Reflect vs Poly

Agent access

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

   weight 2 · round to Poly
   Reflect—none0/10

   There's no llms.txt (404 confirmed by probe) and no agent-oriented documentation aimed at AI agents; Reflect's docs are human-facing product docs, not machine-consumable agent instructions.

   • [probe] “PROBE llms.txt: HTTP 404 at https://reflect.academy/llms.txt”

   proof ↗⚑ flag

   Poly✓fullprobed9/10

   Poly directly serves an llms.txt with a full agent-oriented documentation index, confirmed live via runtime probe (HTTP 200, structured docs list, companion llms-full.txt, /raw/*.md mirrors of every page), explicitly designed for agent consumption alongside CLI and MCP integration docs. Missing for 10: no independent third-party report of an agent actually using llms.txt to onboard, only first-party docs and probes.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.poly.app/llms.txt # docs.poly.app > Poly documentation ## Documentation Sets - [docs.poly.app](h…”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”
   • [claimed-docs] “Import your existing files from Google Drive, Dropbox, iCloud, or your local machine.”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   Reflect—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Poly~partialprobed4/10

   The `poly` CLI is explicitly described as 'scriptable from the terminal' (poly-docs-17) and supports commands like `poly search` (poly-docs-6), suggesting scriptable automation is possible, and the MCP server exists for programmatic agent access (poly-probe-rt-2). However, both the CLI and MCP server rely on browser-based OAuth authentication (poly-probe-rt-2), which is a significant barrier to headless/CI use, and there is no documentation of API keys, service accounts, or CI-specific setup for non-interactive automation. Missing for 10: documented headless/non-interactive auth method (API key or service token), explicit CI/automation examples or docs, evidence of running without a browser session.

   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Reflect—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Poly—none0/10

   All MCP-related evidence describes Poly exposing its own hosted MCP server (mcp.poly.app) for external AI assistants like Claude Code, Codex, ChatGPT, etc. to consume — i.e., Poly acting as the MCP *server* — not Poly acting as an MCP *client* that can plug in and use tools from third-party MCP servers. No documentation, CLI reference, or probe shows Poly's built-in agent connecting to or consuming external MCP servers.

   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 3 · round to Poly
   Reflect—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Poly✓fullprobed9/10

   Poly documents and runtime-verifies an official hosted MCP server (mcp.poly.app/mcp) with OAuth auth, exposing search/fetch/CLI tools, and it's usable from Claude Code, ChatGPT, Codex, Gemini, and other MCP clients. missing for 10: independent third-party (non-vendor) confirmation of a successful end-to-end agent connection beyond the probe and docs.

   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round to Poly
   Reflect—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Poly✓fullprobed8/10

   Poly ships a documented official CLI (`poly`) with 25+ commands for searching, reading, creating, and organizing files from the terminal, plus an agent-skill that composes CLI commands, confirmed by both docs and a runtime probe. missing for 10: independent/hands-on community verification of the CLI itself (community evidence discusses filesystem access concerns, not CLI usage) and no visible changelog/versioning depth for the CLI beyond docs.

   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “The [`poly-cli` agent skill] teaches an agent how to search, read, create, update, and organize your Poly files by composing `poly` commands…”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”

   proof ↗⚑ flag

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

   weight 3 · round to Poly
   Reflect~partialprobed6/10

   Reflect documents a public REST API with OAuth2 (including PKCE) authentication for building third-party clients, and a runtime probe confirms the API endpoint is live and enforces auth as documented. However the API is explicitly limited to appending data and listing bookmarked links (not full CRUD due to E2E encryption), and there is no formal OpenAPI/swagger spec or llms.txt discoverability (both probed and returned 404s). Missing for 10: comprehensive OpenAPI/swagger schema, broader read/write API coverage beyond append-only actions, official SDKs, and machine-readable API discovery file.

   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://reflect.academy/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://reflect.academy/openapi.json, https://reflect.academy/swagger.json, https://reflect.academy/…”

   proof ↗⚑ flag

   Poly~partialprobed7/10

   Poly documents a CLI (`poly` with 25+ commands) and a hosted MCP server (https://mcp.poly.app/mcp with OAuth) that let AI agents and assistants drive file search, read, write, and organization programmatically, confirmed by both docs and a live runtime probe. However, there is no conventional public REST/OpenAPI API — probes for openapi.json/swagger.json all returned 404 — so agentic access is limited to MCP/CLI surfaces rather than a general-purpose documented API. missing for 10: a REST/OpenAPI-documented API, independent third-party corroboration of API usage beyond vendor docs.

   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Reflect—none0/10

   Reflect's API docs describe OAuth2 with PKCE (no secret keys needed) for authenticating a client, but there is no mention of scopes, granular permissions, or the ability to issue least-privilege credentials limited to specific actions/data for an agent — the API is described as a general append/list interface, not a scoped credentialing system.

   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”

   proof ↗⚑ flag

   Poly—none0/10

   Poly's MCP/agent integrations use a single OAuth login granting 'full access to your Poly files' (poly-docs-30, poly-docs-29) rather than any scoped or least-privilege credential/token mechanism; no docs mention granular permission scopes, read-only vs write tokens, or per-agent credential issuance. This axis is applicable (Poly ships agent/API integrations) but no evidence supports scoped credentialing — missing for 10: any documented scope/permission model, token-level restriction, or least-privilege API key issuance for agents.

   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [claimed-docs] “Give Claude Code persistent context and full access to your Poly files.”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to Reflect
   Reflect~partialprobed3/10

   Reflect exposes a documented REST API with OAuth2/PKCE authentication that developers can build against, confirmed live via probe, but there is no dedicated SDK package, no OpenAPI/swagger spec, and no llms.txt for AI-native tooling — the API itself is limited (append-only, no note read due to E2E encryption). missing for 10: official SDK libraries, OpenAPI spec, llms.txt/AI-friendly docs, read access to note content.

   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://reflect.academy/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://reflect.academy/openapi.json, https://reflect.academy/swagger.json, https://reflect.academy/…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”

   proof ↗⚑ flag

   Poly—none0/10

   Evidence shows a CLI and an MCP server integration, but no official SDK (Python/JS/etc.) or API client library is documented; the OpenAPI probe returned 404s across all candidate paths, indicating no formal API spec developers could build an SDK against.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”
   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Reflect—none0/10

   Reflect's API docs describe OAuth2-based REST access for appending/reading data, but there is no mention of webhooks or event subscriptions anywhere in the docs or probes; the API is described as append-only and pull-based, not event-driven.

   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”

   proof ↗⚑ flag

   Poly—none0/10

   No evidence of any webhook or event-subscription mechanism; Poly's integration surface is limited to MCP, CLI, and file sync, none of which describes outbound event notifications via webhooks.

   ⚑ flag

Agentic features

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

   weight 2 · round drawn
   Reflect✓fullclaimed7/10

   Reflect's AI palette lets users summarize meeting notes into action items/key takeaways, ask free-form questions, chat with filtered notes, and choose between GPT-4o and Claude 3.5 Sonnet — clear AI-generated insight/suggestion features built into the product. Missing for 10: independent/hands-on validation of insight quality and any proactive (vs. purely on-demand) suggestion generation.

   • [claimed-docs] “List action-items and key takeaways from meeting notes”
   • [claimed-docs] “You can also ask the AI palette anything you’d like using the open text field, and save it as a custom prompt to quickly call on again later…”
   • [claimed-docs] “To use it, first highlight some text, and then press `cmd j`... That’ll popup the AI palette.”
   • [claimed-docs] “You can also **ask the AI palette anything** you’d like using the open text field, and save it as a custom prompt to quickly call on again l…”
   • [claimed-docs] “Reflect's AI tools give you the option to now use either GPT-4o (the latest model from OpenAI) or Claude 3.5 Sonnet (the latest model from A…”
   • [claimed-docs] “you can also “chat” with those specific notes to ask questions and extract information.”
   • [claimed-docs] “After applying any desired filters to the search, you can also “chat” with those specific notes to ask questions and extract information.”

   proof ↗⚑ flag

   Poly✓fullprobed7/10

   Poly's docs describe natural-language search, an automatic 'second brain' memory layer, and an agent that can summarize, explain, and generate insights from indexed files (docs-2, docs-3, docs-31, docs-14), directly matching the AI-generated insights/suggestions story. Missing for 10: independent/hands-on evidence of proactive insight generation (vs. just search/summarize-on-request) and no third-party validation of insight quality beyond vendor docs.

   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”
   • [claimed-docs] “Poly automatically remembers key details, forming a "second brain" for you out of your files.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “It automatically parses, transcribes, and indexes your files that make it up to 20x faster for an agent to read and understand them. Use our…”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   Reflect—none0/10

   Reflect is a note-taking app with integrations, deep links, and an append-only API, but there is no evidence of any automation/workflow engine, scheduler, or trigger system that runs autonomously in the background without user action. Integrations (Trello, Asana, calendar sync) are passive data pulls, not user-configured autonomous automations.

   ⚑ flag

   Poly~partialprobed5/10

   Poly's agent can perform multi-step file tasks, spawn subagents, and be invoked via CLI/MCP/plugins, but these are triggered interactively (chat requests, CLI commands, agent sessions) rather than described as scheduled or event-triggered background automations running autonomously without a user prompt. There's no documented scheduler, trigger system, or 'run this automatically every day/on file change' capability. missing for 10: explicit scheduling/trigger mechanism (cron-like, event-driven, or always-on background execution), evidence of automations persisting and running unattended over time, and independent confirmation of autonomous background operation.

   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress. Moreover, agents/subagents can communicate with each ot…”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 3 · round to Poly
   Reflect~partialclaimed6/10

   Reflect ships a built-in 'AI palette' that can summarize notes, list action items, answer custom prompts, and let users 'chat' with their notes using GPT-4o or Claude 3.5 Sonnet — a real in-app AI assistant a user can delegate simple analysis/writing tasks to. However, this is limited to text generation/QA over notes rather than broader agentic task execution (no evidence of multi-step autonomous actions, tool use, or task automation beyond note content). Missing for 10: evidence of autonomous multi-step task delegation, agentic tool-use/actions beyond text Q&A, and independent hands-on verification of the AI assistant's reliability.

   • [claimed-docs] “List action-items and key takeaways from meeting notes”
   • [claimed-docs] “You can also ask the AI palette anything you’d like using the open text field, and save it as a custom prompt to quickly call on again later…”
   • [claimed-docs] “To use it, first highlight some text, and then press `cmd j`... That’ll popup the AI palette.”
   • [claimed-docs] “You can also **ask the AI palette anything** you’d like using the open text field, and save it as a custom prompt to quickly call on again l…”
   • [claimed-docs] “Reflect's AI tools give you the option to now use either GPT-4o (the latest model from OpenAI) or Claude 3.5 Sonnet (the latest model from A…”
   • [claimed-docs] “you can also “chat” with those specific notes to ask questions and extract information.”

   proof ↗⚑ flag

   Poly✓fullprobed8/10

   Poly ships a built-in agent that can search, read, write, edit, and organize files across multiple steps (poly-docs-14, poly-docs-27, poly-docs-31), and can even spawn subagents to delegate subtasks (poly-docs-21, poly-docs-35), directly matching the story of delegating tasks to an in-product AI assistant. This is corroborated by runtime probes confirming a live agent/MCP infrastructure (poly-probe-rt-1, poly-probe-rt-2). Missing for 10: independent hands-on user reports specifically validating the agent's task execution (community commentary focuses on search/security concerns rather than confirming agentic task delegation in practice).

   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress. Moreover, agents/subagents can communicate with each ot…”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   Reflect~partialclaimed5/10

   Reflect's AI palette lets users type natural-language prompts to summarize, extract action items, or chat with notes (cmd-j palette, custom prompts), and search supports semantic natural-language queries. However, this NL support is limited to content Q&A/summarization rather than controlling the app's actions—actual app commands are exposed via structured deep-link URLs (reflect://...&command=...) rather than natural language, so full agentic NL control is not evidenced. Missing for 10: evidence of NL commands driving app actions (e.g., creating/organizing notes, triggering integrations) beyond querying/summarizing content, and any independent/hands-on confirmation of this NL interface's reliability.

   • [claimed-docs] “You can also ask the AI palette anything you’d like using the open text field, and save it as a custom prompt to quickly call on again later…”
   • [claimed-docs] “To use it, first highlight some text, and then press `cmd j`... That’ll popup the AI palette.”
   • [claimed-docs] “You can also **ask the AI palette anything** you’d like using the open text field, and save it as a custom prompt to quickly call on again l…”
   • [claimed-docs] “you can also “chat” with those specific notes to ask questions and extract information.”
   • [claimed-docs] “After applying any desired filters to the search, you can also “chat” with those specific notes to ask questions and extract information.”
   • [claimed-docs] “reflect://reflect?command=<command_name>&<parameter1>=<value1>&...”

   proof ↗⚑ flag

   Poly✓fullprobed8/10

   Poly's docs describe a built-in agent operable via natural language — searching, summarizing, editing, and organizing files with plain-language requests (poly-docs-2, poly-docs-31, poly-docs-14, poly-docs-27), plus a CLI and MCP-based integrations exposing the same commands to AI assistants. This directly matches the ai-native natural-language-command story. Missing for 10: independent/hands-on verification that NL commands work reliably in practice (community evidence only discusses trust/security concerns, not functional testing of NL command execution).

   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Reflect—none0/10

   Reflect's API docs (reflect.academy/api) describe OAuth2 endpoints and PKCE support in prose, but there is no evidence of an interactive API reference with runnable examples — probes confirm no OpenAPI/Swagger spec (404s) and no llms.txt, and nothing in the docs shows a live sandbox or try-it-now console.

   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://reflect.academy/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://reflect.academy/openapi.json, https://reflect.academy/swagger.json, https://reflect.academy/…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”

   proof ↗⚑ flag

   Poly—none0/10

   The probe explicitly found no OpenAPI/Swagger spec at any candidate path, and the evidence pack contains no mention of an interactive API reference or runnable examples anywhere in Poly's docs or CLI/MCP materials.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Reflect—none0/10

   Reflect has an API with OAuth2/PKCE docs, but probes confirm no OpenAPI/Swagger spec or machine-readable schema is published (all candidate paths 404, llms.txt 404); documentation is prose-only.

   • [probe] “PROBE openapi: all candidate paths 404 (https://reflect.academy/openapi.json, https://reflect.academy/swagger.json, https://reflect.academy/…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://reflect.academy/llms.txt”
   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”

   proof ↗⚑ flag

   Poly—none0/10

   A direct probe for OpenAPI/Swagger specs at all standard paths returned 404s, and no evidence pack item mentions a downloadable API spec; Poly instead documents an MCP server and CLI, not a machine-readable REST API spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Reflect—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Poly—none0/10

   Poly's docs describe direct agent read/write access to a user's real files, Drive/Dropbox imports, and MCP integrations, but nowhere mention a sandbox, staging, or test environment isolated from production data. Community comments even highlight anxiety about the agent having broad access to real files with no isolation layer. missing for 10: any documented sandbox/staging mode, test data set, or isolated environment separate from the user's live files.

   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [community] “Hooking up the Internet to my filesystem is scary. What security measures are in place to ensure a compromise of your infrastructure doesn't…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Reflect—none0/10

   The API docs describe OAuth2/PKCE authentication and basic endpoints, but there is no evidence of any versioning scheme (e.g., v1/v2 paths), changelog, or documented deprecation policy anywhere in the docs or probes; OpenAPI/spec probes also 404. missing for 10: API version numbering, changelog/release notes, explicit deprecation policy or backward-compatibility guarantees.

   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://reflect.academy/openapi.json, https://reflect.academy/swagger.json, https://reflect.academy/…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”

   proof ↗⚑ flag

   Poly—none0/10

   No evidence of any versioned public API or documented deprecation policy — probes for OpenAPI/Swagger specs all returned 404, and docs only cover CLI/MCP/agent integrations, not API versioning or deprecation guarantees. missing for 10: versioned API reference, deprecation policy documentation, changelog/versioning scheme.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”

   proof ↗⚑ flag

Agent ops

1. ai-native userMy coding agent or assistant can read AND write my notes headlessly — through a documented local API, vendor API, or MCP server — without me touching the GUI

   weight 3 · round to Poly
   Reflect~partialprobed4/10

   Reflect documents a real OAuth2/PKCE REST API (confirmed live via runtime probe) that supports appending data to notes and returning bookmarked links, giving agents a write path. However, the same probe notes the API is append-only by design because end-to-end encryption prevents Reflect's servers from reading note content — so headless READ of actual notes is not possible via the documented API, and no MCP server is documented. Missing for 10: a documented way to read/retrieve full note content headlessly, and an official MCP server integration.

   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”
   • [claimed-docs] “The contents of your notes are end-to-end encrypted. No one else can read them (not even us).”

   proof ↗⚑ flag

   Poly✓fullprobed9/10

   Poly ships a documented hosted MCP server (mcp.poly.app) with OAuth, exposing search, fetch, and CLI-equivalent tools, plus a CLI/agent-skill that lets agents read, write, create, and organize files headlessly, and a Claude Code plugin that loads Poly memory and connects the MCP server automatically — all confirmed live via runtime probes. missing for 10: independent (non-vendor) hands-on confirmation that write operations via MCP work reliably in practice, beyond docs and probes.

   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [claimed-docs] “The [`poly-cli` agent skill] teaches an agent how to search, read, create, update, and organize your Poly files by composing `poly` commands…”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

Ai assist

1. ai-native userConnect external LLMs and AI tools to my notes through first-party connectors or an ecosystem of AI plugins

   weight 2 · round to Poly
   Reflect~partialprobed5/10

   Reflect ships first-party AI features letting users toggle between GPT-4o and Claude 3.5 Sonnet for in-app AI palette actions (summarize, chat with notes), and exposes an OAuth2/PKCE API for building custom clients. However there's no evidence of a broader plugin ecosystem or first-party connectors letting external AI tools/agents read and act on notes — the API is documented as append-only and scoped narrowly (bookmarks, appending data), not an AI integration surface, and no third-party AI plugin marketplace is mentioned. Missing for 10: a documented AI-plugin ecosystem, evidence of external AI tools consuming notes via API, and richer API scope beyond append-only actions.

   • [claimed-docs] “Reflect's AI tools give you the option to now use either GPT-4o (the latest model from OpenAI) or Claude 3.5 Sonnet (the latest model from A…”
   • [claimed-docs] “To use it, first highlight some text, and then press `cmd j`... That’ll popup the AI palette.”
   • [claimed-docs] “You can also **ask the AI palette anything** you’d like using the open text field, and save it as a custom prompt to quickly call on again l…”
   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”

   proof ↗⚑ flag

   Poly✓fullprobed9/10

   Poly ships a first-party MCP server (mcp.poly.app) with OAuth, documented and runtime-verified as live, plus official plugins/integrations for Claude, ChatGPT, Claude Code, VS Code, and a CLI usable by agents, giving AI-native users multiple first-party ways to connect external LLMs to their notes/files. missing for 10: no independent hands-on confirmation of the plugin ecosystem working smoothly beyond docs/probe, and community feedback raises unresolved trust/security concerns rather than functional failures.

   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “The official plugin loads your Poly memory when each session starts, teaches Claude how to use Poly, and connects the Poly MCP server.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [claimed-docs] “Give Claude Code persistent context and full access to your Poly files.”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”
   • [probe] “PROBE runtime (recorded 2026-09-14): https://docs.poly.app/llms.txt served an agent-oriented docs index ('# docs.poly.app', with a companion…”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

2. ai-native userA built-in AI assistant can answer questions, summarize, and draft grounded in my own notes — with clear controls over what data it sees

   weight 2 · round to Reflect
   Reflect✓fullcommunity7/10

   Docs show a built-in AI palette (cmd-j) that can summarize meeting notes, list action items, answer custom prompts, and 'chat' with filtered/specific notes grounded in the user's own content, with model choice (GPT-4o/Claude 3.5). Data-scoping control is shown via search filters before chatting with a subset of notes, and E2E encryption is claimed for note content, though community evidence notes files/images are excluded from encryption. Missing for 10: independent hands-on review of AI answer quality/grounding, explicit UI controls for restricting AI's data access beyond search filters, and no clarification on how E2E encryption interacts with cloud-based AI processing.

   • [claimed-docs] “List action-items and key takeaways from meeting notes”
   • [claimed-docs] “you can also “chat” with those specific notes to ask questions and extract information.”
   • [claimed-docs] “You can also ask the AI palette anything you’d like using the open text field, and save it as a custom prompt to quickly call on again later…”
   • [claimed-docs] “After applying any desired filters to the search, you can also “chat” with those specific notes to ask questions and extract information.”
   • [claimed-docs] “To use it, first highlight some text, and then press `cmd j`... That’ll popup the AI palette.”
   • [claimed-docs] “You can also **ask the AI palette anything** you’d like using the open text field, and save it as a custom prompt to quickly call on again l…”
   • [claimed-docs] “Reflect's AI tools give you the option to now use either GPT-4o (the latest model from OpenAI) or Claude 3.5 Sonnet (the latest model from A…”
   • [claimed-docs] “Reflect’s Semantic search lets you find specific pieces of information without knowing the exact words.”
   • [claimed-docs] “The contents of your notes are end-to-end encrypted. No one else can read them (not even us).”
   • [community] “Question about Reflect's E2E encryption claims: 'We do not end-to-end encrypt things like files or images you upload' - user noted this excl…”

   proof ↗⚑ flag

   Poly~partialcommunity5/10

   Poly's built-in agent clearly summarizes, explains, drafts, and edits notes grounded in the user's own files (poly-docs-31, poly-docs-14, poly-docs-27, poly-docs-3), and Mind/journaling gives a personal-notes corpus for it to draw on (poly-docs-12, poly-docs-26, poly-docs-32). However, evidence for granular controls over *what the assistant itself sees* is thin: docs describe the agent getting 'full access to your Poly files' (poly-docs-30) rather than scoped visibility, and the only access controls documented are sharing/revoke permissions for other people (poly-docs-9, poly-docs-33), not data-scoping for the AI itself — a gap community users flag as a trust concern (poly-comm-2, poly-comm-4). Missing for 10: explicit per-folder/file visibility toggles or exclusion settings for the assistant, and independent confirmation that such controls work as intended.

   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “The Poly agent can write and edit files directly in your storage.”
   • [claimed-docs] “Poly automatically remembers key details, forming a "second brain" for you out of your files.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Give Claude Code persistent context and full access to your Poly files.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it. You stay the owner,…”
   • [community] “Hooking up the Internet to my filesystem is scary. What security measures are in place to ensure a compromise of your infrastructure doesn't…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”

   proof ↗⚑ flag

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

   weight 2 · round to Poly
   Reflect—none0/10

   Reflect's API supports appending data to individual notes and returning bookmark lists, but there is no evidence of any bulk/batch operation capability (e.g., batch update, multi-note transformation, or scripted bulk edits across many items at once); the API is explicitly append-only per note due to E2E encryption.

   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”

   proof ↗⚑ flag

   Poly~partialclaimed5/10

   Poly's CLI is described as 'scriptable from the terminal' (poly-docs-17) and the agent can chain multi-step tasks like 'organizing a folder' or spawning subagents to handle work in parallel (poly-docs-14, poly-docs-21, poly-docs-31, poly-docs-35), which implies some automation across sets of files, but there is no explicit documentation of a true bulk/batch operation (e.g., 'rename/tag/move N files at once') or a dedicated batch API/command. Missing for 10: an explicit bulk-operation example or batch command, evidence of scale (many items processed in one call), and independent/hands-on confirmation that automation reliably spans large item sets.

   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress. Moreover, agents/subagents can communicate with each ot…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Reflect—none0/10

   Reflect's docs describe integrations (Trello/Asana/calendar sync), deep links, and an API, but nowhere is there a rules engine or event-trigger/action automation system (e.g., 'when X happens, do Y'). No evidence supports this capability.

   ⚑ flag

   Poly—none0/10

   Poly's docs describe on-demand agent actions (search, summarize, edit, organize) and multi-step task execution, but there is no evidence of a rules/trigger system that fires actions automatically on defined events (e.g., file-added, schedule, webhook-based automation). Automation is user-initiated per request, not event-driven.

   • [claimed-docs] “The Poly agent can handle tasks that span multiple steps — reading, searching, writing, and organizing — in a single request.”
   • [claimed-docs] “Ask it to summarize, explain, or even edit your files. Automate tasks like organizing a folder.”
   • [claimed-docs] “Your agent can spawn its own subagents, assign them tasks, and track their progress.”

   proof ↗⚑ flag

Capture

1. researcherClip web pages, articles, and highlights from my browser straight into my notes with an official clipper or capture flow

   weight 2 · round to Reflect
   Reflect✓fullclaimed9/10

   Reflect ships an official Chrome and Safari browser extension for bookmarking websites, capturing snippets, and highlights, which are automatically added to the daily note — directly matching the researcher's clipper/capture workflow. Documentation is detailed and first-party; missing for 10: independent hands-on review specifically validating the clipper extension's reliability/quality.

   • [claimed-docs] “Reflect lets you quickly bookmark websites and capture snippets from across the web using our Chrome extension”
   • [claimed-docs] “The link and your highlights will automatically be added to your daily note.”
   • [claimed-docs] “Reflect lets you quickly bookmark websites and capture snippets from across the web using our Chrome extension and Safari extension.”

   proof ↗⚑ flag

   Poly—none0/10

   Poly's docs describe importing from Drive/Dropbox/iCloud/local files and from note apps like Notion/Obsidian/Evernote, but there is no mention of a browser extension, web clipper, or capture flow for saving web pages/articles/highlights directly into Poly. This is a fair capability for a 'second brain' note tool, so absence of evidence means it is not delivered.

   • [claimed-docs] “Import your existing files from Google Drive, Dropbox, iCloud, or your local machine.”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”

   proof ↗⚑ flag

Daily notes

1. power-userI get an automatic daily note for each day, pre-filled from a template, as the default landing place for journaling and capture

   weight 3 · round to Reflect
   Reflect✓fullclaimed8/10

   Reflect's docs explicitly confirm automatic daily notes created every day as the journaling landing place, and multiple features (voice transcription, bookmarking, calendar sync, integrations) are documented as auto-filling into that daily note, showing it's the default capture surface. Missing for 10: explicit confirmation of a customizable daily-note *template* pre-filling structure/content, and independent hands-on verification of the daily-note experience beyond docs.

   • [claimed-docs] “Tools like Reflect will create a new _daily note_ for you everyday for you to journal in.”
   • [claimed-docs] “Tools like Reflect will create a new daily note for you everyday for you to journal in.”
   • [claimed-docs] “Speak your note, then click stop recording... their transcription will be added to your daily note.”
   • [claimed-docs] “The link and your highlights will automatically be added to your daily note.”
   • [claimed-docs] “We support connecting your Google, iCloud and Office 365 account(s) to Reflect. This lets you: Pull in your calendar events, so you can easi…”
   • [claimed-docs] “Add Trello cards or Asana tasks to your Daily Note”
   • [claimed-docs] “Add Trello cards or Asana tasks to your Daily Note Add Google Docs and Slack notes to Reflect Save emails and Tweets to your notes Sync your…”

   proof ↗⚑ flag

   Poly~partialclaimed3/10

   Poly Mind's journaling feature provides a manual 'quiet place' to write daily thoughts and syncs entries as Markdown files, which loosely matches the capture/journaling theme, but there's no evidence of automatic daily note creation, template pre-fill, or it being the default landing screen. missing for 10: automatic daily note generation, template pre-fill mechanism, evidence of default-landing behavior on app open.

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”

   proof ↗⚑ flag

Editor

1. power-userDefine reusable templates (with variables like date and title) and apply them when creating recurring kinds of notes

   weight 2 · round drawn
   Reflect—none0/10

   The evidence pack shows daily notes, backlinks, tags, filters, imports, and AI palette features, but nowhere mentions reusable note templates with variable substitution (e.g., date/title placeholders) for creating recurring note types. Missing for 10: any documentation of a templates feature, variable/placeholder syntax, or ability to save/apply templates to new notes.

   ⚑ flag

   Poly—none0/10

   Poly's Mind/journaling docs describe creating markdown journal entries and importing notes, but there is no evidence of a reusable template system with variables (date, title) for recurring note types.

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”

   proof ↗⚑ flag

2. power-userWrite and format notes with headings, callouts, tables, code blocks, and embedded media in a fast keyboard-driven editor

   weight 2 · round to Poly
   Reflect—none0/10

   The evidence pack covers linking/backlinks, daily notes, import/export in Markdown, AI features, and encryption, but contains no documentation or community evidence about core rich-text editing capabilities such as headings, callouts, tables, code blocks, or embedded media, nor about keyboard-driven editing speed. Missing for 10: any docs mentioning headings/callout blocks/tables/code blocks/embedded media support, and any evidence of keyboard-shortcut-driven formatting workflow.

   ⚑ flag

   Poly~partialclaimed3/10

   Poly supports Markdown-based journaling (auto-synced .md files in the Mind folder) and offers Vim keybindings for file editing, suggesting some keyboard-driven text editing capability, but there is no documentation of rich formatting elements like callouts, tables, code blocks, or embedded media in a dedicated note editor. Missing for 10: explicit support for headings/callouts/tables/code blocks, embedded media, and any description of a fast dedicated editor UI beyond basic Markdown journaling.

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Vim keybindings (enable in Settings)”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”

   proof ↗⚑ flag

Migration

1. switcherExport my entire knowledge base at any time in open formats, so leaving is as easy as arriving

   weight 2 · round to Reflect
   Reflect✓fullcommunity8/10

   Reflect explicitly documents export into open formats (HTML, Markdown) at any time, and the founder corroborates this as an anti-lock-in feature in community discussion. missing for 10: independent hands-on verification of a full/bulk knowledge-base export (vs per-note export) and confirmation that all note types/attachments are included.

   • [claimed-docs] “you can always export it into an open format (like HTML or Markdown).”
   • [community] “Reflect founder on data lock-in: 'you can always export your notes into markdown or HTML so you shouldn't feel too locked in.' Also noted th…”

   proof ↗⚑ flag

   Poly~partialclaimed4/10

   Poly stores files as real files that sync to a local Finder/Explorer folder (poly-docs-23) and journal entries are plain Markdown (poly-docs-12), implying your data always exists in accessible, mostly-original formats rather than a locked proprietary export. However, there is no explicit 'export my knowledge base' feature, bulk-export tool, or open-format guarantee for the indexed metadata/second-brain layer — only import pathways (poly-docs-1, poly-docs-22) are documented. Missing for 10: an explicit export/backup command or API, confirmation that indexed metadata (tags, memory, search index) can be exported, and any open-format guarantee beyond raw file sync.

   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Import your existing files from Google Drive, Dropbox, iCloud, or your local machine.”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”

   proof ↗⚑ flag

2. switcherImport my existing notes from Notion, Evernote, Roam, or plain Markdown with structure, links, and attachments preserved

   weight 3 · round to Reflect
   Reflect~partialclaimed6/10

   Reflect's docs confirm native import support for Evernote (ENEX), Roam (JSON), and Markdown files, three of the four sources named in the story, plus Apple Notes and Workflowy. However, Notion import is not mentioned anywhere in the import/export documentation, and there is no explicit confirmation that internal links or attachments are preserved through the import process for any of these formats. Missing for 10: Notion import support, explicit evidence that links and attachments (not just note text) survive import.

   • [claimed-docs] “We currently support imports from: Apple Notes (HTML) Evernote (ENEX) Markdown files Roam (JSON) Workflowy (OPML)”
   • [claimed-docs] “We currently support imports from: * Apple Notes (HTML) * Evernote (ENEX) * Markdown files * Roam (JSON) * Workflowy (OPML)”
   • [claimed-docs] “First you’ll have to export your existing Apple Notes using the provided script below, then import them into Reflect normally.”
   • [claimed-docs] “you can always export it into an open format (like HTML or Markdown).”

   proof ↗⚑ flag

   Poly~partialclaimed5/10

   Poly's docs explicitly state you can 'bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more,' directly covering two of the four named sources, and general file import (Google Drive/Dropbox/local) plus native Markdown journal files supports plain Markdown ingestion. However, Roam is never explicitly named, and there is no documented detail on how structure, internal links, or attachments are preserved during the import process, nor any hands-on/community confirmation of import fidelity. Missing for 10: explicit Roam support, documented handling of internal links/structure/attachments during migration, independent corroboration of import fidelity.

   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”
   • [claimed-docs] “Import your existing files from Google Drive, Dropbox, iCloud, or your local machine.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”

   proof ↗⚑ flag

Graph

1. researcherExplore my knowledge base as an interactive graph of notes and connections, filtered to what I care about

   weight 1 · round drawn
   Reflect—none0/10

   Reflect's docs describe backlinks, [[ ]] linking, and filtering notes by tags/date/backlinks, but nowhere is an interactive visual graph view of the knowledge base mentioned or shown — the evidence only covers list-style backlinks and search filters, not a graph exploration UI.

   • [claimed-docs] “Networked note-taking tools, like Reflect, support creating links between notes... backlinks”
   • [claimed-docs] “Backlinks are just a list of incoming links from other notes.”
   • [claimed-docs] “You can filter notes by: Date created or updated, Daily Notes, Where they are backlinked to/from, #tags, Pinned notes”
   • [claimed-docs] “You can filter notes by: Date created or updated Daily Notes Where they are backlinked to/from #tags Pinned notes”
   • [claimed-docs] “You can filter notes by: * Date created or updated * Daily Notes * Where they are backlinked to/from * #tags * Pinned notes”

   proof ↗⚑ flag

   Poly—none0/10

   Poly's docs describe a 'second brain' with search, journaling, tagging, multiple folder views (Icon, Grid, Feed, Detail, Tree, etc.), and Notion/Obsidian import, but nowhere mention a graph visualization of notes/connections or filtering such a graph — this is a plausible axis for a notes/second-brain product but no evidence supports it.

   • [claimed-docs] “Poly automatically remembers key details, forming a "second brain" for you out of your files.”
   • [claimed-docs] “Eight ways to look at a folder — Icon, Grid, Feed, Detail, Tree, C”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”

   proof ↗⚑ flag

Links

1. researcherLink notes with [[wiki-style]] links and see every backlink and unlinked mention of a note in context

   weight 3 · round to Reflect
   Reflect~partialclaimed7/10

   Docs confirm [[ ]] wiki-link shortcut, backlinks as incoming links, and filtering notes by where they're backlinked to/from, covering the core linking-graph story. However, evidence never explicitly mentions detection/surfacing of 'unlinked mentions' in context, which is a specific part of the story. Missing for 10: explicit unlinked-mention detection/surfacing, independent hands-on demonstration of backlink UI in context.

   • [claimed-docs] “Networked note-taking tools, like Reflect, support creating links between notes... backlinks”
   • [claimed-docs] “Generally note-taking tools, including Reflect, use the `[[` shortcut to link some text.”
   • [claimed-docs] “Backlinks are just a list of incoming links from other notes.”
   • [claimed-docs] “You can filter notes by: Date created or updated, Daily Notes, Where they are backlinked to/from, #tags, Pinned notes”
   • [claimed-docs] “You can filter notes by: Date created or updated Daily Notes Where they are backlinked to/from #tags Pinned notes”
   • [claimed-docs] “You can filter notes by: * Date created or updated * Daily Notes * Where they are backlinked to/from * #tags * Pinned notes”

   proof ↗⚑ flag

   Poly—none0/10

   Poly's 'Mind' feature supports journaling, importing notes from other PKM tools, and semantic search, but nothing in the evidence pack mentions [[wiki-style]] linking, backlink panels, or unlinked-mention detection — core PKM/wiki-linking features. Since Poly Mind explicitly targets note-taking/second-brain use cases, this axis is a fair question for the product, but no evidence shows it delivers wiki-links or backlinks.

   • [claimed-docs] “Poly automatically remembers key details, forming a "second brain" for you out of your files.”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”

   proof ↗⚑ flag

2. power-userReference or transclude an individual block or section of one note inside another and have it stay in sync

   weight 2 · round drawn
   Reflect—none0/10

   Evidence shows Reflect supports note-to-note linking and backlinks ([[ shortcuts, backlinks list) but nowhere documents block- or section-level transclusion/embedding that stays synced across notes — only whole-note linking and filtering by backlink is described.

   • [claimed-docs] “Networked note-taking tools, like Reflect, support creating links between notes... backlinks”
   • [claimed-docs] “Generally note-taking tools, including Reflect, use the `[[` shortcut to link some text.”
   • [claimed-docs] “Backlinks are just a list of incoming links from other notes.”

   proof ↗⚑ flag

   Poly—none0/10

   Poly's docs describe file search, an agent, a CLI/MCP integration, and a Markdown-based Mind/journal folder, but nothing in the evidence describes block- or section-level transclusion between notes that stays synced (no backlinks, embeds, or live-sync block references are mentioned anywhere in the docs pack).

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life.”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”

   proof ↗⚑ flag

Ownership

1. power-userMy notes live in local files or a local-first store that I own and can read without the app, and everything keeps working fully offline

   weight 3 · round to Poly
   Reflect—none0/10

   Reflect is a cloud-synced, end-to-end-encrypted note service (docs-16/35) with export-to-Markdown/HTML available (docs-44, comm-7), but there is no evidence notes are stored as local files or in a local-first store the user can read without the app, nor evidence of full offline functionality — the API and encryption model imply server-mediated sync rather than local-first ownership.

   • [claimed-docs] “End-to-end encryption keeps your notes secure.”
   • [claimed-docs] “The contents of your notes are end-to-end encrypted. No one else can read them (not even us).”
   • [claimed-docs] “you can always export it into an open format (like HTML or Markdown).”
   • [community] “Reflect founder on data lock-in: 'you can always export your notes into markdown or HTML so you shouldn't feel too locked in.' Also noted th…”
   • [community] “Question about Reflect's E2E encryption claims: 'We do not end-to-end encrypt things like files or images you upload' - user noted this excl…”

   proof ↗⚑ flag

   Poly!disputedcontradicted4/10

   Docs describe files/journal entries as real local files (synced Finder folder, Markdown notes in a 'Mind' folder), suggesting some local-first storage, but the core search/indexing/agent stack is cloud-hosted (remote MCP server at mcp.poly.app, OAuth-gated, server-side parsing/transcribing/indexing) — and a hands-on community reviewer explicitly notes 'your service, by nature, is reading and analyzing all of my files using a remote server,' directly contradicting a fully offline, locally-owned workflow. Missing for 10: no documentation of an offline mode, no evidence local files remain fully functional/searchable without the cloud service, and no rebuttal to the community's remote-dependency observation.

   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “It automatically parses, transcribes, and indexes your files that make it up to 20x faster for an agent to read and understand them.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”
   • [community] “It feels like an LLM wrapper in search of a problem. Cloud search plus already exists... I do not find the idea of bringing my data to your …”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

2. researcherMy notes are stored or exportable in open, documented formats (Markdown, JSON) so my archive outlives the vendor

   weight 2 · round to Reflect
   Reflect✓fullcommunity8/10

   Reflect explicitly documents export to open formats (Markdown, HTML) and import from Markdown/JSON-based formats, and the founder publicly confirms notes can always be exported to Markdown/HTML to avoid lock-in. Missing for 10: no independent hands-on verification of export fidelity/completeness, and export format is somewhat limited (HTML/Markdown only, not full JSON archive of all metadata).

   • [claimed-docs] “We currently support imports from: Apple Notes (HTML) Evernote (ENEX) Markdown files Roam (JSON) Workflowy (OPML)”
   • [claimed-docs] “We currently support imports from: * Apple Notes (HTML) * Evernote (ENEX) * Markdown files * Roam (JSON) * Workflowy (OPML)”
   • [claimed-docs] “you can always export it into an open format (like HTML or Markdown).”
   • [community] “Reflect founder on data lock-in: 'you can always export your notes into markdown or HTML so you shouldn't feel too locked in.' Also noted th…”

   proof ↗⚑ flag

   Poly~partialclaimed5/10

   Poly's Mind journal entries are explicitly stored as plain Markdown files synced to a folder (poly-docs-12), and the desktop client exposes all Poly files as a real Finder/Explorer folder that syncs back automatically (poly-docs-23), so notes aren't locked in a proprietary blob. However there is no documented bulk-export feature, no JSON export format, and no explicit statement about long-term archival or vendor-independence beyond this folder-sync mechanism; import from other note apps (poly-docs-22) is one-way and does not evidence export-out portability. Missing for 10: explicit JSON/structured export option, a documented full-archive export or backup mechanism, and any statement guaranteeing data portability/format stability if the vendor shuts down.

   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “Bring existing notes and memory archives into Poly Mind from Notion, Obsidian, Evernote, Bear, and more.”

   proof ↗⚑ flag

Self host

1. developerRun the whole system without the vendor's cloud — local-only mode or a self-hosted sync backend I operate myself

   weight 2 · round drawn
   Reflect—none0/10

   Reflect is a cloud-hosted, closed-source SaaS with E2E encryption on the vendor's servers — there is no evidence of a local-only mode or self-hostable sync backend; only export to Markdown/HTML for backup is documented, not operating your own sync server.

   • [claimed-docs] “you can always export it into an open format (like HTML or Markdown).”
   • [community] “Reflect founder on data lock-in: 'you can always export your notes into markdown or HTML so you shouldn't feel too locked in.' Also noted th…”
   • [claimed-docs] “The contents of your notes are end-to-end encrypted. No one else can read them (not even us).”

   proof ↗⚑ flag

   Poly—none0/10

   All evidence points to Poly being a cloud-backed service (hosted MCP server at mcp.poly.app requiring OAuth login to Poly's cloud, cloud-based indexing/search) with no documented local-only mode or self-hosted sync backend option; community comments even complain that files/data must go through Poly's remote servers rather than staying local.

   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”
   • [community] “It feels like an LLM wrapper in search of a problem. Cloud search plus already exists... I do not find the idea of bringing my data to your …”

   proof ↗⚑ flag

Mobile

1. power-userFull-featured iOS and Android apps give me my whole knowledge base — capture, search, and linking — not a stripped-down companion

   weight 2 · round drawn
   Reflect—none0/10

   The evidence pack covers imports, API, AI features, publishing, security, and integrations extensively, but contains no mention of iOS or Android apps, their feature set, or mobile-specific capture/search/linking capabilities. Without any documentation or community evidence describing dedicated mobile apps (full-featured or otherwise), there is nothing to substantiate this story.

   ⚑ flag

   Poly—none0/10

   Evidence pack extensively documents desktop, CLI, web/MCP, and Finder/Explorer integration, but contains no mention whatsoever of iOS or Android apps, mobile capture, or mobile search/linking capability. missing for 10: any evidence of iOS app, Android app, or mobile-specific capture/search/linking features.

   ⚑ flag

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

   weight 2 · round to Poly
   Reflect~partialprobed3/10

   Reflect does expose an OAuth2/PKCE REST API confirmed live via runtime probe, but by its own docs it only supports appending data to notes and returning bookmarked links plus 'a few other things' — a small subset of UI capabilities (semantic search, AI chat, publishing, backlinks, calendar/integrations, deep links) with no evidence these are API-accessible. The API is also explicitly append-only for note content since E2E encryption prevents server-side reads, meaning even reading/editing existing notes via API is not possible as it is in the UI. Missing for 10: API endpoints for search/AI features, note reading/editing, publishing, and integrations parity with the UI.

   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”
   • [claimed-docs] “Reflect’s Semantic search lets you find specific pieces of information without knowing the exact words.”
   • [claimed-docs] “Reflect offers one-click publishing of your notes. Simply hit the publish button and your note will be publicly available behind a long hard…”

   proof ↗⚑ flag

   Poly~partialprobed5/10

   Poly ships a scriptable CLI (25+ commands) and a hosted MCP server exposing search, fetch, and a virtual `poly` CLI as tools, giving programmatic access to core file search/read/write/organize workflows that mirror the UI's agent capabilities (poly-docs-17, poly-probe-rt-2, poly-probe-4). However there is no documented REST/OpenAPI API (openapi probes all 404'd), and no evidence that UI-only features like sharing/permissions management, the eight folder views, flashback/version history, or journaling are exposed programmatically. Missing for 10: a general-purpose REST/OpenAPI surface, API parity for sharing/permissions, version history, and Mind/journaling features.

   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “The [`poly-cli` agent skill] teaches an agent how to search, read, create, update, and organize your Poly files by composing `poly` commands…”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it.”
   • [claimed-docs] “Go into flashback mode at any time to see exactly what your files looked like at any point in the past, down to the millisecond.”

   proof ↗⚑ flag

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

   weight 3 · round to Reflect
   Reflect✓fullcommunity8/10

   Reflect explicitly documents export to open formats (HTML, Markdown) and the founder confirms this is a deliberate anti-lock-in policy, directly matching the story. missing for 10: no independent hands-on verification of a full data export/migration, and export is confined to notes (E2E-encrypted files/images may not be fully portable per reflect-comm-8).

   • [claimed-docs] “you can always export it into an open format (like HTML or Markdown).”
   • [claimed-docs] “We currently support imports from: Apple Notes (HTML) Evernote (ENEX) Markdown files Roam (JSON) Workflowy (OPML)”
   • [community] “Reflect founder on data lock-in: 'you can always export your notes into markdown or HTML so you shouldn't feel too locked in.' Also noted th…”
   • [community] “Question about Reflect's E2E encryption claims: 'We do not end-to-end encrypt things like files or images you upload' - user noted this excl…”

   proof ↗⚑ flag

   Poly~partialclaimed4/10

   Poly's desktop sync exposes files as a real folder in Finder/Explorer with files kept in their original formats and synced back automatically (poly-docs-23), and journal entries are stored as plain Markdown files (poly-docs-12), which implies some natural portability rather than lock-in. However, there is no explicit documentation of a bulk 'export all data' feature, data-export API, or guarantee that a user can fully extract their indexed memory/context in open formats and leave — missing for 10: an explicit export/data-portability feature, documentation of exporting the 'second brain'/index data, and any mention of account deletion/data takeout.

   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”
   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Reflect—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Poly—none0/10

   No evidence of any open-source license or public source repository for Poly; it appears to be a closed, proprietary SaaS/desktop product with only documentation and API/MCP endpoints disclosed. Missing for 10: any open-source license file, public code repository, or statement of source availability.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Reflect—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Poly—none0/10

   All evidence describes Poly as a hosted SaaS (cloud sync, hosted MCP endpoint at mcp.poly.app requiring OAuth, subscription-based) with no mention of a self-hosted or on-prem deployment option anywhere in the docs or probes.

   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [community] “This is really cool! I suck at organizing my filesystem and I've lost track of how many times I had to find that ONE PDF which I KNOW I have…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”

   proof ↗⚑ flag

Metadata

1. power-userAttach typed properties and tags to notes and use them consistently for organization and retrieval

   weight 2 · round to Reflect
   Reflect~partialclaimed5/10

   Reflect clearly supports tags (#tags) for organization and retrieval, including automatic tagging (e.g. Kindle imports tagged #book) and filtering notes by #tags, backlinks, dates, and pinned status. However, there is no evidence of 'typed properties' (structured metadata fields with types, akin to database properties) — Reflect's organization model is built around tags, backlinks, and daily notes, not typed property schemas. Missing for 10: evidence of typed/structured properties (not just tags), evidence of consistent property schemas across notes, and any UI for defining property types.

   • [claimed-docs] “You can filter notes by: Date created or updated, Daily Notes, Where they are backlinked to/from, #tags, Pinned notes”
   • [claimed-docs] “You can filter notes by: Date created or updated Daily Notes Where they are backlinked to/from #tags Pinned notes”
   • [claimed-docs] “You can filter notes by: * Date created or updated * Daily Notes * Where they are backlinked to/from * #tags * Pinned notes”
   • [claimed-docs] “Reflect can automatically sync your books, highlights, and comments from your Kindle. They will be imported into Reflect as individual notes…”
   • [claimed-docs] “Reflect can automatically sync your books, highlights, and comments from your Kindle. They will be imported into Reflect as individual notes…”

   proof ↗⚑ flag

   Poly~partialclaimed4/10

   Poly documents tag support that syncs bidirectionally with Finder tags and colors, and search/retrieval features (natural language, visual similarity), but there is no evidence of 'typed properties' (structured metadata fields/schemas) or of consistent, structured tag-based retrieval workflows beyond basic color/tag sync. missing for 10: typed/structured property fields, evidence of consistent tag-based filtering or retrieval UI, cross-file property schemas.

   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”
   • [claimed-docs] “Eight ways to look at a folder — Icon, Grid, Feed, Detail, Tree, C”
   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”

   proof ↗⚑ flag

Queries

1. power-userQuery my notes by their structured properties and render live database-style views (tables, boards, lists) from those queries

   weight 3 · round drawn
   Reflect—none0/10

   Reflect only supports basic filtering (tags, dates, backlinks, pinned) per reflect-docs-15/22/27, with no evidence of structured/typed properties, query language, or database-style table/board/list views like Notion or Roam-style databases. No documentation or community evidence mentions live queryable views rendered from structured properties.

   • [claimed-docs] “You can filter notes by: Date created or updated, Daily Notes, Where they are backlinked to/from, #tags, Pinned notes”
   • [claimed-docs] “You can filter notes by: Date created or updated Daily Notes Where they are backlinked to/from #tags Pinned notes”
   • [claimed-docs] “You can filter notes by: * Date created or updated * Daily Notes * Where they are backlinked to/from * #tags * Pinned notes”

   proof ↗⚑ flag

   Poly—none0/10

   Poly's docs describe file search, tagging, journaling, and multiple folder 'views' (Icon, Grid, Feed, Detail, Tree, etc.) but there is no evidence of structured/custom properties on notes nor of live query-driven database views like tables or boards built from property filters — the 'eight ways to look at a folder' are display modes, not queryable schema-based views.

   • [claimed-docs] “Eight ways to look at a folder — Icon, Grid, Feed, Detail, Tree, C”
   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”
   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”

   proof ↗⚑ flag

Search

1. researcherInstantly search all my notes with full-text search plus filters on tags, properties, and paths — including offline

   weight 3 · round to Reflect
   Reflect~partialclaimed6/10

   Reflect documents semantic + full-text search with filters on tags, backlinks, date, daily notes, and pinned status (reflect-docs-6,15,22,27,41), covering most of the story. However, no explicit filter on "properties" (beyond tags) or "paths" is documented, and offline capability/search-while-offline is never mentioned anywhere in the evidence. Missing for 10: explicit property-based filtering, path-based filtering, and any documentation of offline search support.

   • [claimed-docs] “Reflect’s Semantic search lets you find specific pieces of information without knowing the exact words.”
   • [claimed-docs] “You can filter notes by: Date created or updated, Daily Notes, Where they are backlinked to/from, #tags, Pinned notes”
   • [claimed-docs] “You can filter notes by: Date created or updated Daily Notes Where they are backlinked to/from #tags Pinned notes”
   • [claimed-docs] “You can filter notes by: * Date created or updated * Daily Notes * Where they are backlinked to/from * #tags * Pinned notes”
   • [claimed-docs] “Reflect's Semantic search lets you find specific pieces of information without knowing the exact words.”
   • [claimed-docs] “After applying any desired filters to the search, you can also “chat” with those specific notes to ask questions and extract information.”

   proof ↗⚑ flag

   Poly~partialclaimed4/10

   Poly documents natural-language full-text search (down to timestamp/page/paragraph), a CLI 'poly search' command, visual similarity search, and Finder-tag syncing, but nowhere combines these into documented filter syntax on tags/properties/paths, nor claims search works offline (files instead 'download on demand' and sync back, implying online-first indexing). missing for 10: explicit support for combined tag/property/path filters in search queries, explicit documentation of offline full-text search capability.

   • [claimed-docs] “Search inside your files with natural language that's gives you results down to the exact timestamp, page, paragraph, or frame.”
   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “Visual similarity — find images that look like a reference image you provide”
   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”
   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”

   proof ↗⚑ flag

Automation hooks

1. developerDrive the app from outside — create or open notes via a URI scheme, deep links, or a local endpoint — to wire it into my scripts and workflows

   weight 2 · round to Reflect
   Reflect✓fullprobed8/10

   Reflect ships a documented custom URI scheme (reflect://reflect?command=...) for deep linking into the app, plus a REST API with OAuth2/PKCE authentication that a runtime probe confirms is live and enforcing auth, letting developers script note creation/appending from outside the app. missing for 10: independent/hands-on developer confirmation of building an external integration, and full endpoint/command reference beyond the docs snippets.

   • [claimed-docs] “Reflect supports deep linking, allowing users to perform actions within the app using custom URLs.”
   • [claimed-docs] “reflect://reflect?command=<command_name>&<parameter1>=<value1>&...”
   • [claimed-docs] “For authentication, we support OAuth 2. You will need to create credentials here.”
   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://reflect.app/api/graphs returned HTTP 401 {"error":{"typ…”

   proof ↗⚑ flag

   Poly~partialprobed6/10

   Poly ships a scriptable `poly` CLI (poly-docs-6, poly-docs-17, poly-probe-4) and a local/hosted MCP endpoint (poly-docs-29, poly-probe-rt-2) that let external scripts search, read, and create/edit files including Mind journal notes, satisfying the 'local endpoint for workflows' part of the story. However there is no documented URI scheme or OS-level deep-link mechanism for opening/creating notes, only CLI/MCP paths. Missing for 10: URI scheme/deep-link support, explicit CLI subcommand for creating a note by title/URI, independent confirmation of CLI scripting reliability.

   • [claimed-docs] “poly search "the contract with the March deadline"”
   • [claimed-docs] “`poly` is Poly's command-line tool: your files, searchable and scriptable from the terminal.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

Plugins

1. power-userBrowse and install from a large catalog of community plugins/extensions to add features the core app doesn't ship

   weight 3 · round drawn
   Reflect—none0/10

   There is no evidence of a plugin/extension marketplace; instead community evidence explicitly states Reflect is designed to be 'fully functional without any plugins' as a differentiator from Obsidian, indicating no such catalog exists.

   • [community] “What drew me to Reflect (away from Obsidian) was full functionality out of the box without the need for plugins... Reflect is fully function…”

   proof ↗⚑ flag

   Poly—none0/10

   Evidence shows Poly ships its own integrations (CLI, MCP server, plugins for Claude/ChatGPT/VS Code) that let Poly connect into other tools, but there is no mention of a marketplace or catalog of third-party/community-built plugins that extend Poly itself with new features.

   • [claimed-docs] “Use our plugin with leading agents like Claude, ChatGPT, and VS Code and make your file workflows insanely fast.”
   • [claimed-docs] “The Model Context Protocol (MCP) lets compatible AI assistants connect to Poly.”
   • [claimed-docs] “Connect Poly to AI assistants and code editors with the local CLI first, then set up an MCP integration.”
   • [claimed-docs] “MCP clients can connect to `https://mcp.poly.app/mcp` (streamable HTTP). Authentication is OAuth: a browser window signs you into Poly on fi…”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”

   proof ↗⚑ flag

2. developerBuild my own plugins against a documented extension API/SDK with samples and developer docs

   weight 2 · round drawn
   Reflect—none0/10

   Reflect documents a limited OAuth2 REST API for appending data/links and deep-linking (reflect-docs-2,17,18,38), but this is not a plugin extension SDK, and community evidence explicitly states Reflect is 'fully functional without any plugins' by design, unlike Obsidian (reflect-comm-2). No plugin architecture, extension samples, or plugin developer docs exist.

   • [claimed-docs] “Our supports appending data to your notes, returning a list of the links you've bookmarked, and a few other things.”
   • [claimed-docs] “We do support OAuth's PKCE extension which means you can build a client to Reflect without shipping secret keys around.”
   • [community] “What drew me to Reflect (away from Obsidian) was full functionality out of the box without the need for plugins... Reflect is fully function…”

   proof ↗⚑ flag

   Poly—none0/10

   Evidence shows Poly ships an MCP server, a CLI, and an agent-skill file for its own CLI, but nothing documents a first-party extension API/SDK for developers to build their own Poly plugins — the 'plugin' references are about installing Poly's plugin into other agents (Claude, ChatGPT, VS Code), not the reverse. A direct probe for an OpenAPI/Swagger spec returned 404 on all candidate paths, and no developer SDK, plugin manifest format, or extension samples are mentioned anywhere in the docs pack.

   • [claimed-docs] “Use our plugin with leading agents like Claude, ChatGPT, and VS Code and make your file workflows insanely fast.”
   • [claimed-docs] “It automatically parses, transcribes, and indexes your files that make it up to 20x faster for an agent to read and understand them. Use our…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.poly.app/openapi.json, https://docs.poly.app/swagger.json, https://docs.poly.app/api/op…”
   • [probe] “official CLI documented at https://docs.poly.app/cli”
   • [probe] “official MCP server documented at https://docs.poly.app/integrations/using-mcp”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Reflect—none0/10

   No evidence anywhere in the pack mentions data residency, region selection, or storage location choices; Reflect discusses E2E encryption and export options but nothing about choosing where data is stored geographically.

   ⚑ flag

   Poly—none0/10

   No evidence in the pack addresses data residency, region selection, or storage location choice for Poly's cloud-hosted service; documentation focuses on features, sync, and MCP/CLI integrations without any regional/residency controls. Missing for 10: any mention of data center regions, residency options, or compliance-driven storage location settings.

   ⚑ flag

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

   weight 3 · round drawn
   Reflect—none0/10

   Reflect advertises end-to-end encryption of note content (reflect-docs-16, reflect-docs-35), which limits Reflect's own server-side access, but there is no explicit statement anywhere in the evidence about whether note content sent to third-party AI models (GPT-4o, Claude 3.5 Sonnet per reflect-docs-37) is used for model training, nor any opt-out/data-processing policy addressing AI training use. Community evidence even notes files/images are excluded from E2E encryption (reflect-comm-8), raising unaddressed questions rather than resolving them.

   • [claimed-docs] “End-to-end encryption keeps your notes secure.”
   • [claimed-docs] “The contents of your notes are end-to-end encrypted. No one else can read them (not even us).”
   • [claimed-docs] “Reflect's AI tools give you the option to now use either GPT-4o (the latest model from OpenAI) or Claude 3.5 Sonnet (the latest model from A…”
   • [community] “Question about Reflect's E2E encryption claims: 'We do not end-to-end encrypt things like files or images you upload' - user noted this excl…”

   proof ↗⚑ flag

   Poly—none0/10

   No evidence in the pack of any data-training opt-out, privacy policy, or model-training exclusion commitment from Poly; docs focus on file search/agent features, not data-usage privacy controls. Community comments raise general trust/security concerns but don't confirm or deny a training-opt-out policy, so this is an unaddressed gap rather than a dispute.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Reflect—none0/10

   Evidence covers export/backup, encryption, and API access, but there is no documentation or mention of account/data deletion, retention settings, or right-to-erasure controls anywhere in the pack.

   ⚑ flag

   Poly—none0/10

   The evidence pack covers file import, search, sharing, versioning, and MCP/CLI integrations, but contains no documentation on data retention policies, permanent deletion, or export/purge controls for an AI-native privacy-conscious user. Community comments raise general trust/security concerns but don't confirm or deny specific retention/deletion mechanisms. missing for 10: retention policy docs, account/file deletion controls, data export or purge guarantees, any first-party statement on how long data is kept or how to fully erase it.

   • [claimed-docs] “Even conflicting edits are preserved, so you can recover any version of any file at any time.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it. You stay the owner,…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Reflect—none0/10

   No evidence pack item discusses telemetry, analytics, usage tracking, or an opt-out/privacy settings toggle for such tracking; the evidence covers encryption, imports, AI features, and API access instead. Missing for 10: any mention of telemetry collection, opt-out settings, or a privacy policy addressing usage tracking.

   ⚑ flag

   Poly—none0/10

   No evidence in the pack addresses telemetry, analytics, or usage-tracking opt-out settings for Poly; the docs and community discussion cover file syncing, search, MCP integrations, and general privacy/security concerns about filesystem access, not telemetry controls.

   ⚑ flag

Publish

1. researcherPublish selected notes as a browsable website — a digital garden with working links — without leaving the app

   weight 2 · round to Reflect
   Reflect~partialclaimed5/10

   Reflect docs confirm one-click publishing of individual notes to a public URL with minimal branding, which supports sharing selected notes without leaving the app, but there is no evidence of a browsable multi-page 'digital garden' site (index/navigation) or confirmation that backlinks between published notes remain functional as working links. Missing for 10: evidence of a site-level index/navigation across multiple published notes, confirmation that internal links/backlinks resolve correctly between published pages, and any custom-domain or site-branding options.

   • [claimed-docs] “Reflect offers one-click publishing of your notes. Simply hit the publish button and your note will be publicly available behind a long hard…”
   • [claimed-docs] “We try to keep the style clean and branding to a minimum.”
   • [claimed-docs] “Backlinks are just a list of incoming links from other notes.”

   proof ↗⚑ flag

   Poly—none0/10

   Poly's evidence covers sharing individual files/folders via links or team drives (poly-docs-9, poly-docs-24, poly-docs-33) and journaling/Mind notes storage, but there is no mention of publishing a collection of notes as a browsable, interlinked website (digital garden) with working cross-links. Sharing appears to be file/folder link-based, not a rendered site with navigable note-to-note links.

   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it.”
   • [claimed-docs] “Share individual files with a link, or give a team its own storage space.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it. You stay the owner,…”
   • [claimed-docs] “Journaling gives you a quiet place to document your day-to-day life. Write a few thoughts, attach files, or add the broader context behind a…”

   proof ↗⚑ flag

Collaboration

1. researcherShare a vault or space with collaborators and edit notes together without stepping on each other's changes

   weight 2 · round to Poly
   Reflect—none0/10

   No evidence pack item mentions shared vaults/spaces, multi-user collaboration, or real-time co-editing/conflict resolution; Reflect's documented features are import/export, linking, AI, search, publishing, integrations, and E2E encryption for a single user's notes, with no mention of collaborative editing between multiple people.

   ⚑ flag

   Poly~partialclaimed5/10

   Poly supports sharing files/folders and creating team Shared Drives with members and roles, and it preserves conflicting edits so any version can be recovered, which addresses collaborative access and non-destructive conflict handling. However, this is file-versioning-based (conflicts are preserved as separate recoverable versions, not merged live), with no evidence of real-time co-editing, presence awareness, or seamless merge like a true multiplayer notes app. Missing for 10: real-time simultaneous editing support, live presence/cursor indicators, and conflict-free merge (vs. version preservation) for concurrent note edits.

   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it.”
   • [claimed-docs] “Share a file or folder when the content belongs to you and you want specific people — or anyone with a link — to see it. You stay the owner,…”
   • [claimed-docs] “Create a Shared Drive when the content belongs to a team rather than to a person. A Shared Drive is its own storage space with its own membe…”
   • [claimed-docs] “Even conflicting edits are preserved, so you can recover any version of any file at any time.”
   • [claimed-docs] “Share individual files with a link, or give a team its own storage space.”

   proof ↗⚑ flag

Sync

1. power-userAn official sync service keeps my notes updated across all my devices with end-to-end encryption the vendor can't read

   weight 3 · round to Reflect
   Reflect!disputedcontradicted5/10

   Reflect markets end-to-end encryption 'no one else can read them (not even us)' and syncs notes across devices as a core feature, but a founder-sourced community comment reveals a concrete carve-out: files/images uploaded are NOT end-to-end encrypted, contradicting the blanket vendor claim. Missing for 10: explicit documentation of sync architecture/conflict resolution across devices, independent security audit report details, and a full accounting of what content types are/aren't encrypted.

   • [claimed-docs] “End-to-end encryption keeps your notes secure.”
   • [claimed-docs] “The contents of your notes are end-to-end encrypted. No one else can read them (not even us).”
   • [community] “Question about Reflect's E2E encryption claims: 'We do not end-to-end encrypt things like files or images you upload' - user noted this excl…”
   • [community] “Reflect founder: 'We're building it as a lifestyle company. There's only four of us. We bootstrapped for a while, and then did a $1m crowdfu…”
   • [community] “Props to Reflect for their security audit too. I will be keeping an eye on how they progress.”

   proof ↗⚑ flag

   Poly—none0/10

   Poly's docs describe file sync (desktop folder sync, Finder tag sync, sharing, MCP/CLI integrations) but nowhere claim end-to-end encryption that the vendor itself cannot read; in fact the architecture explicitly routes files through Poly's servers for indexing/search, and community comments explicitly worry that Poly's remote servers read and analyze all files, contradicting the premise of vendor-blind E2EE. No evidence of an E2EE sync mechanism exists in the pack.

   • [claimed-docs] “your Poly files appear as a real folder in Finder or Explorer, with files downloading on demand and syncing back automatically.”
   • [claimed-docs] “Finder tags sync bidirectionally with Poly tags, colors included.”
   • [community] “Hooking up the Internet to my filesystem is scary. What security measures are in place to ensure a compromise of your infrastructure doesn't…”
   • [community] “With Google Drive, I choose which files to upload. It doesn't have broad access to everything on my computer... your service, by nature, is …”
   • [probe] “PROBE runtime (recorded 2026-09-14): keyless JSON-RPC initialize POST to Poly's hosted MCP server https://mcp.poly.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

2. power-userView a note's version history and restore earlier versions or recover deleted notes

   weight 2 · round to Reflect
   Reflect✓fullclaimed8/10

   Reflect's documentation explicitly states it continually records edits and lets users revert a note to any point in time, directly matching the version history/restore story (docs-8). Deleted note recovery isn't explicitly documented, so missing for 10: explicit documentation of deleted-note recovery/trash restoration, and independent hands-on corroboration of restore functionality.

   • [claimed-docs] “We continually record edits to notes which means you can see all your changes and revert a note to any point in time.”

   proof ↗⚑ flag

   Poly✓fullclaimed7/10

   Poly's docs explicitly describe file-level version history and recovery: 'flashback mode' lets you see exactly what files looked like at any past point, and edits/conflicts are preserved so 'you can recover any version of any file at any time' (poly-docs-5, poly-docs-10). Since notes (journal entries, Mind files) are just files synced in Poly, this recovery/versioning applies to them too. Missing for 10: no independent/hands-on verification of the restore UX specifically for notes, and no explicit mention of undeleting a note versus just reverting content.

   • [claimed-docs] “Go into flashback mode at any time to see exactly what your files looked like at any point in the past, down to the millisecond.”
   • [claimed-docs] “Even conflicting edits are preserved, so you can recover any version of any file at any time.”
   • [claimed-docs] “New journal entries are Markdown files synced to your **Mind** folder.”

   proof ↗⚑ flag