user-facing feature for building a custom assistant with its own persistent instructions plus an attached knowledge base that can be shared with others (e.g., a Spaces/custom-GPT-like capability).

   ⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack documents agentic task automation (Cowork, scheduled tasks, Research) and single-document file handling, but no feature is described for processing or acting on many items at once (e.g., batch file processing, bulk edit across records, or a batch API). Automation-depth stories like this are plausible for Claude given its agentic tooling, but nothing in the pack shows bulk/multi-item operation support.

   ⚑ flag

   Perplexity—none0/10

   No evidence of a batch/bulk API, batch endpoint, or multi-item processing mode; the CLI and Agent API are described as single-call/pipeline-oriented tools that a user could script externally, but Perplexity itself does not document any bulk-operation capability.

   • [claimed-docs] “The `pplx` CLI returns structured JSON from the Perplexity Search API, making it useful for shell pipelines, interactive terminal work, and …”
   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to Claude
   Claude~partialclaimed4/10

   Claude Cowork supports scheduled/recurring tasks that run automatically on a time-based schedule or on demand (claude-docs-38, claude-docs-58), which is a form of automation, but there's no evidence of user-defined rules triggered by external events (e.g., 'when an email arrives' or 'when a file changes, do X') as opposed to calendar/time-based scheduling. missing for 10: event-driven trigger conditions (webhooks, connector-based event listeners), a rules engine for conditional automation, and any documentation of non-time-based triggers.

   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Perplexity—none0/10

   No evidence of a rules/trigger/automation engine (event-based conditions triggering actions) anywhere in the docs — Perplexity's evidence covers search, chat, APIs, MCP/Computer agent tasks, and CLI, but nothing about defining persistent rules that fire automatically on events.

   ⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork explicitly supports scheduled recurring tasks, letting users describe a workflow once and have Claude execute it automatically on a recurring or on-demand basis, delivering outputs like reports and briefings — this directly matches the story. Missing for 10: independent/hands-on verification of scheduling reliability and details on scheduling granularity/limits beyond vendor docs.

   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”

   proof ↗⚑ flag

   Perplexity—none0/10

   No evidence of scheduling, cron-like triggers, or recurring workflow automation anywhere in the docs, apps, or API references; the Agent API, CLI, MCP servers, and assistant features described are all single-invocation or on-demand tools with no persistent job scheduler.

   ⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round to Perplexity
   Claude—none0/10

   No evidence describes versioning, reviewing, or rolling back automations like scheduled Cowork tasks or Skills; docs cover creating/scheduling tasks but not history, diffs, or rollback capability.

   ⚑ flag

   Perplexity~partialclaimed3/10

   The Agent API's 'profiles' feature is described as a reusable, versioned configuration that can be saved and managed, offering a thin sliver of version control for automation configs, but there is no documented review workflow or rollback mechanism for automations. missing for 10: rollback/restore functionality, review/diff UI, versioning for Computer/MCP-based automations, evidence of actual usage beyond a single doc line.

   • [claimed-docs] “A profile is a reusable, versioned configuration that you save and manage.”

   proof ↗⚑ flag

Connectors

1. power-userBrowse a directory of third-party apps and connectors and add them to the assistant

   weight 2 · round to Claude
   Claude✓fullclaimed9/10

   Claude documents a unified directory that brings skills, connectors, and plugins together in one place to find and install everything that customizes Claude, plus specific connectors like Google Workspace and remote/local MCP servers to extend the assistant. Missing for 10: no independent hands-on review confirming the browsing/discovery UX of the directory itself.

   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “installing and managing local MCP servers has become significantly easier... install local MCP servers on your computer as easily as browser…”
   • [claimed-docs] “you can now install local MCP servers on your computer as easily as browser extensions”
   • [claimed-docs] “You can: Connect Claude to existing remote MCP servers. Build your own remote MCP servers to connect with any tool.”

   proof ↗⚑ flag

   Perplexity~partialclaimed4/10

   Docs mention Perplexity's Computer feature can 'connect to 400+ services through a managed connector framework with one-click OAuth,' implying a connector catalog exists, but there is no evidence of an actual browsable directory UI, categories, or user-facing app marketplace, and no independent/hands-on confirmation of this experience. Missing for 10: dedicated connector/app directory UI evidence, list of example connectors, independent user reports of browsing/adding connectors.

   • [claimed-docs] “**Connect to 400+ services** through a managed connector framework with one-click OAuth”
   • [claimed-docs] “Give AI assistants the ability to complete real-world tasks using Perplexity Computer through the Model Context Protocol (MCP).”

   proof ↗⚑ flag

2. knowledge-workerConnect my cloud drive, email, and calendar so the assistant can search and use them in answers

   weight 3 · round to Claude
   Claude✓fullclaimed9/10

   Claude has a documented Google Workspace connector letting users connect Gmail, Google Calendar, and Google Drive so Claude can search emails, manage calendar, and work with documents/files directly in conversation, plus a privacy commitment not to train on this data. This directly satisfies the story's cloud drive/email/calendar connection use case. Missing for 10: no independent hands-on report corroborating real-world reliability of these specific connectors.

   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”

   proof ↗⚑ flag

   Perplexity~partialcommunity5/10

   Perplexity's Computer/MCP docs claim a 'managed connector framework' connecting to 400+ services via one-click OAuth, and the Assistant feature claims it can draft emails and schedule appointments, which implies email/calendar integration, but no evidence names specific connectors like Google Drive, Gmail, or Google/Outlook Calendar, nor shows search results being grounded in those personal sources. Community reports also note the 'Computer' feature (where this connector framework lives) often fails to trigger via the UI and stalls without returning an answer, raising doubts about reliability. Missing for 10: named cloud-drive/email/calendar connector examples, documentation of how connected-source data is surfaced in answers, and independent confirmation the connector framework works reliably.

   • [claimed-docs] “**Connect to 400+ services** through a managed connector framework with one-click OAuth”
   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “· Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

Analysis

1. power-userHave the assistant write and run code on my data to produce charts, computed answers, and downloadable files

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Docs explicitly describe generating downloadable Excel/PowerPoint/Word/PDF files, producing reports with charts and visualizations, and using artifacts to build code-driven visualizations and interactive components from uploaded data files (CSV, XLSX, etc.). This directly matches the power-user story of writing/running code on data to produce charts, computed answers, and downloadable outputs. missing for 10: independent/hands-on community corroboration specifically validating the data-analysis/code-execution-to-chart workflow (community evidence in the pack focuses on coding agent quality, not this analysis feature).

   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”
   • [claimed-docs] “Generate code and visualize data”
   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”
   • [claimed-docs] “Claude can work with the following document types: PDF DOCX CSV TXT HTML ODT RTF EPUB JSON XLSX”
   • [claimed-docs] “Common examples of artifact content include: Documents (Markdown or plain text) - Code snippets ... Interactive React components”
   • [claimed-docs] “Common examples of artifact content include: - Documents (Markdown or plain text) - Code snippets - Single-page HTML websites - SVG images -…”
   • [claimed-docs] “Artifacts allow you to turn ideas into shareable apps, tools, or content—build tools, visualizations, and experiences by simply describing w…”
   • [claimed-docs] “build tools, visualizations, and experiences by simply describing what you need”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”

   proof ↗⚑ flag

   Perplexity!disputedcontradicted4/10

   Perplexity documents a code-execution sandbox (Computer MCP / Agent API 'sandbox' tool) that can write and run Python/Node code and return outputs, and Labs is pitched for 'reports and projects,' suggesting some support for computing answers/files from data. However, hands-on community reporting says the 'Computer' feature 'often fails to trigger via the UI, and when it does work, sessions frequently stall without returning an answer,' directly contradicting reliable delivery of this workflow. missing for 10: explicit evidence of chart generation, working with user-uploaded datasets, downloadable file outputs, and independent confirmation the sandbox reliably works in the consumer product.

   • [claimed-docs] “Computer can: Search and browse the web for real-time information, including login-gated pages; Write and execute code in an interactive Lin…”
   • [claimed-docs] “Computer can: **Search and browse** the web for real-time information, including login-gated pages * **Write and execute code** in an intera…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer”
   • [claimed-docs] “Perplexity Labs: Bring your reports and projects to life faster than ever before.”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”

   proof ↗⚑ flag

Artifacts

1. knowledge-workerHave the assistant create and iteratively edit documents, presentations, and other files I can export

   weight 2 · round to Claude
   Claude✓fullclaimed9/10

   Docs explicitly describe generating and editing Excel, PowerPoint, Word, and PDF files via natural-language prompts, plus Artifacts for documents/code/interactive content that can be iteratively refined and downloaded, and uploading/persisting files in Projects for ongoing editing. Missing for 10: independent hands-on review confirming export fidelity/iteration quality across file types.

   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”
   • [claimed-docs] “Common examples of artifact content include: Documents (Markdown or plain text) - Code snippets ... Interactive React components”
   • [claimed-docs] “Common examples of artifact content include: - Documents (Markdown or plain text) - Code snippets - Single-page HTML websites - SVG images -…”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”
   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”

   proof ↗⚑ flag

   Perplexity~partialclaimed3/10

   Perplexity Labs is described as helping 'bring your reports and projects to life,' hinting at document/report generation, but the evidence pack gives no detail on iterative editing, presentation creation, or exporting files to common formats. Missing for 10: iterative document/presentation editing workflow, export format support (PDF/DOCX/PPT), and any independent confirmation these outputs are usable/editable.

   • [claimed-docs] “Perplexity Labs: Bring your reports and projects to life faster than ever before.”

   proof ↗⚑ flag

Files

1. knowledge-workerUpload documents, spreadsheets, and PDFs and get accurate analysis of their contents

   weight 3 · round to Claude
   Claude✓fullclaimed9/10

   Docs confirm Claude supports uploading PDFs, DOCX, CSV, XLSX, TXT, HTML, ODT, RTF, EPUB, JSON, with analysis of both text and visual elements in PDFs up to 100 pages, plus persistent Project file storage for cross-conversation reference and generation of derived documents/reports. Missing for 10: independent hands-on benchmarking of analysis accuracy across large/complex spreadsheets or long PDFs beyond the 100-page limit.

   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”
   • [claimed-docs] “Claude can work with the following document types: PDF DOCX CSV TXT HTML ODT RTF EPUB JSON XLSX”
   • [claimed-docs] “Claude analyzes both text and visual elements (like images, charts, and graphics) in PDFs of 100 pages or fewer”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”

   proof ↗⚑ flag

   Perplexity—none0/10

   The evidence pack contains no mention of document, spreadsheet, or PDF upload/analysis features anywhere in Perplexity's docs, API, CLI, MCP server, or app store listings — coverage focuses on web search, citations, sandboxed code execution, and browser automation. Missing for 10: any documentation of file/PDF/spreadsheet upload, parsing, or analysis capability, and any user or hands-on evidence of accurate document Q&A.

   ⚑ flag

Memory

1. power-userHave the assistant remember relevant context from previous chats and apply it in new conversations

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude has explicit first-party memory/chat-search docs: it can search previous conversations and "remember context from your chats and carry it into new conversations and Cowork tasks," plus a dedicated article on how memory works, what's remembered, and how to review/edit it; the product page also advertises "Memory across conversations" as a core feature. This directly matches the story of remembering context across chats and applying it in new ones. Missing for 10: independent/hands-on corroboration of memory quality or limitations in practice beyond vendor docs.

   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop ... Memory across conversations”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Claude can also remember context from your chats and carry it into new conversations and Cowork tasks.”

   proof ↗⚑ flag

   Perplexity—none0/10

   Evidence shows only within-conversation context ('conversation context across turns', 'Thread Follow-Ups') and a searchable history/library, but no documented feature where the assistant recalls or applies context from previous separate chats into new conversations. Missing for 10: any explicit cross-session memory feature, opt-in/opt-out memory controls, or evidence of persisted user facts being reused in new threads.

   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”
   • [claimed-docs] “Thread Follow-Ups: Keep the conversation going for a deeper understanding.”
   • [claimed-docs] “Your Library: More than search history, it's a curation of your discoveries.”

   proof ↗⚑ flag

2. power-userSet persistent custom instructions and preferences that shape every response

   weight 1 · round to Claude
   Claude~partialclaimed6/10

   Claude supports persistent memory/context (chat search and memory, Projects with knowledge bases, custom instructions implied via Skills and Projects) that carries into new conversations, but there is no explicit documented feature for setting global 'custom instructions' that shape every response the way ChatGPT's system prompt does. missing for 10: dedicated persistent custom-instructions/preferences UI applying to all chats, independent/hands-on verification that memory reliably shapes every response, and clarity on scope/limits of what's remembered.

   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Claude can also remember context from your chats and carry it into new conversations and Cowork tasks.”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelin…”

   proof ↗⚑ flag

   Perplexity~partialclaimed3/10

   The only related evidence is the Agent API 'profiles' feature (a reusable, versioned configuration you save and manage), which could function as persistent settings shaping responses, but this is a developer/API concept, not documented as a consumer-facing custom-instructions or persona feature. Missing for 10: explicit evidence of user-facing custom instructions/preferences in the consumer app, confirmation that profiles persist across all conversations/responses, and independent corroboration of this working as claimed.

   • [claimed-docs] “A profile is a reusable, versioned configuration that you save and manage.”
   • [claimed-docs] “Your Library: More than search history, it's a curation of your discoveries.”

   proof ↗⚑ flag

Projects

1. knowledge-workerOrganize related chats and files into a project or space that shares context and instructions

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Projects docs confirm self-contained workspaces with shared chat histories and knowledge bases, persistent file uploads scoped to a project for cross-conversation reference, and memory/chat search to build on prior context. missing for 10: no evidence of custom instructions/system prompt configuration per project beyond files, and no independent/hands-on corroboration of the project workflow in practice.

   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop ... Memory across conversations”

   proof ↗⚑ flag

   Perplexity—none0/10

   The evidence pack mentions a 'Library' for curating search history but nothing about a 'Spaces'/'Projects' feature that groups chats and files with shared context or custom instructions, which is the core of this story. Missing for 10: any mention of collections/spaces, file upload grounding within a project, or persistent custom instructions per project.

   ⚑ flag

Images

1. knowledge-workerGenerate and edit images from natural-language prompts

   weight 2 · round to Claude
   Claude~partialclaimed4/10

   Claude can understand and analyze uploaded/pasted images (JPEG, PNG, GIF, WebP) and can produce SVG images, diagrams, and flowcharts as artifacts from natural-language descriptions, but there is no evidence of true raster image generation or photo-editing capability comparable to dedicated image models. Editing of generated visual artifacts is possible via iterative prompting, but this is limited to code-rendered graphics rather than general image generation/editing. Missing for 10: dedicated raster image-generation model, photo editing/inpainting features, and any independent confirmation of image-generation quality.

   • [claimed-docs] “Common examples of artifact content include: - Documents (Markdown or plain text) - Code snippets - Single-page HTML websites - SVG images -…”
   • [claimed-docs] “Claude analyzes both text and visual elements (like images, charts, and graphics) in PDFs of 100 pages or fewer”
   • [claimed-docs] “Claude supports the following image formats: - JPEG - PNG - GIF - WebP”
   • [claimed-docs] “You can also copy images and paste them from your clipboard into Claude”
   • [claimed-docs] “build tools, visualizations, and experiences by simply describing what you need”

   proof ↗⚑ flag

   Perplexity—none0/10

   The evidence pack shows Perplexity is focused on web-grounded search, citations, code sandboxes, MCP/CLI integrations, and browser automation via 'Computer,' but contains no mention of image generation or editing capabilities from natural-language prompts anywhere in the docs, app store listings, or community reports.

   ⚑ flag

2. knowledge-workerShare screenshots and photos and have the assistant accurately interpret what is in them

   weight 2 · round to Claude
   Claude✓fullclaimed7/10

   Claude's docs confirm native image upload/paste support (JPEG, PNG, GIF, WebP) and clipboard paste, plus PDF analysis that includes visual elements like images and charts, directly supporting screenshot/photo interpretation for knowledge workers. Missing for 10: independent/hands-on evidence validating accuracy of image interpretation, and no explicit mention of screenshot-specific use cases (e.g., UI screenshots, photos of documents) beyond general image/PDF support.

   • [claimed-docs] “Claude analyzes both text and visual elements (like images, charts, and graphics) in PDFs of 100 pages or fewer”
   • [claimed-docs] “Claude supports the following image formats: - JPEG - PNG - GIF - WebP”
   • [claimed-docs] “You can also copy images and paste them from your clipboard into Claude”
   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”

   proof ↗⚑ flag

   Perplexity—none0/10

   The evidence pack contains no mention of image/screenshot upload or visual interpretation capability anywhere in the docs, app store listings, or API references—only text search, voice, browsing, and coding features are described.

   ⚑ flag

Voice

1. knowledge-workerHave a natural, real-time voice conversation with the assistant

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude ships an explicit Voice mode enabling complete spoken conversations, available across web, desktop, iOS and Android, positioned to work best on phone. Missing for 10: independent hands-on reviews of voice latency/naturalness and confirmation it's out of beta.

   • [claimed-docs] “Voice mode allows you to have complete spoken conversations with Claude.”
   • [claimed-docs] “Voice mode is a beta feature available to all plans (Free, Pro, Max, Team, and Enterprise) on Claude Mobile (iOS and Android), Claude Deskto…”

   proof ↗⚑ flag

   Perplexity~partialclaimed4/10

   Perplexity's mobile app docs mention a 'Voice' feature ('Instant, up-to-date answers whether you type or say it'), indicating voice input/output exists, but there's no evidence describing a natural, continuous, real-time back-and-forth voice conversation mode (like a dedicated voice-chat UI) or its quality/latency. Missing for 10: details on conversational turn-taking, interruption handling, voice mode UX specifics, and independent hands-on validation of voice conversation quality.

   • [claimed-docs] “Voice: Instant, up-to-date answers whether you type or say it.”
   • [claimed-docs] “· Voice: Instant, up-to-date answers whether you type or say it.”

   proof ↗⚑ flag

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

   weight 2 · round to Perplexity
   Claude—none0/10

   The evidence pack details many UI-exclusive Claude.ai features (Cowork, voice mode, computer use, memory/chat search, artifacts, browser extension, scheduled tasks) but contains no documentation that these capabilities are exposed through the Claude API, nor any statement of API/UI feature parity. Enterprise API mentions are limited to a Compliance API for logs, not general feature parity.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Voice mode allows you to have complete spoken conversations with Claude.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”

   proof ↗⚑ flag

   Perplexity~partialclaimed5/10

   The API/Agent API exposes web-grounded search, citations, sandboxed code execution, structured output, model fallback, and CLI/MCP integrations, covering much of what the UI offers, but UI-only consumer features like Assistant task automation (email drafting, scheduling, reservations), Voice, Library/Discover, and browser extension page-context features have no documented API equivalents. missing for 10: API parity for Assistant actions (email/scheduling/booking), Voice interface, Library/Discover/curation features, browser-extension contextual page understanding, and independent confirmation that all UI capabilities are API-accessible.

   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”
   • [claimed-docs] “The `sandbox` tool gives the agent an isolated Linux container to run real code and use the output in its answer”
   • [claimed-docs] “Structured output makes the model return JSON that conforms to a schema you define, so you can deserialize it directly.”
   • [claimed-docs] “Model fallback enables specifying multiple models in a `models` array. The API tries each model in order until one succeeds, providing autom…”
   • [claimed-docs] “Assistant: Draft emails, schedule appointments, book reservations, and more.”
   • [claimed-docs] “Voice: Instant, up-to-date answers whether you type or say it.”
   • [claimed-docs] “Your Library: More than search history, it's a curation of your discoveries.”
   • [claimed-docs] “Discover: Learn new things from the community.”
   • [claimed-docs] “Contextual Understanding: Get answers relevant to your current page or even specific to your current domain.”

   proof ↗⚑ flag

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

   weight 3 · round to Claude
   Claude~partialclaimed6/10

   Claude documents a data-export feature covering conversation and account data, letting users take their data with them ([claude-docs-12], [claude-docs-40]). However, there is no evidence specifying the export format is an open/standard one (e.g., JSON/portable), nor documentation of easy migration/interoperability with other tools, so the 'open format' and full portability aspects of the story are unconfirmed. missing for 10: explicit statement of open/standard export format, evidence of full interoperability/reuse elsewhere, and independent confirmation of export completeness.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”

   proof ↗⚑ flag

   Perplexity—none0/10

   No evidence of a data export/portability feature for user account data (chat history, library, settings) in open formats; the docs cover API access to models/search but nothing about exporting personal user data or account deletion workflows. missing for 10: any documented data export tool, format spec (JSON/CSV/etc.), or account-deletion-with-export flow.

   ⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round drawn
   Claude—none0/10

   Claude is closed-source; there is no evidence of an open-license source release for the model or app, and community evidence even criticizes it as closed/opaque compared to FOSS alternatives like Codex CLI (claude-comm-6).

   • [community] “Codex CLI is FOSS, unlike Claude Code, so Codex is less likely to do things like that, and it's one more reason to avoid Claude Code and Cla…”

   proof ↗⚑ flag

   Perplexity—none0/10

   Perplexity is a closed, proprietary product; the evidence pack shows API docs, apps, CLI, and MCP integrations but no mention of open-sourcing the product itself or any open-license source code repository.

   ⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   No evidence in the pack mentions data residency, regional storage options, or geographic controls for where account/chat data is stored; the closest items concern export, audit logs, and training opt-outs, none of which address residency choice.

   ⚑ flag

   Perplexity—none0/10

   No evidence in the pack mentions data residency, regional storage options, or any user-selectable region controls; Perplexity's docs focus on models, search, MCP/CLI integrations, and app features but never address data storage location or residency choices.

   ⚑ flag

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

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude documents explicit user controls to prevent training use: incognito chats are never used to improve Claude even with Model Improvement enabled, users can toggle the 'Model Improvement' privacy setting, and connector data (Gmail/Drive/Calendar) is explicitly excluded from training. This directly satisfies the ai-native privacy-posture story of preventing data from being used for model training. Missing for 10: independent/third-party verification of these claims and explicit default policy for Enterprise/Team plans beyond connectors.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”

   proof ↗⚑ flag

   Perplexity—none0/10

   No evidence in the pack of any opt-out setting, privacy policy statement, or documented control letting users prevent their data from being used for AI training; the evidence pack only covers product features (search, CLI, MCP, browser extension) and unrelated community complaints about crawling/robots.txt behavior. Missing for 10: any documentation of a training opt-out toggle, privacy settings page, or data-use policy addressing model training.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude provides explicit user-facing data controls: exporting chat history/user data (claude-docs-12, 40), reviewing/editing/turning off memory (claude-docs-45), incognito chats excluded from training (claude-docs-46), and enterprise audit logs plus a compliance API for data governance (claude-docs-11, 44). Missing for 10: explicit self-service account/data deletion flow documentation and independent verification that deletion requests are honored.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”

   proof ↗⚑ flag

   Perplexity—none0/10

   The evidence pack contains no documentation of data retention settings, deletion controls, export options, or privacy dashboard features for Perplexity users; the only privacy-adjacent items concern the company's own web-crawling/robots.txt controversy, which is off-topic for user data control. This axis clearly applies to a consumer AI assistant, so absence of evidence yields 'none'.

   ⚑ flag

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

   weight 2 · round to Claude
   Claude~partialclaimed6/10

   Claude documents a 'Model Improvement' privacy setting that can be toggled off and 'incognito chats' that are excluded from training even if Model Improvement is enabled, giving users control over whether their conversations are used to improve the model (claude-docs-46, claude-docs-47). This addresses opt-out of usage-for-training, and data export/deletion options exist (claude-docs-12, claude-docs-40), but there is no explicit documentation of a broader telemetry/analytics opt-out (e.g., product usage metrics, crash reporting) beyond model-training data use. missing for 10: explicit telemetry/analytics tracking opt-out settings, independent confirmation that toggling actually stops all usage tracking, documentation of what non-training telemetry data is collected.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”

   proof ↗⚑ flag

   Perplexity—none0/10

   No evidence in the pack describes any telemetry opt-out, privacy settings, or usage-tracking controls; the community items discuss crawling/robots.txt disputes and product quality, not telemetry opt-out. Missing for 10: any documentation of a privacy settings page, data-collection opt-out toggle, or telemetry policy.

   ⚑ flag

Research

1. knowledge-workerLaunch a deep research run that autonomously searches many sources and returns a cited report

   weight 3 · round to Claude
   Claude✓fullcommunity8/10

   Claude's Research feature is well documented: it operates agentically running multiple searches that build on each other, determines what to investigate next, and delivers thorough answers in minutes with easy-to-check citations. Community evidence is mixed on research depth (some say it lags ChatGPT/Gemini), which caps quality but the core capability is clearly delivered. Missing for 10: independent hands-on benchmark showing citation accuracy/report quality, and clearer detail on breadth of sources searched.

   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [community] “Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the…”
   • [community] “Works pretty nicely for research still, not seeing a substantial qualitative improvement over Opus 4.5.”

   proof ↗⚑ flag

   Perplexity!disputedcontradicted5/10

   Perplexity's docs explicitly advertise 'Pro Search & Deep Research: Guided AI search for deeper exploration' with citations built into every answer, matching the story's core capability. However, hands-on community reports directly contradict reliable delivery: one user found citations/references 'frequently mismatched to the text' and quality declining over time, and another reports the 'Computer' research feature 'often fails to trigger via the UI, and when it does work, sessions frequently stall without returning an answer,' leading them to prefer other tools for actual research. Missing for 10: independent verification of successful autonomous multi-source runs, resolution of the stalling/citation-mismatch complaints, and clearer documentation distinguishing 'Deep Research' reliability from the separate 'Computer' agent.

   • [claimed-docs] “Perplexity Pro Search & Deep Research: Guided AI search for deeper exploration.”
   • [claimed-docs] “Features: · Perplexity Pro Search & Deep Research: Guided AI search for deeper exploration.”
   • [claimed-docs] “Trust Built In: Cited sources for every answer.”
   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”
   • [community] “User used a free 12-month Perplexity Pro offer: initially useful for quick queries like recipes or manuals, but quality declined as the comp…”
   • [community] “The 'Computer' research feature in Perplexity often fails to trigger via the UI, and when it does work, sessions frequently stall without re…”
   • [community] “For actual research, the user now prefers Claude or ChatGPT over Perplexity, saying results are higher quality and more accurate despite bei…”

   proof ↗⚑ flag

2. knowledge-workerGet answers grounded in current web results with citations back to the sources

   weight 2 · round to Claude
   Claude~partialcommunity7/10

   Claude's Research feature is documented to perform agentic multi-step web searches and deliver answers with 'easy-to-check citations' (claude-docs-20, 27, 39, 68), directly matching the story. However, independent community feedback suggests mixed real-world quality—commenters say Claude's general research 'is fine' but that ChatGPT and Gemini 'run circles around it' in depth and presentation (claude-comm-8, claude-comm-9), tempering confidence in how well-grounded/comprehensive the citations truly are. missing for 10: independent hands-on verification of citation accuracy/source quality, and confirmation research draws from live/current web data versus stale index.

   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [community] “Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the…”
   • [community] “Works pretty nicely for research still, not seeing a substantial qualitative improvement over Opus 4.5.”

   proof ↗⚑ flag

   Perplexity!disputedcontradicted5/10

   Perplexity's docs and consumer apps clearly document web-grounded answers with inline citations across the API, apps, and browser extension (perplexity-docs-2, -12, -24, -31), and this is a core, heavily marketed feature. However, hands-on community reports concretely contradict citation quality: users report citations/links frequently mismatched to the text and Perplexity citing AI-generated 'best software' listicle spam, undermining trust in the grounding (perplexity-comm-6, perplexity-comm-11), with some users switching to Claude/ChatGPT for research quality (perplexity-comm-9). missing for 10: independent verification that citation accuracy holds up at scale, and resolution of reported citation/source mismatch issues.

   • [claimed-docs] “Get web-grounded answers with built-in citations in one call, or access third-party models from OpenAI, Anthropic, Google, and xAI with web …”
   • [claimed-docs] “Trust Built In: Cited sources for every answer.”
   • [claimed-docs] “Cut through the clutter and get straight to credible, up-to-date answers.”
   • [claimed-docs] “Get accurate, up-to-date answers grounded in real-time web search, with inline citations in a single call, and conversation context across t…”
   • [community] “User used a free 12-month Perplexity Pro offer: initially useful for quick queries like recipes or manuals, but quality declined as the comp…”
   • [community] “For actual research, the user now prefers Claude or ChatGPT over Perplexity, saying results are higher quality and more accurate despite bei…”
   • [community] “Report claims Perplexity cites AI-generated 'best software' listicle sites en masse, raising concerns about it being manipulated by SEO/AEO …”

   proof ↗⚑ flag

Admin

1. team-adminManage members, permissions, and data policies for my organization's workspace

   weight 2 · round to Claude
   Claude~partialclaimed4/10

   Evidence confirms Enterprise plan admin/security features like audit logs and a Compliance API for programmatic access to usage data, implying some org-level governance, but there is no documentation of member management, role/permission assignment, or granular data policy controls for team admins. missing for 10: member invitation/removal workflows, role-based permission management, workspace-level data retention/policy settings, and independent corroboration of admin console functionality.

   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access.”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”

   proof ↗⚑ flag

   Perplexity—none0/10

   No evidence in the pack mentions team/workspace admin controls, member management, permission roles, or data policy settings; all evidence covers API features, apps, CLI, and MCP integrations. This is a fair axis for a team-oriented product like Perplexity (which offers Enterprise/Team plans), but absence of any admin-console or policy documentation means it cannot be credited.

   ⚑ flag

Data controls

1. knowledge-workerExport my complete chat history and account data

   weight 1 · round to Claude
   Claude✓fullclaimed9/10

   Claude's docs explicitly state individual users can export user information and chat history from Settings > Privacy, and that exports include both conversation data and account/user data; Enterprise adds a Compliance API for programmatic access to chat histories and file content. Missing for 10: independent/hands-on confirmation of export completeness or format details beyond first-party docs.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”

   proof ↗⚑ flag

   Perplexity—none0/10

   No evidence in the pack mentions a data export feature, account data download, or chat history export capability for Perplexity's consumer product; documentation focuses on API, MCP, CLI, and app features with no trust-controls/export functionality described.

   ⚑ flag

2. knowledge-workerControl whether my conversations are used to train models

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude provides explicit privacy controls: incognito chats are excluded from model training even with Model Improvement enabled, a 'Model Improvement' opt-in/out toggle exists, and connector data (Gmail/Drive/Calendar) is explicitly excluded from training. Missing for 10: independent/hands-on verification that the training opt-out is actually honored in practice, and clearer documentation of the toggle's exact location/scope for all plan tiers.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”

   proof ↗⚑ flag

   Perplexity—none0/10

   No evidence in the pack addresses privacy settings, opt-out of training, or data-usage controls for conversations; all citations concern product features (search, MCP, CLI, apps) or unrelated crawler/quality controversies. This axis applies to any consumer AI product handling user conversations, so absence of evidence yields 'none'.

   ⚑ flag