Perplexity vs Microsoft Copilot

Agent access

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

   weight 2 · round to Perplexity
   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

   Microsoft Copilot—none0/10

   Probes show no llms.txt, no markdown docs endpoint, and no OpenAPI spec for Microsoft Copilot's support site, and no evidence anywhere in the pack of agent-oriented documentation formats being offered. This axis applies (any product could publish llms.txt or agent-friendly docs) but there is no evidence Copilot does so.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Microsoft Copilot—none0/10

   The evidence pack describes Copilot connecting to first-party consumer services (OneDrive, Outlook.com, Google Drive/Gmail) via 'Copilot connectors,' but there is no mention of MCP (Model Context Protocol) server support or an ability for users to plug in arbitrary MCP tool servers. This is an applicable axis for an AI assistant product, but no evidence shows the capability exists.

   • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
   • [claimed-docs] “Copilot can connect with the following consumer services: Microsoft OneDrive, Microsoft Outlook.com (email, calendar, and contacts), Google …”
   • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”

   proof ↗⚑ flag

3. ai-native userUse an official CLI

   weight 2 · round to Perplexity
   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

   Microsoft Copilot—none0/10

   No evidence of an official CLI for Microsoft Copilot; all evidence covers chat, browser, and Office app integrations, with probes confirming no machine-readable API/CLI artifacts.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”

   proof ↗⚑ flag

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

   weight 3 · round to Perplexity
   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

   Microsoft Copilot—none0/10

   No evidence of a documented public API for programmatically driving Microsoft Copilot; probes for OpenAPI/llms.txt specs all returned 404, and all docs describe end-user chat/UI interactions rather than API access. Missing for 10: any public API documentation, SDK, or endpoint spec that lets developers programmatically invoke Copilot's capabilities.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   No evidence describes issuing scoped or least-privilege API credentials for an agent; Copilot's documented connectors involve OAuth-style account sign-in to consumer services, not developer-controlled scoped credential issuance. missing for 10: any mention of API keys, scoped tokens, permission scoping, or credential management for agent access.

   ⚑ flag

6. ai-native userBuild against official SDKs

   weight 2 · round to Perplexity
   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

   Microsoft Copilot—none0/10

   The evidence pack covers Microsoft Copilot as a consumer AI assistant with features like connectors, browsing, and app integrations, but contains no mention of official SDKs, developer APIs, or programmatic build tooling for third-party developers; probes for API/OpenAPI specs returned 404s, further indicating no discoverable developer SDK surface.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”

   proof ↗⚑ flag

7. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   No evidence anywhere in the pack of Copilot offering webhook subscriptions or any event-driven notification API for developers; probes for API/OpenAPI specs returned 404s, and docs only describe chat/connector features, not webhook subscription mechanisms.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Perplexity
   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

   Microsoft Copilot!disputedcontradicted5/10

   Microsoft heavily documents AI-generated insights across Word, Excel, PowerPoint, Outlook, Researcher, and Analyst, and describes proactive suggestions and code-run analysis (copilot-docs-2, copilot-docs-6, copilot-docs-16, copilot-docs-33, copilot-docs-31). However, hands-on community reports concretely contradict these claims for core products: a user found Copilot in Word 'couldn't do anything except append to the end of the document... couldn't create tables' (copilot-comm-4), and Outlook's summarization is described as 'so bad' with a tiny UI button (copilot-comm-5); others report never finding a use case (copilot-comm-9). One community report is positive about cross-document data fetching (copilot-comm-7), so evidence is genuinely mixed rather than uniformly negative. Missing for 10: independent benchmark of insight quality/accuracy, resolution of the Word/Outlook hands-on failures, and clearer distinction of chat vs. Office-integrated Copilot performance.

   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
   • [claimed-docs] “Go from raw numbers to real insight—use Analyst to help analyze data with ease.”
   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel. Detail your task, attach data, and tweak via chat.”
   • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
   • [claimed-docs] “Copilot can also run code to complete complex calculations and generate graphs.”
   • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
   • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”
   • [community] “the way it can fetch data from across documents in 365 is really good”
   • [community] “I use AI everyday and never found a use case for Copilot.”

   proof ↗⚑ flag

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

   weight 2 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialclaimed4/10

   Docs mention agentic-style capabilities (Cowork multi-step task completion, automating repetitive tasks, proactive research suggestions, browser action-taking) suggesting some autonomy, but Browse with Copilot explicitly requires user attention/supervision for many actions and no docs describe scheduled or fully background-running automations without a user session. Missing for 10: explicit scheduling/trigger mechanism, evidence of unattended background execution, and independent confirmation that these automations run without active supervision.

   • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
   • [claimed-docs] “Hand off repetitive work so you can focus on what matters.”
   • [claimed-docs] “A copilot can automate repetitive tasks, no coding required.”
   • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
   • [claimed-docs] “Copilot will ask for your attention and supervision for certain actions, such as buying an item, booking a reservation, sending an email, or…”

   proof ↗⚑ flag

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

   weight 3 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialcommunity6/10

   Microsoft's own docs describe extensive delegation features—Copilot in Word/Excel/PowerPoint/Outlook, Researcher, Analyst, Browse with Copilot performing multi-step browser actions, and Cowork handling 'bigger, multi-step tasks'—clearly positioning Copilot as a built-in assistant that can take on tasks. However, hands-on community reports contradict smooth delegation in practice (e.g., Copilot in Word 'couldn't do anything except append to the end of the document,' couldn't create tables or maintain formatting, and some users report never finding a real use case), indicating real-world task execution is often shallow or unreliable. Missing for 10: independent verification of successful complex multi-step task completion, and resolution of documented editing/execution failures in flagship apps.

   • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
   • [claimed-docs] “Go from prompt to presentation with Copilot in PowerPoint. Outline the flow, describe visuals, and generate.”
   • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
   • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
   • [claimed-docs] “A copilot can automate repetitive tasks, no coding required.”
   • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
   • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”
   • [community] “I use AI everyday and never found a use case for Copilot.”

   proof ↗⚑ flag

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

   weight 2 · round to Perplexity
   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

   Microsoft Copilot!disputedcontradicted5/10

   Docs extensively describe natural-language operation—prompting Copilot in Word/Excel/PowerPoint, natural-language file/email/calendar search, and browser action commands (copilot-docs-1,2,3,8,14,20-22,26,27). However, hands-on community evidence directly contradicts this for at least one core surface: a user reports Copilot in Word 'couldn't do anything except append to the end of the document... couldn't create tables! couldn't search and replace! couldn't maintain formatting' (copilot-comm-4), and others found the Outlook summarize feature and overall NL assistant underwhelming or unused (copilot-comm-5, copilot-comm-9). This is a concrete documented failure of the claimed NL command capability, not mere skepticism. Missing for 10: independent third-party benchmarking of NL command reliability across all Office apps, and resolution of the reported Word functional gaps.

   • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
   • [claimed-docs] “Find my budget spreadsheet” or “Show me the project plan from last month.”
   • [claimed-docs] “Find files quickly: "Find my budget spreadsheet" or "Show me the project plan from last month."”
   • [claimed-docs] “Find Word documents about vacation plans” or “Show me all PDFs.”
   • [claimed-docs] “Find emails: “Show me emails from Sarah about the budget” or “Find my flight confirmation email.””
   • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
   • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”
   • [community] “I use AI everyday and never found a use case for Copilot.”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round to Perplexity
   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

   Microsoft Copilot—none0/10

   No evidence of a machine-readable API spec; explicit probes for OpenAPI/swagger endpoints all returned 404, and no docs mention a public API or spec for Microsoft Copilot as an end-user product.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   Microsoft Copilot is presented here as a consumer-facing AI assistant product; there is no evidence of a public versioned API, developer API reference, or documented deprecation policy for it. Probes for API/OpenAPI specs and llms.txt all return 404, confirming absence of such developer-facing documentation.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”

   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 Microsoft Copilot
   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

   Microsoft Copilot~partialclaimed5/10

   Copilot's 'Cowork' feature is explicitly described as handling 'bigger, multi-step tasks and deliver completed to-dos,' and 'Browse with Copilot' can perform multi-step actions while pausing for user approval on sensitive steps, which aligns with delegate-and-review workflows. However, these are single thin doc mentions with no independent/hands-on validation of true background/asynchronous operation, and community feedback focuses on other Copilot surfaces (Word, Outlook) being underwhelming rather than confirming Cowork's autonomous task delivery. Missing for 10: hands-on or independent evidence of a background task actually running unattended and returning a completed result, clearer scope/limits of Cowork, and confirmation this isn't just synchronous chat-assisted editing.

   • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
   • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
   • [claimed-docs] “You can see each step in real time and take control at any time. All actions run locally in your browser, ensuring full visibility and contr…”
   • [claimed-docs] “You can see each step in real time and take control at any time.”
   • [claimed-docs] “Copilot will ask for your attention and supervision for certain actions, such as buying an item, booking a reservation, sending an email, or…”

   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 Microsoft Copilot
   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

   Microsoft Copilot~partialclaimed6/10

   Microsoft documents a dedicated 'Browse with Copilot' capability that lets Copilot click, type, and navigate tabs in Edge to complete web tasks, with real-time visibility and required user confirmation for sensitive actions like purchases or bookings, plus a 'Cowork' mode for multi-step task completion. However, all supporting evidence is first-party docs with no independent/hands-on confirmation of browser-operation success, and community feedback in the pack focuses on Office-integrated Copilot rather than this browsing agent feature. Missing for 10: independent/hands-on validation of the browse-and-complete-task capability, more detail on reliability/success rate on real websites.

   • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
   • [claimed-docs] “You can see each step in real time and take control at any time. All actions run locally in your browser, ensuring full visibility and contr…”
   • [claimed-docs] “You can see each step in real time and take control at any time.”
   • [claimed-docs] “Copilot will ask for your attention and supervision for certain actions, such as buying an item, booking a reservation, sending an email, or…”
   • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”

   proof ↗⚑ flag

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

   weight 2 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialcommunity6/10

   Microsoft documents 'Browse with Copilot' letting the assistant click, type, and navigate tabs directly in Edge, plus 'Cowork' for multi-step task completion and Vision for seeing images/screens, with human-in-the-loop confirmation for sensitive actions. However, this operating capability is scoped mainly to the browser and Office apps rather than general desktop application control, and community reports describe weak real-world execution (e.g., Copilot in Word failing at basic edits, Outlook integration being minimal), undercutting the strength of the claim. Missing for 10: broad OS-level/desktop app automation beyond Edge/Office, and independent hands-on validation that agentic actions reliably complete tasks.

   • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
   • [claimed-docs] “You can see each step in real time and take control at any time. All actions run locally in your browser, ensuring full visibility and contr…”
   • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
   • [claimed-docs] “Copilot will ask for your attention and supervision for certain actions, such as buying an item, booking a reservation, sending an email, or…”
   • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
   • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”

   proof ↗⚑ flag

Tasks

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   The evidence shows Copilot can handle multi-step tasks (Cowork) and automate repetitive work, but there is no mention of scheduling recurring or one-off tasks that run automatically and return results later. Missing for 10: any documentation of a task-scheduling feature, recurrence settings, or proactive notification of completed scheduled runs.

   • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
   • [claimed-docs] “Hand off repetitive work so you can focus on what matters.”
   • [claimed-docs] “A copilot can automate repetitive tasks, no coding required.”

   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 drawn
   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

   Microsoft Copilot—none0/10

   The evidence pack covers web/Office integrations, browser automation (Edge), and mobile/iOS/Android connectors, but nowhere documents an official standalone desktop app with OS-level keyboard shortcuts or the ability to see/interact with the user's screen content outside a browser. Vision (copilot-docs-30) is limited to photo/image analysis, not live screen capture, and Browse with Copilot (copilot-docs-9, -15, -24) is scoped to actions inside Microsoft Edge, not OS-wide screen access.

   • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
   • [claimed-docs] “You can see each step in real time and take control at any time. All actions run locally in your browser, ensuring full visibility and contr…”
   • [claimed-docs] “You can see each step in real time and take control at any time.”
   • [claimed-docs] “See and understand. Use Vision to analyze images, get insights from photos, and search visually.”

   proof ↗⚑ flag

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

   weight 2 · round to Perplexity
   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

   Microsoft Copilot~partialclaimed6/10

   Docs explicitly confirm 'Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)', establishing official iOS/Android apps exist and support core connector/chat features. However, there's no first-party or hands-on evidence detailing mobile-specific feature parity (e.g., Word/Excel/PowerPoint copilots, Vision, voice mode) on the mobile apps, and community feedback focuses only on desktop/Office integration quality, not mobile experience. Missing for 10: mobile-specific feature parity details, hands-on mobile app reviews, and confirmation of full functionality (Vision, Voice, connectors) actually working within the mobile app UI.

   • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”
   • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
   • [claimed-docs] “If users send prompts in natural language voice within the Copilot Voice mode, they will receive audio responses.”
   • [claimed-docs] “See and understand. Use Vision to analyze images, get insights from photos, and search visually.”

   proof ↗⚑ flag

Custom bots

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   No evidence describes creating custom Copilot agents/assistants with custom instructions and knowledge base (like Copilot Studio agents or GPT-builder equivalents) nor sharing them with others; evidence only covers built-in Office integrations, connectors, and memory features. Missing for 10: any mention of an agent/assistant builder, custom instructions, custom knowledge upload, and sharing/publishing mechanism for user-built assistants.

   ⚑ flag

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

   weight 2 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialcommunity3/10

   Docs mention general automation of 'repetitive tasks' and multi-step task completion via Cowork, but there's no concrete evidence of bulk operations across many items (e.g., batch-editing many files, mass email actions, or large-scale spreadsheet manipulation). Community feedback (copilot-comm-4) reports Copilot in Word failing at basic single-document tasks like search-and-replace, casting doubt on any claim of robust bulk-item processing. missing for 10: explicit bulk/batch operation examples (e.g., mass-processing many files/rows/emails at once), independent hands-on evidence of successful bulk actions, and confirmation that Cowork or Analyst can operate at scale across many items reliably.

   • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
   • [claimed-docs] “Hand off repetitive work so you can focus on what matters.”
   • [claimed-docs] “A copilot can automate repetitive tasks, no coding required.”
   • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Microsoft Copilot—none0/10

   The evidence describes Copilot responding to prompts, browsing, summarizing, and connecting to services, but there is no mention of user-defined rules or triggers that fire actions automatically on events (e.g., 'when email arrives, do X' style automation). No scheduling, event-trigger, or workflow-builder capability is documented.

   ⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   No evidence describes scheduling recurring jobs, timers, or automated recurring workflows in Microsoft Copilot; the pack shows one-off task automation (Cowork, connectors, browse actions) but nothing about recurrence or scheduling.

   ⚑ flag

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

   weight 1 · round to Perplexity
   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

   Microsoft Copilot—none0/10

   No evidence describes any versioning, history, review workflow, or rollback capability for Copilot's automations (e.g., Cowork, connectors, or agent tasks); evidence only covers connecting services, browsing, memory, and privacy controls. Missing for 10: version history UI, diff/review of automation changes, rollback/undo mechanism, any audit trail for automation edits.

   ⚑ flag

Connectors

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

   weight 2 · round drawn
   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

   Microsoft Copilot~partialclaimed4/10

   Docs confirm Copilot supports 'connectors' to a small fixed list of services (OneDrive, Outlook.com, Google Drive, Gmail/Calendar/Contacts) and note these are available on Copilot.com/Mobile, but there is no evidence of a browsable directory/marketplace of third-party apps that power-users can explore and add beyond this short built-in list. missing for 10: evidence of a searchable app/connector marketplace, breadth of third-party (non-Microsoft/Google) integrations, and any independent confirmation of the browsing/add experience.

   • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
   • [claimed-docs] “Copilot can connect with the following consumer services: Microsoft OneDrive, Microsoft Outlook.com (email, calendar, and contacts), Google …”
   • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”
   • [claimed-docs] “Copilot can connect with the following consumer services: ... Google Drive ... Google Gmail, Calendar, Contacts”
   • [claimed-docs] “Copilot can connect with the following consumer services: Microsoft OneDrive... Google Drive... Google Gmail, Calendar, Contacts”

   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 Microsoft Copilot
   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

   Microsoft Copilot✓fullcommunity8/10

   Microsoft's documentation explicitly describes connecting Copilot to OneDrive, Outlook.com (email/calendar/contacts), Google Drive, and Google Gmail/Calendar/Contacts, with example queries for finding files, emails, and calendar events, indicating the assistant can search and use this data in answers. Community evidence corroborates that cross-document/data fetching works well in some contexts, though other complaints focus on unrelated feature quality issues (e.g., editing limitations) rather than disputing the connector capability itself. Missing for 10: independent hands-on verification specifically of the cloud-drive/email/calendar connector search feature (rather than in-app Office Copilot) and more detail on reliability/completeness of search results.

   • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
   • [claimed-docs] “Find my budget spreadsheet” or “Show me the project plan from last month.”
   • [claimed-docs] “Copilot can connect with the following consumer services: Microsoft OneDrive, Microsoft Outlook.com (email, calendar, and contacts), Google …”
   • [claimed-docs] “Find files quickly: "Find my budget spreadsheet" or "Show me the project plan from last month."”
   • [claimed-docs] “Find Word documents about vacation plans” or “Show me all PDFs.”
   • [claimed-docs] “Show me emails from Sarah about the budget” or “Find my flight confirmation email.”
   • [claimed-docs] “What's on my calendar for tomorrow?” or “When is my next dentist appointment?”
   • [claimed-docs] “Find emails: “Show me emails from Sarah about the budget” or “Find my flight confirmation email.””
   • [claimed-docs] “Check in on your calendar: “What’s on my calendar for tomorrow?” or “When is my next dentist appointment?””
   • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”
   • [community] “the way it can fetch data from across documents in 365 is really good”

   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 Microsoft Copilot
   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

   Microsoft Copilot~partialclaimed6/10

   Docs explicitly state Copilot can 'run code to complete complex calculations and generate graphs' and the 'Analyst' feature 'analyzes data with ease,' plus Excel/Word integrations for working with attached data—covering charts and computed answers. However, there is no explicit documentation of producing downloadable files as an output of this code-execution flow, and no hands-on/community evidence corroborates this specific capability working well (community comments focus on other Office Copilot shortcomings, not code-execution). Missing for 10: explicit downloadable-file output evidence, independent/hands-on confirmation of the code-execution feature itself.

   • [claimed-docs] “Copilot can also run code to complete complex calculations and generate graphs.”
   • [claimed-docs] “Go from raw numbers to real insight—use Analyst to help analyze data with ease.”
   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel. Detail your task, attach data, and tweak via chat.”
   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”

   proof ↗⚑ flag

Artifacts

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

   weight 2 · round to Perplexity
   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

   Microsoft Copilot!disputedcontradicted4/10

   Microsoft's own docs claim Copilot in Word/Excel/PowerPoint can create and iteratively refine documents, spreadsheets, and presentations via chat (copilot-docs-1,2,3,16), which would let users export finished files. However, a hands-on community report directly contradicts this for Word, stating Copilot 'couldn't do anything except append to the end of the document,' couldn't create tables, search/replace, or maintain formatting (copilot-comm-4), and another user calls Outlook's summarize feature 'so bad' (copilot-comm-5). This is a concrete documented capability failure, not mere skepticism. Missing for 10: independent corroboration of successful iterative multi-turn editing, PowerPoint/Excel hands-on validation, and confirmation of clean export/formatting fidelity.

   • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
   • [claimed-docs] “Go from prompt to presentation with Copilot in PowerPoint. Outline the flow, describe visuals, and generate.”
   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel. Detail your task, attach data, and tweak via chat.”
   • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
   • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”

   proof ↗⚑ flag

Files

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

   weight 3 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialcommunity6/10

   Microsoft's own docs describe multiple file-analysis capabilities—attaching data in Excel, analyzing notes in Word, finding/searching PDFs and Office documents, an 'Analyst' tool for data insight, and code execution for calculations—giving broad first-party coverage of the story. However, hands-on community reports contradict smooth real-world usability (e.g. Word Copilot 'couldn't do anything except append text... couldn't maintain formatting' and Outlook summarization deemed 'so bad'), while another user praises cross-document data-fetching, so the accuracy/quality of analysis is mixed rather than assured. Missing for 10: independent verification of analysis accuracy on complex spreadsheets/PDFs, and resolution of the documented Word-editing/formatting failures.

   • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
   • [claimed-docs] “Go from raw numbers to real insight—use Analyst to help analyze data with ease.”
   • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel. Detail your task, attach data, and tweak via chat.”
   • [claimed-docs] “Find Word documents about vacation plans” or “Show me all PDFs.”
   • [claimed-docs] “Copilot can also run code to complete complex calculations and generate graphs.”
   • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
   • [community] “the way it can fetch data from across documents in 365 is really good”

   proof ↗⚑ flag

Memory

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

   weight 3 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialclaimed6/10

   First-party docs confirm a memory feature: Copilot can store facts users ask it to remember and use that context in future responses, and can proactively surface suggestions based on past queries and memory (copilot-docs-32, copilot-docs-33). However, this is opt-in/explicit fact storage rather than full automatic context carry-over, and there is no independent/hands-on evidence confirming it works reliably across conversations. missing for 10: independent verification of cross-conversation recall, detail on scope/limits of automatic memory use, and confirmation it isn't just facts explicitly asked to be remembered.

   • [claimed-docs] “Copilot can store specific facts users request it to remember, allowing it to generate more relevant responses and suggestions based on that…”
   • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
   • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”

   proof ↗⚑ flag

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

   weight 1 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialclaimed5/10

   Docs confirm a memory feature where Copilot can store facts users ask it to remember and use them to personalize future responses and suggestions, plus controls to view/delete memory (copilot-docs-32, copilot-docs-33, copilot-docs-38). However there is no dedicated 'custom instructions' setting described (unlike explicit persona/tone controls), and no independent/hands-on evidence confirming these stored facts consistently shape *every* response. Missing for 10: explicit custom-instructions UI documentation, hands-on confirmation that memory reliably influences all responses, and community corroboration of the feature's effectiveness.

   • [claimed-docs] “Copilot can store specific facts users request it to remember, allowing it to generate more relevant responses and suggestions based on that…”
   • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
   • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
   • [claimed-docs] “opt out of use of your conversation activity for model training”

   proof ↗⚑ flag

Projects

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   The evidence pack shows Copilot memory (storing facts), connectors to files/email/calendar, and per-app integrations, but nowhere describes a 'project' or 'space' concept that lets a user group related chats and files together with shared instructions/context, unlike competitors' project/space features. Community feedback focuses on integration quality issues, not on organizational/workspace features. Missing for 10: any documented 'project', 'space', 'workspace', or chat-grouping feature with shared custom instructions and file scoping.

   • [claimed-docs] “Copilot can store specific facts users request it to remember, allowing it to generate more relevant responses and suggestions based on that…”
   • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
   • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”

   proof ↗⚑ flag

Images

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   The evidence pack only shows Copilot's 'Vision' feature for analyzing and understanding images (copilot-docs-30), not generating or editing images from text prompts; no docs, community, or probe evidence mentions an image-generation or image-editing capability (e.g., a Designer/DALL·E-style feature).

   • [claimed-docs] “See and understand. Use Vision to analyze images, get insights from photos, and search visually.”

   proof ↗⚑ flag

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

   weight 2 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialclaimed5/10

   Docs confirm Copilot has a 'Vision' capability to analyze images and photos ([copilot-docs-30]), directly supporting the story, but this is a single first-party mention with no elaboration on screenshot-specific use cases or accuracy, and no independent/hands-on evidence corroborates real-world interpretation quality. Missing for 10: detailed documentation on screenshot vs photo handling, accuracy benchmarks, and independent/community verification of correct image interpretation.

   • [claimed-docs] “See and understand. Use Vision to analyze images, get insights from photos, and search visually.”

   proof ↗⚑ flag

Voice

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

   weight 2 · round to Microsoft Copilot
   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

   Microsoft Copilot✓fullclaimed6/10

   Microsoft's transparency docs explicitly describe Copilot Voice mode: users send natural-language voice prompts and receive audio responses, with citations shown in conversation transcripts, confirming real-time spoken interaction. Missing for 10: independent/hands-on corroboration of voice mode's real-time quality, latency, or interruption handling, and no community evidence specifically validates or disputes the voice experience.

   • [claimed-docs] “If users send prompts in natural language voice within the Copilot Voice mode, they will receive audio responses.”
   • [claimed-docs] “This means that Copilot centers its response on high-ranking content from the web and provides hyperlinked citations following generated tex…”

   proof ↗⚑ flag

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

   weight 2 · round to Perplexity
   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

   Microsoft Copilot—none0/10

   No evidence of a public API exposing Copilot's UI capabilities (chat, connectors, Word/Excel/PowerPoint copilots) programmatically; probes for OpenAPI/docs endpoints returned 404s, and all evidence describes UI/chat-only functionality. Missing for 10: any documented API/SDK, endpoint parity documentation, or third-party confirmation of programmatic access to Copilot features.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
   • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
   • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Microsoft Copilot—none0/10

   No evidence of a data export/portability feature or open-format export mechanism; docs only mention deleting conversation history, not exporting it, and probes for machine-readable docs/APIs 404. There is nothing showing users can export chats, memory, or generated content in open formats to leave the platform.

   • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
   • [claimed-docs] “opt out of use of your conversation activity for model training”
   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   Microsoft Copilot is closed-source proprietary software; no evidence indicates any open-license source availability, and probes for docs/API artifacts returned 404s. This is an applicable axis (a product could conceivably be open-sourced) but no evidence supports it, so verdict is none rather than na.

   • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”

   proof ↗⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Perplexity—none0/10

   Perplexity is offered exclusively as a hosted SaaS (web app, mobile apps, browser extension, cloud API/CLI/MCP) with no evidence of any self-hostable core product, open-source release, or on-prem deployment option.

   ⚑ flag

   Microsoft Copilot—none0/10

   Microsoft Copilot is a cloud-hosted SaaS product with no evidence of any self-hosted or on-premises deployment option; all documentation describes it as a hosted service (Copilot.com, Microsoft 365 cloud integration, Edge browser actions) with no self-hosting mechanism mentioned.

   ⚑ flag

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   No evidence in the pack mentions data residency, regional storage controls, or any user-facing setting to choose where data is stored; the docs cover features, connectors, and privacy opt-outs but not geographic data residency choices.

   ⚑ flag

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

   weight 3 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialcommunity6/10

   Microsoft's privacy FAQ explicitly states users can opt out of having conversation activity used for model training and can delete conversation history (copilot-docs-35, copilot-docs-36, copilot-docs-38), giving a documented mechanism to prevent training use. However, community reports (copilot-comm-6, copilot-comm-1) show real confusion about scope — a user working in Word had no clear indication whether their document content was being fed to training, and commenters note the opt-out/behavior differs between standalone Copilot chat and 365-integrated Copilot, undermining confidence that the control is comprehensive or transparent across all surfaces. missing for 10: independent verification that opt-out actually blocks training across all integrated products (Word/Excel/Outlook), clearer UI-level opt-out controls inside Office apps, and confirmation the toggle covers enterprise/connector data sources.

   • [claimed-docs] “opt out of use of your conversation activity for model training”
   • [claimed-docs] “Train our generative AI models to create a better experience for you and others.”
   • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
   • [community] “When CoPilot showed up in my Word, I was writing a pitch doc... It made me realize I didn't know whether this doc was getting auto-pushed to…”
   • [community] “To be clear this is only for the standalone Copilot chat or app and website; not for the 'Copilot' services integrated into Office 365 etc.”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialcommunity6/10

   Docs confirm users can delete individual conversations or entire history and opt out of conversation data being used for model training, giving basic retention/deletion control for the standalone Copilot chat experience (copilot-docs-35, copilot-docs-38). However, community evidence notes this applies only to the standalone Copilot app/site, not to Copilot embedded in Office apps like Word, where a user reported uncertainty about whether their document was being auto-pushed for training with no visible deletion controls (copilot-comm-1, copilot-comm-6). Missing for 10: enterprise/Office-integrated retention controls, clarity on data retention duration before deletion, and independent verification that deletion actually removes data from training pipelines.

   • [claimed-docs] “opt out of use of your conversation activity for model training”
   • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
   • [community] “To be clear this is only for the standalone Copilot chat or app and website; not for the 'Copilot' services integrated into Office 365 etc.”
   • [community] “When CoPilot showed up in my Word, I was writing a pitch doc... It made me realize I didn't know whether this doc was getting auto-pushed to…”

   proof ↗⚑ flag

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

   weight 2 · round to Microsoft Copilot
   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

   Microsoft Copilot!disputedcontradicted5/10

   Microsoft's own privacy FAQ states users can opt out of having conversation activity used for model training and can delete individual or entire conversation history (copilot-docs-35, copilot-docs-38), which is a real opt-out mechanism for the standalone Copilot chat. However, community reports directly contradict this for Copilot as embedded in Office apps: a Word for Mac user reports 'no way of turning it off' and 'no opt-out mechanism' (copilot-comm-3), and another user reports uncertainty over whether their document was being auto-pushed to Copilot for training with no visible control (copilot-comm-6) — and copilot-comm-1 clarifies the training opt-out only applies to the standalone chat app, not the Office-integrated Copilot surfaces. Missing for 10: a unified, product-wide opt-out control covering all Copilot surfaces (Office, Edge, Windows), independent verification that the training opt-out actually stops data use, and clarity on telemetry beyond training data.

   • [claimed-docs] “opt out of use of your conversation activity for model training”
   • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
   • [community] “To be clear this is only for the standalone Copilot chat or app and website; not for the 'Copilot' services integrated into Office 365 etc.”
   • [community] “Hate that if you use Word for Mac, you now have Copilot next to your cursor with no way of turning it off. I just want to use Word... Now th…”
   • [community] “When CoPilot showed up in my Word, I was writing a pitch doc... It made me realize I didn't know whether this doc was getting auto-pushed to…”

   proof ↗⚑ flag

Research

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

   weight 3 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialclaimed5/10

   Copilot's 'Researcher' agent is documented as designed to 'find, synthesize, and understand information faster' and Copilot's web-grounded answers include hyperlinked citations, which maps to the deep-research/cited-report story, but there is no detail on autonomous multi-source search depth, report format, or any hands-on/independent validation of report quality. Missing for 10: documentation of the autonomous multi-step search process, description of report output structure, and independent corroboration of research depth/accuracy.

   • [claimed-docs] “Find, synthesize, and understand information faster with Researcher.”
   • [claimed-docs] “This means that Copilot centers its response on high-ranking content from the web and provides hyperlinked citations following generated tex…”
   • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”

   proof ↗⚑ flag

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

   weight 2 · round to Microsoft Copilot
   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

   Microsoft Copilot✓fullclaimed8/10

   Docs explicitly state Copilot grounds responses in high-ranking web content and provides hyperlinked citations after generated responses, directly matching the story; this is corroborated by broader documentation on research/answer features (Researcher, ask questions and get answers fast). Missing for 10: independent hands-on verification of citation accuracy/quality and no community evidence specifically testing web-grounded citation behavior.

   • [claimed-docs] “This means that Copilot centers its response on high-ranking content from the web and provides hyperlinked citations following generated tex…”
   • [claimed-docs] “Ask questions and get answers fast.”
   • [claimed-docs] “Find, synthesize, and understand information faster with Researcher.”

   proof ↗⚑ flag

Admin

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

   weight 2 · round drawn
   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

   Microsoft Copilot—none0/10

   The evidence pack covers only individual/consumer Copilot features (writing, spreadsheets, browsing, memory, privacy opt-outs for personal conversations) with no mention of team/workspace admin controls such as member management, role-based permissions, or organizational data policies. Missing for 10: admin console documentation, member/role management, org-wide data governance policies, and any evidence of a team-admin experience.

   ⚑ flag

Data controls

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

   weight 1 · round drawn
   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

   Microsoft Copilot—none0/10

   Evidence shows users can delete individual conversations or entire history (copilot-docs-38) and opt out of training use (copilot-docs-35), but there is no mention of an export/download feature for complete chat history or account data as required by the story.

   • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
   • [claimed-docs] “opt out of use of your conversation activity for model training”

   proof ↗⚑ flag

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

   weight 3 · round to Microsoft Copilot
   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

   Microsoft Copilot~partialcommunity6/10

   Microsoft's own docs confirm a control exists: users can opt out of conversation activity being used for model training and can delete conversation history (copilot-docs-35, copilot-docs-36, copilot-docs-38). However, community evidence indicates confusion about scope—one commenter notes the opt-out applies to standalone Copilot chat/app, not to Copilot embedded in Office apps like Word (copilot-comm-1), and another user reports genuine uncertainty whether their Word document was being used for training with no clear indication (copilot-comm-6). Missing for 10: clear unified documentation covering training-data opt-out scope across all Copilot surfaces (Office-integrated vs standalone), and independent verification that the opt-out setting functions as described.

   • [claimed-docs] “opt out of use of your conversation activity for model training”
   • [claimed-docs] “Train our generative AI models to create a better experience for you and others.”
   • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
   • [community] “To be clear this is only for the standalone Copilot chat or app and website; not for the 'Copilot' services integrated into Office 365 etc.”
   • [community] “When CoPilot showed up in my Word, I was writing a pitch doc... It made me realize I didn't know whether this doc was getting auto-pushed to…”

   proof ↗⚑ flag