Stripe Financial Connections vs Plaid

Hosted flows

1. developerLet a user connect their bank with a drop-in hosted flow — create a session server-side, open the widget, and get back a token for the connected account — without building institution UI myself

   weight 3 · round drawn
   Stripe Financial Connections✓fullcommunity8/10

   Docs describe a server-side session (client_secret) that launches a hosted collectFinancialConnectionsAccounts widget with built-in institution selection across 12,000+ banks, returning connected account data and firing webhooks on link — exactly the drop-in flow described, and community reports confirm real-world adoption for ACH/fraud use cases (docs-6, docs-7, docs-12, comm-6). missing for 10: no explicit doc snippet naming a returned 'token' object schema, and no independent hands-on write-up specifically validating the create-session-then-widget code path (only high-level docs and general community sentiment).

   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [claimed-docs] “Users select their bank from frequently chosen institutions or by searching more than 12,000 supported banks.”
   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “the authentication flow exclusively shows a selection of test institutions managed by Stripe. The client can link accounts from any of these…”
   • [community] “I work at one of the companies that integrated Financial Connections during its beta, moving from Plaid Auth. We use the link to bank accoun…”

   proof ↗⚑ flag

   Plaid✓fullclaimed8/10

   Plaid Link is explicitly documented as the client-side hosted widget that lets users connect their bank without the developer building institution UI, paired with server-side session/token creation (public_token/access_token flow) shown in SDKs and Sandbox docs. missing for 10: no independent/hands-on developer report confirming the end-to-end token exchange experience, and no explicit token-exchange code snippet in this pack (only Sandbox/public_token creation and general Link description).

   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”
   • [claimed-docs] “You can customize parts of Link's flow straight from the Dashboard. You can preview your changes in real time and then publish them instantl…”
   • [claimed-docs] “you can also create Items in Sandbox via the API, using a special Sandbox-only endpoint, /sandbox/public_token/create. This endpoint allows …”
   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing. All Plaid functionality of both the Plai…”
   • [claimed-docs] “Let's test out running Plaid locally by cloning the Quickstart app. You'll need API keys, which you can receive by signing up in the Dashboa…”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”

   proof ↗⚑ flag

Oauth

1. developerConnections to major institutions use bank-hosted OAuth rather than screen-scraped credentials — the platform documents its OAuth coverage and how legacy credential flows are being retired

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   None of the docs mention OAuth explicitly, document which institutions use bank-hosted OAuth versus other methods, or describe retirement of legacy credential-based flows. In fact, community commentary indicates Stripe proxies to Plaid-like providers (i.e., non-OAuth/screen-scraping) for institutions lacking OAuth support, undermining the premise that connections are exclusively OAuth-based.

   • [community] “If Stripe can leverage their banking relationships to leapfrog Plaid by integrating directly with bank's APIs instead of screen scraping, th…”
   • [claimed-docs] “Users select their bank from frequently chosen institutions or by searching more than 12,000 supported banks.”
   • [claimed-docs] “You can use one integration to instantly verify bank accounts for ACH payments, reduce underwriting risk with balances data, mitigate fraud …”

   proof ↗⚑ flag

   Plaid—none0/10

   The evidence pack contains no Plaid documentation describing OAuth coverage for institutions or a plan to retire legacy credential/screen-scraping flows; docs only describe Auth/Balance/Identity/Transactions products generically. Community evidence in fact describes Plaid using screen-scraped credentials and even mimicking bank login pages, reinforcing the absence of documented OAuth-first coverage.

   • [community] “Plaid is terrible! Both Wells Fargo and Bank of America support API integration, but Plaid chooses to screen-scrape and does not work if you…”
   • [community] “Slightly off topic... Privacy virtual card use Plaid... The integration was extremely questionable. They were faking the bank's login page. …”
   • [community] “Teller does not use screen scraping. They reverse engineer each bank's mobile APIs — contrasted favorably against Plaid's approach in discus…”
   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”

   proof ↗⚑ flag

Repair

1. ops leadBroken connections are repairable — expired or revoked links surface as documented statuses, and users can re-authenticate in an update flow without starting over

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections~partialclaimed6/10

   Stripe documents a dedicated relink API to help reconnect an inactive/broken account, plus webhooks marking refresh completions (balance, ownership, transaction), implying some status tracking for account health. However, the pack lacks explicit documentation of distinct 'expired' vs 'revoked' status codes or a walkthrough showing the re-auth update flow preserving prior account context so users don't start over. missing for 10: explicit status enumeration for expired/revoked links, end-to-end UX documentation of the re-auth flow without data loss, and independent confirmation the relink flow works as described.

   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”
   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”

   proof ↗⚑ flag

   Plaid~partialclaimed3/10

   Plaid's webhook docs mention that webhooks inform developers about 'changes to Plaid Items or the status of asynchronous processes' (plaid-docs-8), which touches on connection status changes, and Link (plaid-docs-5, plaid-docs-11) is the client-side re-linking component. However, the evidence pack never explicitly documents the specific re-authentication 'update mode' flow, named error statuses like ITEM_LOGIN_REQUIRED, or confirmation that re-auth avoids re-onboarding from scratch. Missing for 10: explicit documentation of update-mode Link flow, named broken-connection status codes/webhooks, and confirmation users don't restart the full linking process.

   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”
   • [claimed-docs] “You can customize parts of Link's flow straight from the Dashboard. You can preview your changes in real time and then publish them instantl…”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections✓fullprobed8/10

   Stripe hosts a live llms.txt (HTTP 200) and markdown-formatted docs (financial-connections.md) confirmed by direct probes, and there's also agent-oriented documentation like use-cases.md with an explicit 'Financial insights for agents' section referencing agent-powered analysis tools. Missing for 10: independent/community confirmation that agents actually consume these docs successfully, and no dedicated llms.txt content specific to Financial Connections (it's the site-wide docs.stripe.com/llms.txt).

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.stripe.com/llms.txt # Stripe Documentation When installing Stripe packages, always check the npm r…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.stripe.com/financial-connections.md # Stripe Financial Connections Access permissioned data from yo…”
   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”

   proof ↗⚑ flag

   Plaid~partialprobed6/10

   Plaid has a live llms.txt at plaid.com/llms.txt (HTTP 200) confirming basic agent-oriented discovery, but the content is minimal (a short description, not a full doc index), the /docs/.md and openapi.json probes 404 rather than exposing machine-readable docs, and there's no independent corroboration of agents actually consuming these successfully. missing for 10: richer llms.txt content indexing full doc set, working markdown/OpenAPI endpoints, independent/hands-on evidence of an agent successfully using these to navigate docs.

   • [probe] “PROBE llms.txt: HTTP 200 at https://plaid.com/llms.txt # Plaid > Plaid helps all companies build fintech solutions by making it easy, safe …”
   • [probe] “PROBE docs-md: HTTP 404 at https://plaid.com/docs/.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plaid.com/openapi.json, https://plaid.com/swagger.json, https://plaid.com/api/openapi.json, …”

   proof ↗⚑ flag

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

   weight 2 · round to Plaid
   Stripe Financial Connections~partialprobed4/10

   Financial Connections exposes server-side webhooks and a documented testing mode where test institutions can be linked without credentials, which supports some automated/CI testing (docs-15, docs-26, docs-12/13/24/25), and Stripe's broader platform offers a CLI and MCP server for agent-driven automation (probe-4, probe-5, docs-18). However, the core account-linking flow requires a client-side authentication step (collectFinancialConnectionsAccounts) that is inherently interactive, not headless, for real accounts. Missing for 10: explicit documentation of a fully headless/server-only flow for production account linking, and independent confirmation that CI-only automation works end-to-end without any UI step.

   • [claimed-docs] “the authentication flow exclusively shows a selection of test institutions managed by Stripe. The client can link accounts from any of these…”
   • [claimed-docs] “The client can link accounts from any of these institutions without providing credentials.”
   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”
   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [probe] “official MCP server documented at https://docs.stripe.com/mcp”
   • [probe] “official CLI documented at https://docs.stripe.com/stripe-cli”

   proof ↗⚑ flag

   Plaid~partialclaimed6/10

   Plaid's Sandbox exposes a special API endpoint (/sandbox/public_token/create) that lets developers generate test Items and public tokens purely via API calls, without any UI, which supports scripted/headless testing suitable for CI (plaid-docs-14, plaid-docs-13). The Node SDK further demonstrates programmatic, promise-based server-side calls (plaid-gh-1, plaid-gh-2) that can run in automated pipelines. However, real (non-sandbox) account linking still requires the client-side Plaid Link UI component, so full production automation isn't headless, and no explicit CI/automation documentation or examples are provided. missing for 10: explicit CI/headless automation guide, confirmation that production flows can bypass Link UI, independent evidence of running Plaid in automated pipelines.

   • [claimed-docs] “you can also create Items in Sandbox via the API, using a special Sandbox-only endpoint, /sandbox/public_token/create. This endpoint allows …”
   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing. All Plaid functionality of both the Plai…”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”
   • [claimed-docs] “Let's test out running Plaid locally by cloning the Quickstart app. You'll need API keys, which you can receive by signing up in the Dashboa…”

   proof ↗⚑ flag

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

   weight 3 · round to Stripe Financial Connections
   Stripe Financial Connections✓fullprobed8/10

   Stripe documents an official MCP server that lets AI agents interact with the Stripe API and knowledge base, and Financial Connections docs explicitly call out an agent use case ('Financial insights for agents' with agent-powered spending analysis and balance/transaction monitoring), confirmed by a live docs probe at docs.stripe.com/mcp. Missing for 10: independent/hands-on confirmation that Financial Connections-specific tools (balances, transactions, ownership) are exposed via the MCP server, and no community reports of using it.

   • [claimed-docs] “The Stripe Model Context Protocol (MCP) server provides tools that AI agents can use to interact with the Stripe API and search Stripe’s kno…”
   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”
   • [probe] “official MCP server documented at https://docs.stripe.com/mcp”

   proof ↗⚑ flag

   Plaid~partialprobed7/10

   Plaid documents an official 'Dashboard MCP server' hosted by Plaid providing Production diagnostics and analytics tools (debugging Items, Link conversion data, usage metrics), confirmed by both docs and a probe hit. However, this MCP server is scoped only to dashboard/analytics functions rather than full API/product access (Auth, Transactions, Identity, etc.), so an agent cannot use it to perform general Plaid operations via MCP. Missing for 10: MCP coverage of core Plaid API functionality (Auth, Transactions, Payments) and independent/community corroboration of real-world MCP usage.

   • [claimed-docs] “The Dashboard MCP server is a remote MCP server hosted by Plaid. It provides Production diagnostics and analytics tools, including tools for…”
   • [probe] “official MCP server documented at https://plaid.com/docs/resources/mcp/”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections✓fullprobed7/10

   Stripe provides an official Stripe CLI documented at docs.stripe.com/stripe-cli, which applies across Stripe products including Financial Connections, and this is a first-party, well-documented tool rather than just a wrapper. missing for 10: Financial Connections-specific CLI usage examples/workflows and independent hands-on corroboration of CLI use for this product's API.

   • [probe] “official CLI documented at https://docs.stripe.com/stripe-cli”

   proof ↗⚑ flag

   Plaid—none0/10

   Evidence shows Plaid SDKs (e.g., plaid-node), Quickstart apps, and a hosted MCP server, but no mention anywhere of an official CLI tool for interacting with Plaid's API or dashboard.

   ⚑ flag

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

   weight 3 · round to Plaid
   Stripe Financial Connections~partialprobed6/10

   Stripe Financial Connections is documented via Stripe's broader public REST API and webhooks (account linking, balance/ownership/transaction refresh events, relink API), and Stripe provides an official MCP server for AI agents to interact with the Stripe API plus a documented CLI, which together support agent-driven use. However, evidence doesn't show Financial Connections-specific MCP tools or agent-native documentation beyond a generic 'Financial insights for agents' use-case mention, and no independent corroboration of agents successfully driving this specific product exists. Missing for 10: dedicated Financial Connections MCP tool documentation, hands-on/independent verification of agentic API usage for this product specifically, and full OpenAPI spec discoverability (404s found).

   • [claimed-docs] “The Stripe Model Context Protocol (MCP) server provides tools that AI agents can use to interact with the Stripe API and search Stripe’s kno…”
   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”
   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [probe] “official MCP server documented at https://docs.stripe.com/mcp”
   • [probe] “official CLI documented at https://docs.stripe.com/stripe-cli”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.stripe.com/openapi.json, https://docs.stripe.com/swagger.json, https://docs.stripe.com/…”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”

   proof ↗⚑ flag

   Plaid~partialprobed7/10

   Plaid provides extensive public API documentation (Auth, Balance, Identity, Transactions, Payment Initiation), SDKs (plaid-node), webhooks, and a Sandbox for programmatic testing, all of which let a developer (including an AI agent) drive the product via documented endpoints. However, there's no discoverable OpenAPI/Swagger spec (404s on all candidate paths) and no llms.txt-style machine-readable API map beyond a generic landing page, which limits pure agentic/machine-driven discovery. missing for 10: publicly discoverable OpenAPI/machine-readable spec, evidence of AI-agent-specific API tooling beyond the separate Dashboard MCP server.

   • [claimed-docs] “Auth allows you to request a user's checking, savings, or cash management account and routing number, making it easy for you to initiate cre…”
   • [claimed-docs] “Balance is Plaid's product for receiving real-time balance information. This data is commonly used to tell if an account has sufficient fund…”
   • [claimed-docs] “Plaid's Identity product helps you verify users' identities by accessing information on file with their financial institution.”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing... you can create an unlimited number of …”
   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [claimed-docs] “you can also create Items in Sandbox via the API, using a special Sandbox-only endpoint, /sandbox/public_token/create. This endpoint allows …”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”
   • [probe] “PROBE docs-md: HTTP 404 at https://plaid.com/docs/.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plaid.com/openapi.json, https://plaid.com/swagger.json, https://plaid.com/api/openapi.json, …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   The evidence pack covers Financial Connections' bank-linking, data-access, and webhook features, plus a generic Stripe MCP server for agent API access, but nothing about issuing scoped or least-privilege API credentials/keys specifically for agents. No mention of restricted API keys, credential scoping, or permission granularity for agentic use is present.

   ⚑ flag

   Plaid—none0/10

   Plaid's evidence covers products (Auth, Balance, Identity, Transactions), Sandbox testing, Link, and a read-only diagnostics MCP server, but nothing describes issuing scoped or least-privilege API credentials/tokens specifically for an agent or any granular permissioning model for AI-native use. Missing for 10: any documentation of scoped API keys, credential minimization, or agent-specific access tokens.

   • [claimed-docs] “The Dashboard MCP server is a remote MCP server hosted by Plaid. It provides Production diagnostics and analytics tools, including tools for…”
   • [claimed-docs] “Let's test out running Plaid locally by cloning the Quickstart app. You'll need API keys, which you can receive by signing up in the Dashboa…”
   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing... you can create an unlimited number of …”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections✓fullprobed7/10

   Stripe provides official SDKs and client integration methods (e.g., collectFinancialConnectionsAccounts) for Financial Connections, plus a documented official CLI and an official MCP server enabling AI agents to interact with Stripe APIs including this product, and docs explicitly mention 'Financial insights for agents' use cases. missing for 10: independent hands-on developer confirmation of building an AI-native agent integration specifically with Financial Connections via SDK/MCP, and no explicit SDK code samples in multiple languages shown in evidence.

   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”
   • [claimed-docs] “The Stripe Model Context Protocol (MCP) server provides tools that AI agents can use to interact with the Stripe API and search Stripe’s kno…”
   • [probe] “official MCP server documented at https://docs.stripe.com/mcp”
   • [probe] “official CLI documented at https://docs.stripe.com/stripe-cli”

   proof ↗⚑ flag

   Plaid~partialclaimed6/10

   Plaid ships an official Node.js SDK (plaid-node) with documented async/await error-handling patterns and a quickstart guide showing API-key based setup, which supports building integrations programmatically. However, the evidence pack only shows one language SDK, no explicit mention of other official SDKs (Python, Java, Go, etc.) or SDK features tailored to AI-native/agentic workflows, and no independent corroboration of SDK quality. missing for 10: evidence of multi-language official SDKs, AI-specific SDK tooling or agent integration guides, independent developer corroboration of SDK usability.

   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”
   • [claimed-docs] “Let's test out running Plaid locally by cloning the Quickstart app. You'll need API keys, which you can receive by signing up in the Dashboa…”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Stripe Financial Connections✓fullclaimed7/10

   Stripe Financial Connections documents specific webhook events (account linked, balance/ownership/transaction refresh completed) that any integrator, including AI-native agent backends, can subscribe to for event-driven workflows. This is standard first-party webhook documentation but lacks AI-specific framing or independent corroboration of agentic webhook consumption. Missing for 10: independent/hands-on confirmation of AI agents consuming these webhooks, and explicit agent-oriented event subscription guidance.

   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”

   proof ↗⚑ flag

   Plaid✓fullclaimed7/10

   Plaid documents a first-class webhooks system that notifies subscribers of Item/product state changes (e.g., new transactions), which any AI-native integration could consume just like a human-built app. Missing for 10: independent/hands-on corroboration of webhook reliability and any agent-specific guidance for consuming webhooks programmatically.

   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections~partialprobed3/10

   Docs list 'Financial insights for agents' with 'Agent-powered spending analysis' and 'Balance and transaction monitoring' as a named use case, and Stripe's MCP server lets AI agents query account data — but these are thin, high-level mentions rather than a documented native AI-insights feature inside the Financial Connections product itself; the core product is described as raw data access (balances, transactions, ownership) for developers to build on, not an insight-generation UI. Missing for 10: concrete documentation of an actual AI-generated insights/suggestions feature, UI screenshots or workflow showing insights surfaced to end users, and independent/hands-on confirmation that agent-powered analysis works as described.

   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”
   • [claimed-docs] “The Stripe Model Context Protocol (MCP) server provides tools that AI agents can use to interact with the Stripe API and search Stripe’s kno…”
   • [probe] “official MCP server documented at https://docs.stripe.com/mcp”
   • [claimed-docs] “Access an account’s current and available balances.”
   • [claimed-docs] “Access an account’s transaction history.”

   proof ↗⚑ flag

   Plaid—none0/10

   No evidence that Plaid generates AI-driven insights or suggestions from a user's financial data; the closest item (Dashboard MCP server) only exposes diagnostics/analytics tools for developers, not AI-generated insights delivered to end users. Missing for 10: any AI/ML insight-generation feature, natural-language summarization of transactions/balances, or user-facing recommendation engine.

   • [claimed-docs] “The Dashboard MCP server is a remote MCP server hosted by Plaid. It provides Production diagnostics and analytics tools, including tools for…”

   proof ↗⚑ flag

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

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections~partialclaimed5/10

   Financial Connections supports webhook events (account linked, balance/ownership/transaction refresh completed) and a relink API, which let developers build background automations that react to account/data changes without manual polling, and docs even reference an 'agent-powered spending analysis' use case. However, there's no evidence of built-in scheduling, orchestration, or agent-specific automation tooling beyond webhooks — it's infrastructure a developer must wire up themselves. Missing for 10: native scheduling/orchestration primitives, explicit AI-agent automation framework, and hands-on evidence of autonomous background agents running on this data.

   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”
   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”

   proof ↗⚑ flag

   Plaid~partialclaimed3/10

   Plaid provides webhooks and transactionsSync for asynchronous, background processing of financial data changes (docs-8, gh-1), which could underpin automations, but there is no evidence of any AI-native automation/agent orchestration capability, scheduling, or autonomous workflow builder — the Dashboard MCP server is limited to diagnostics/analytics, not automation setup. Missing for 10: explicit automation/agent framework, scheduling or trigger-action tooling, and any AI-native framing of background autonomy beyond generic webhooks.

   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [claimed-docs] “The Dashboard MCP server is a remote MCP server hosted by Plaid. It provides Production diagnostics and analytics tools, including tools for…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Stripe Financial Connections~partialprobed4/10

   Stripe's docs mention an 'agent-powered spending analysis' use case for Financial Connections and Stripe's general MCP server lets AI agents call the Stripe API, implying some natural-language operability, but there's no detailed documentation of specific natural-language commands or agent workflows scoped to Financial Connections itself. Missing for 10: concrete examples of NL commands/agent interactions specific to Financial Connections, independent/hands-on validation that agents can operate this product conversationally, and clarity on how much of the flow (bank auth, consent) can be agent-driven vs. requiring a human UI step.

   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”
   • [claimed-docs] “The Stripe Model Context Protocol (MCP) server provides tools that AI agents can use to interact with the Stripe API and search Stripe’s kno…”
   • [probe] “official MCP server documented at https://docs.stripe.com/mcp”

   proof ↗⚑ flag

   Plaid~partialprobed4/10

   Plaid documents an official 'Dashboard MCP server' that exposes diagnostics/analytics tools (debugging Items, Link conversion data, usage metrics) which an AI agent could invoke via natural language, but this only covers dashboard operations, not the core product functionality (Auth, Transactions, Identity, Payments) — there is no broader natural-language interface for operating Plaid's main capabilities. Missing for 10: NL control over core Plaid products (linking, transactions, payments), independent/hands-on confirmation of MCP usability, and any conversational agent interface beyond dashboard diagnostics.

   • [claimed-docs] “The Dashboard MCP server is a remote MCP server hosted by Plaid. It provides Production diagnostics and analytics tools, including tools for…”
   • [probe] “official MCP server documented at https://plaid.com/docs/resources/mcp/”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   The evidence pack shows only text-based documentation pages (feature descriptions, webhooks list, testing docs) and confirms no OpenAPI spec was found at any candidate path (probe-3: all 404). There is no mention of an interactive API reference, live code runner, or runnable examples for Financial Connections specifically.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.stripe.com/openapi.json, https://docs.stripe.com/swagger.json, https://docs.stripe.com/…”
   • [claimed-docs] “Access an account’s current and available balances.”

   proof ↗⚑ flag

   Plaid—none0/10

   Evidence shows only static docs pages, a Quickstart sample app to clone locally, and a Sandbox test environment, but no interactive API reference (e.g., try-it console, embedded runnable code snippets) — probes for an OpenAPI spec and docs-as-markdown interactive surface both returned 404s, suggesting no such interactive reference exists.

   • [claimed-docs] “Let's test out running Plaid locally by cloning the Quickstart app. You'll need API keys, which you can receive by signing up in the Dashboa…”
   • [probe] “PROBE docs-md: HTTP 404 at https://plaid.com/docs/.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plaid.com/openapi.json, https://plaid.com/swagger.json, https://plaid.com/api/openapi.json, …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   A direct probe for OpenAPI/swagger specs at expected doc paths returned 404 for all candidates, and no other evidence in the pack shows a downloadable machine-readable API spec for Financial Connections; only markdown docs (.md) and llms.txt are available, which are not an OpenAPI-equivalent spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.stripe.com/openapi.json, https://docs.stripe.com/swagger.json, https://docs.stripe.com/…”

   proof ↗⚑ flag

   Plaid—none0/10

   Direct probes for OpenAPI/swagger spec files at standard paths all returned 404, and no documentation references a downloadable machine-readable API spec; only an llms.txt marketing page was found, not an OpenAPI/equivalent spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://plaid.com/openapi.json, https://plaid.com/swagger.json, https://plaid.com/api/openapi.json, …”
   • [probe] “PROBE docs-md: HTTP 404 at https://plaid.com/docs/.md”
   • [probe] “PROBE llms.txt: HTTP 200 at https://plaid.com/llms.txt # Plaid > Plaid helps all companies build fintech solutions by making it easy, safe …”

   proof ↗⚑ flag

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

   weight 1 · round to Plaid
   Stripe Financial Connections✓fullclaimed7/10

   Stripe documents a dedicated testing mode where the authentication flow shows only Stripe-managed test institutions and accounts can be linked without real credentials, explicitly separating sandbox testing from production data access. Missing for 10: no explicit mention of a fully isolated test API key/environment guarantee for financial data, no independent hands-on confirmation of sandbox fidelity, and no detail on how test data maps to production behavior.

   • [claimed-docs] “the authentication flow exclusively shows a selection of test institutions managed by Stripe. The client can link accounts from any of these…”
   • [claimed-docs] “The client can link accounts from any of these institutions without providing credentials.”

   proof ↗⚑ flag

   Plaid✓fullclaimed8/10

   Plaid provides a dedicated, fully-featured Sandbox environment supporting all API/Link functionality with unlimited test Items and test credentials, plus a special sandbox-only endpoint for programmatic Item creation, clearly separating test from production data. missing for 10: no independent/hands-on developer corroboration of sandbox fidelity, and no explicit mention of AI-agent-specific sandbox testing workflows.

   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing... you can create an unlimited number of …”
   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing. All Plaid functionality of both the Plai…”
   • [claimed-docs] “you can also create Items in Sandbox via the API, using a special Sandbox-only endpoint, /sandbox/public_token/create. This endpoint allows …”
   • [claimed-docs] “Let's test out running Plaid locally by cloning the Quickstart app. You'll need API keys, which you can receive by signing up in the Dashboa…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   No evidence pack items reference API versioning, version headers, or a documented deprecation policy for Stripe Financial Connections; only feature descriptions, webhooks, and community sentiment are present.

   ⚑ flag

   Plaid—none0/10

   The evidence pack contains no documentation of API versioning scheme or a deprecation policy — no changelog, version headers, or sunset timeline are mentioned anywhere, only product feature docs (Auth, Balance, Identity, Transactions) and SDK error-handling snippets.

   ⚑ flag

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

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   No evidence of bulk/batch operations (e.g., batch account linking, bulk transaction pulls, multi-item API calls) for AI-native automation; the closest evidence is a webhook that emits one event per linked account, which is not a bulk-operation capability.

   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”

   proof ↗⚑ flag

   Plaid—none0/10

   Plaid's docs describe per-Item operations (Auth, Balance, Identity, Transactions, sandbox item creation) and webhooks, but no evidence shows a bulk/batch API for operating across many Items simultaneously (e.g., no bulk sync, bulk webhook re-fire, or multi-item query endpoint documented).

   ⚑ flag

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

   weight 3 · round to Plaid
   Stripe Financial Connections—none0/10

   Financial Connections offers webhooks for events (account linked, balance refresh, etc.) but there is no evidence of a rules engine or automation layer where users can define conditional rules that trigger actions on those events—developers would need to build that logic themselves outside the product. missing for 10: rule-definition interface, conditional trigger-action mapping, any built-in automation/workflow engine.

   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”

   proof ↗⚑ flag

   Plaid~partialclaimed4/10

   Plaid provides webhooks that notify developers of events (item changes, transaction updates, async completions), which can be used to build automated reactions, but there is no evidence of a declarative rules engine where an AI-native user defines 'if event X then action Y' logic directly within Plaid—developers must write their own handling code. Missing for 10: a native rule/condition-action builder, AI-triggered automation config, or no-code trigger definitions beyond raw webhook payloads.

   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Stripe Financial Connections—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

   Plaid—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

Ach details

1. developerObtain verified account and routing numbers (or tokenized equivalents) from a linked account to fund ACH or bank-debit payments without micro-deposits

   weight 3 · round drawn
   Stripe Financial Connections✓fullcommunity8/10

   Docs explicitly describe an 'instant' verification flow with 'no manual entry and microdeposit fallback' for ACH Direct Debit, collecting bank account + ownership/balance data in one integration, eliminating the need for users to locate account/routing numbers, and a real-world adopter (comm-6) confirms using it for instant account verification and ACH fraud signaling in production, replacing Plaid Auth. Missing for 10: explicit technical detail on the exact token/PaymentMethod format returned to the server and any independent benchmarking of ACH failure-rate reduction beyond Stripe's own claims.

   • [claimed-docs] “instant | Financial Connections only, with no manual entry and microdeposit fallback”
   • [claimed-docs] “Reduce your payment failure rate from closed or inactive accounts - Improve payments conversion by keeping users on session, instead of forc…”
   • [claimed-docs] “Collect a bank account for ACH Direct Debit payments while using account data, including balances.”
   • [claimed-docs] “Save development time by eliminating the need to create a custom bank account collection form”
   • [community] “I work at one of the companies that integrated Financial Connections during its beta, moving from Plaid Auth. We use the link to bank accoun…”

   proof ↗⚑ flag

   Plaid✓fullclaimed8/10

   Plaid Auth explicitly provides checking/savings/cash management account and routing numbers to initiate ACH/wire debits/credits without micro-deposits, and is paired with Balance and Identity for verification, with Sandbox/Link supporting full dev testing. missing for 10: no independent/hands-on corroboration of micro-deposit-free instant verification success rate, and no explicit mention of tokenized-equivalent output formats.

   • [claimed-docs] “Auth allows you to request a user's checking, savings, or cash management account and routing number, making it easy for you to initiate cre…”
   • [claimed-docs] “Balance is Plaid's product for receiving real-time balance information. This data is commonly used to tell if an account has sufficient fund…”
   • [claimed-docs] “Plaid's Identity product helps you verify users' identities by accessing information on file with their financial institution.”
   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”
   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing. All Plaid functionality of both the Plai…”

   proof ↗⚑ flag

Balances

1. developerFetch a real-time balance for a connected account before initiating a payment — a documented balance endpoint intended for NSF and risk checks

   weight 3 · round to Plaid
   Stripe Financial Connections✓fullcommunity7/10

   Docs explicitly state Financial Connections lets you 'Access an account's current and available balances' and 'reduce underwriting risk with balances data', with a dedicated balance-refresh webhook event, and community evidence confirms real customers use the linked-account data as a fraud/risk signal before ACH debits. This matches the NSF/risk-check use case described in the story. missing for 10: explicit API reference/endpoint schema for the balance object, and confirmation of real-time (vs refresh-triggered) latency guarantees.

   • [claimed-docs] “Access an account’s current and available balances.”
   • [claimed-docs] “Collect a bank account for ACH Direct Debit payments while using account data, including balances.”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “reduce underwriting risk with balances data”
   • [community] “I work at one of the companies that integrated Financial Connections during its beta, moving from Plaid Auth. We use the link to bank accoun…”

   proof ↗⚑ flag

   Plaid✓fullclaimed8/10

   Plaid's Balance product is explicitly documented as a real-time balance endpoint used to check sufficient funds before using an account as a payment funding source, directly matching the NSF/risk-check use case. missing for 10: independent hands-on developer confirmation of the /accounts/balance/get endpoint behavior and no explicit mention of latency/SLA guarantees for pre-payment checks.

   • [claimed-docs] “Balance is Plaid's product for receiving real-time balance information. This data is commonly used to tell if an account has sufficient fund…”

   proof ↗⚑ flag

Ownership

1. ops leadRetrieve account-holder details — names, addresses, contact data on file at the bank — to match the account owner against my customer

   weight 2 · round drawn
   Stripe Financial Connections✓fullcommunity8/10

   Docs explicitly state you can 'Access account owners' names and mailing addresses' and 'mitigate fraud by verifying account ownership details,' plus an ownership-refresh webhook event confirms this data can be kept current for ownership matching. Community evidence corroborates real-world use as a fraud/ownership signal for ACH payments. Missing for 10: explicit documentation of contact/phone/email fields beyond name+address, and independent hands-on verification of the exact data schema returned.

   • [claimed-docs] “Access account owners’ names and mailing addresses.”
   • [claimed-docs] “mitigate fraud by verifying account ownership details”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [community] “I work at one of the companies that integrated Financial Connections during its beta, moving from Plaid Auth. We use the link to bank accoun…”

   proof ↗⚑ flag

   Plaid✓fullclaimed8/10

   Plaid's Identity product is explicitly documented to return name, phone, email, and mailing address on file with the account holder's financial institution, directly matching the ops-lead need to verify account-owner identity against a customer record. Missing for 10: no independent/hands-on corroboration of match-accuracy or match-rate quality, and no explicit description of a 'match' scoring feature (e.g., identity match API) beyond raw data retrieval.

   • [claimed-docs] “Plaid's Identity product helps you verify users' identities by accessing information on file with their financial institution.”
   • [claimed-docs] “Plaid's Identity product helps you verify users' identities by accessing information on file with their financial institution. Using Identit…”

   proof ↗⚑ flag

Processor tokens

1. developerLinked accounts plug into my payment processor — documented integrations or token exchange that hand verified account credentials to third-party processors and platforms

   weight 2 · round drawn
   Stripe Financial Connections✓fullcommunity8/10

   Stripe's docs describe explicit, well-documented integrations where Financial Connections hands verified bank-account data (balances, ownership, transactions) to other Stripe payment products—ACH Direct Debit collection, Connect payouts, and underwriting/fraud tooling—via a documented client_secret/token exchange flow and webhooks, and a Hacker News commenter confirms real-world production use for ACH verification and fraud signals alongside other Stripe products. missing for 10: evidence of handoff to non-Stripe third-party processors/platforms specifically, and independent security review of the credential-exchange mechanism.

   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [claimed-docs] “Collect a bank account for ACH Direct Debit payments while using account data, including balances.”
   • [claimed-docs] “Collect a bank account to use for Connect payouts, and use account data, such as ownership details, with your integration.”
   • [claimed-docs] “instant | Financial Connections only, with no manual entry and microdeposit fallback”
   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [community] “I work at one of the companies that integrated Financial Connections during its beta, moving from Plaid Auth. We use the link to bank accoun…”

   proof ↗⚑ flag

   Plaid✓fullclaimed8/10

   Plaid's Auth product explicitly hands over verified account and routing numbers to enable third-party ACH/wire debits/credits, and Payment Initiation extends this to real-time European bank transfers without manual entry, with Balance/Identity supplementing verification data used by payment processors. This is documented as a core first-party capability (token exchange via Link → API access to account credentials for downstream money movement). missing for 10: named case studies/integrations with specific processors (e.g., Stripe), independent technical corroboration of the token-exchange flow beyond docs.

   • [claimed-docs] “Auth allows you to request a user's checking, savings, or cash management account and routing number, making it easy for you to initiate cre…”
   • [claimed-docs] “Balance is Plaid's product for receiving real-time balance information. This data is commonly used to tell if an account has sufficient fund…”
   • [claimed-docs] “Plaid's European Payments suite enables your users to make real-time payments without manually entering their account details or leaving you…”
   • [claimed-docs] “Plaid's European Payments suite enables your users to make real-time payments without manually entering their account details or leaving you…”
   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”

   proof ↗⚑ flag

Agent data

1. ai-native userThe data comes back agent-consumable — clean structured JSON, documented schemas, and enrichment an automated financial workflow can reason over without heuristic parsing

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections~partialprobed6/10

   Stripe's docs show structured API objects for balances, ownership, and transactions plus typed webhook events (docs-2,3,4,12-14,24,25), and even a dedicated 'Financial insights for agents' use-case section citing agent-powered spending analysis and balance/transaction monitoring (docs-11), supporting agent-consumable data. However, no OpenAPI/schema file could be found (probe-3 shows all openapi.json paths 404), and there's no independent/hands-on evidence confirming an agent can parse this data without additional tooling. Missing for 10: published OpenAPI/JSON schema docs, and independent corroboration of agent-consumability beyond Stripe's own docs.

   • [claimed-docs] “Access an account’s current and available balances.”
   • [claimed-docs] “Access account owners’ names and mailing addresses.”
   • [claimed-docs] “Access an account’s transaction history.”
   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”
   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.stripe.com/openapi.json, https://docs.stripe.com/swagger.json, https://docs.stripe.com/…”

   proof ↗⚑ flag

   Plaid~partialprobed5/10

   Plaid's docs describe structured JSON products (Auth, Balance, Identity, Transactions) with clear semantics and webhooks for async updates, and SDKs show typed request/response handling with try/catch error parsing, suggesting machine-consumable output. However, there's no evidence of a public OpenAPI/JSON-schema spec (probe explicitly found 404s for openapi.json/swagger.json), and no documentation of transaction enrichment/categorization features an agent could reason over without extra parsing logic. Missing for 10: published OpenAPI or JSON schema definitions, explicit enrichment/categorization documentation, and independent confirmation that outputs require no heuristic post-processing.

   • [claimed-docs] “Auth allows you to request a user's checking, savings, or cash management account and routing number, making it easy for you to initiate cre…”
   • [claimed-docs] “Balance is Plaid's product for receiving real-time balance information. This data is commonly used to tell if an account has sufficient fund…”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plaid.com/openapi.json, https://plaid.com/swagger.json, https://plaid.com/api/openapi.json, …”

   proof ↗⚑ flag

Agent operations

1. ai-native userAn agent can operate the platform — create link sessions, retrieve balances and transactions, and manage connections through the API or an MCP surface with scoped credentials

   weight 3 · round drawn
   Stripe Financial Connections~partialprobed6/10

   Financial Connections' API clearly supports creating link sessions, retrieving balances/transactions, and managing connections (docs-2,3,4,5,6,14), and Stripe publishes both a generic MCP server for AI agents to interact with the Stripe API (docs-18, probe-4) and an explicit 'Financial insights for agents' use case mentioning agent-powered spending analysis and balance/transaction monitoring (docs-11). However, no evidence specifies that the MCP surface exposes Financial-Connections-specific tools (e.g., create_link_session, get_balances) or how scoped/restricted credentials are issued for agent use. missing for 10: explicit MCP tool list for Financial Connections actions, documentation of scoped-credential/permission model for agent access, independent confirmation of agent operation end-to-end.

   • [claimed-docs] “Access an account’s current and available balances.”
   • [claimed-docs] “Access an account’s transaction history.”
   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”
   • [claimed-docs] “The Stripe Model Context Protocol (MCP) server provides tools that AI agents can use to interact with the Stripe API and search Stripe’s kno…”
   • [probe] “official MCP server documented at https://docs.stripe.com/mcp”

   proof ↗⚑ flag

   Plaid~partialprobed6/10

   Plaid's REST API comprehensively covers the core story — creating Link sessions (plaid-docs-5), retrieving balances (plaid-docs-2), pulling transactions (plaid-docs-4, plaid-gh-1), and managing connections/Items via webhooks (plaid-docs-8) — and SDKs like plaid-node make this scriptable by an agent. However, the only documented MCP surface is the Dashboard MCP server, which is scoped to Production diagnostics/analytics (debugging Items, Link conversion, usage metrics) rather than operational banking actions like initiating Link or pulling balances/transactions (plaid-docs-9, plaid-probe-4). Missing for 10: an MCP surface (or equivalent agent-native interface) that actually performs Link session creation/balance/transaction retrieval, and explicit documentation of scoped/limited credentials designed for autonomous agent use rather than server-side API keys.

   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”
   • [claimed-docs] “Balance is Plaid's product for receiving real-time balance information. This data is commonly used to tell if an account has sufficient fund…”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [claimed-docs] “The Dashboard MCP server is a remote MCP server hosted by Plaid. It provides Production diagnostics and analytics tools, including tools for…”
   • [probe] “official MCP server documented at https://plaid.com/docs/resources/mcp/”

   proof ↗⚑ flag

Consent

1. ops leadEnd users can see and revoke what they've shared — a documented consent surface or portal where a user manages which apps hold access to their bank data

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   No evidence describes an end-user-facing consent dashboard or portal where users can view/revoke which apps hold access to their linked bank data; documentation only covers merchant-side integration flows (linking, webhooks, relink API) and business-side account/balance/transaction access controls. This is a fair axis for a financial data aggregation product (competitors offer such portals), but Stripe's evidence pack contains no mention of a user-facing consent management surface.

   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”
   • [claimed-docs] “allowing them to save and reuse their bank account details across Stripe businesses”

   proof ↗⚑ flag

   Plaid—none0/10

   The evidence pack contains no documentation of a Plaid-hosted consent management portal or dashboard where end users can view or revoke connected apps' access to their bank data; Plaid Link (docs-5) only covers the initial linking/consent flow, not ongoing management or revocation. Community comments even show a user explicitly asking how to revoke Plaid's access with no clear answer, reinforcing the absence of a documented self-service revocation surface.

   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”
   • [community] “I gave them access to my bank via coinbase. If I change my bank password would they lose access to my account? If not, what do I need to do …”

   proof ↗⚑ flag

Deletion

1. ops leadSever and clean up — a documented way to delete a connection or user and have the platform stop collecting and purge held data

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   No evidence pack item documents a disconnect/delete-account API, data deletion/purge process, or account termination workflow for Financial Connections; the docs focus on connecting, collecting, and refreshing account data, not severing/purging it. Missing for 10: documented disconnect/delete API or account endpoint, data retention/purge policy, and any confirmation that collection stops and data is deleted upon disconnection.

   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.stripe.com/financial-connections.md # Stripe Financial Connections Access permissioned data from yo…”

   proof ↗⚑ flag

   Plaid—none0/10

   The evidence pack contains no documentation of an item/access-token deletion endpoint, account disconnection flow, or data purge/retention policy — only product feature docs (Auth, Balance, Identity, Transactions) and Sandbox/dashboard mentions. A community comment even shows a user asking how to revoke Plaid's bank access with no clear answer surfaced, reinforcing the absence of a documented sever-and-purge mechanism in the pack.

   • [community] “I gave them access to my bank via coinbase. If I change my bank password would they lose access to my account? If not, what do I need to do …”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”

   proof ↗⚑ flag

Scopes

1. developerI request only the data scopes I need — product-scoped consents and documented data-minimization controls, not an all-or-nothing grant

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections~partialclaimed6/10

   Docs show Financial Connections lets you request specific data types (balances, ownership, transactions) rather than a single blanket account link, and different use-case flows (ACH, Connect payouts, personal finance apps) pull only the subset of data relevant to that use case, implying product-scoped consent. However, there's no explicit documentation of a formal 'permissions' parameter/API, no description of the actual consent screen showing scoped checkboxes, and no independent/community evidence confirming data-minimization behavior in practice. Missing for 10: explicit permissions/scopes API reference, documented consent UI mechanics, and independent verification that only requested scopes are granted.

   • [claimed-docs] “Access an account’s current and available balances.”
   • [claimed-docs] “Access account owners’ names and mailing addresses.”
   • [claimed-docs] “Access an account’s transaction history.”
   • [claimed-docs] “Collect a bank account for ACH Direct Debit payments while using account data, including balances.”
   • [claimed-docs] “Collect a bank account to use for Connect payouts, and use account data, such as ownership details, with your integration.”
   • [claimed-docs] “Collect user accounts and gain access to account data to build more complex integrations, such as personal finance apps.”

   proof ↗⚑ flag

   Plaid!disputedcontradicted4/10

   Plaid's docs show genuinely separate, scopeable products (Auth, Balance, Identity, Transactions, Payment Initiation) that a developer can choose to request individually rather than one monolithic grant, which supports a product-scoped consent model. However, independent/community reports concretely contradict the 'data-minimization by design' claim: users report Plaid flows give 'no indication... you're likely giving away much more than just the bare minimum' and that dark patterns lead to over-broad grants (transaction, identity, balance data) beyond what the integrating app needs. Missing for 10: first-party documentation of a scoped-consent UI/permission screen, independent audit confirming least-privilege enforcement, and no rebuttal to the dark-pattern complaints.

   • [claimed-docs] “Auth allows you to request a user's checking, savings, or cash management account and routing number, making it easy for you to initiate cre…”
   • [claimed-docs] “Balance is Plaid's product for receiving real-time balance information. This data is commonly used to tell if an account has sufficient fund…”
   • [claimed-docs] “Plaid's Identity product helps you verify users' identities by accessing information on file with their financial institution.”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [claimed-docs] “Plaid's European Payments suite enables your users to make real-time payments without manually entering their account details or leaving you…”
   • [community] “Have to say I'm not a fan of Plaid at all. Dark patterns galore. Absolutely no indication when you go through a Plaid flow that you're likel…”
   • [community] “Plaid is a terrible company. Their main product scrapes financial data from unsuspecting users that simply think they're making a bank trans…”

   proof ↗⚑ flag

Refresh

1. developerTrigger an on-demand refresh of a connected account's data through the API when my use case needs now-fresh data, with the refresh semantics documented

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections~partialcommunity5/10

   Docs mention webhook events fired after a balance, ownership, and transaction 'refresh' is complete (docs-13, docs-24, docs-25), implying an underlying refresh mechanism exists, but the evidence pack never documents the actual API call/endpoint to trigger an on-demand refresh or its semantics (rate limits, latency, cost). A community report even suggests refresh is limited to daily pulls rather than freely on-demand, indicating real constraints on freshness. Missing for 10: explicit API reference for a refresh endpoint, documented refresh-trigger semantics (frequency limits, sync latency), and confirmation this applies across balance/ownership/transaction data uniformly.

   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”
   • [community] “The limit to only daily pulls and up to 180 days of historical data is pretty disappointing. Would expect Stripe to push the envelope here..…”

   proof ↗⚑ flag

   Plaid~partialclaimed4/10

   The evidence shows Plaid supports webhook-based updates (plaid-docs-8, plaid-docs-4) and an API-driven `transactionsSync` call (plaid-gh-1, plaid-gh-2) that developers can invoke to pull current data, which is adjacent to an on-demand refresh trigger, but the pack never cites Plaid's dedicated refresh endpoint (e.g. /transactions/refresh) or documents its specific semantics (timing, cost, which products support it). Missing for 10: explicit documentation of a refresh-on-demand endpoint and its semantics, confirmation of which products it applies to, and any independent/hands-on confirmation of its behavior.

   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”

   proof ↗⚑ flag

Webhooks

1. developerData changes arrive as signed webhooks — new transactions, balance updates, connection state changes — so my system stays current without polling

   weight 2 · round to Plaid
   Stripe Financial Connections~partialclaimed6/10

   Docs confirm signed webhook events for account linking, balance refresh, ownership refresh, and transaction refresh, directly enabling event-driven freshness instead of polling. However, evidence lacks detail on signature verification specifics, latency/timeliness guarantees, connection state-change events beyond relink, and independent/hands-on confirmation of webhook reliability. missing for 10: signature verification documentation detail, guaranteed latency/freshness SLAs, broader connection-state-change event coverage, independent developer corroboration of webhook reliability.

   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”

   proof ↗⚑ flag

   Plaid✓fullclaimed8/10

   Plaid's docs explicitly describe webhooks for transactions, balance, and Item/connection state changes to keep systems updated without polling, and this is a well-documented core mechanism (plaid-docs-4, plaid-docs-8) reinforced by SDK error-handling examples showing transactionsSync usage in conjunction with webhooks (plaid-gh-1). No evidence indicates webhook signing/verification is missing or broken. Missing for 10: explicit mention of webhook signature verification mechanics and independent third-party confirmation of webhook reliability in production.

   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”

   proof ↗⚑ flag

Coverage

1. founderThe platform documents how many institutions it reaches and where — published coverage numbers and geographies I can check against where my users actually bank

   weight 3 · round to Stripe Financial Connections
   Stripe Financial Connections~partialcommunity4/10

   Stripe's docs publish a single coverage figure ("more than 12,000 supported banks") but no official breakdown of geographies or country-level coverage; the only geography signal comes from community reports that the product is US-only (and doesn't work for Canada or other countries), which isn't corroborated by first-party documentation. Missing for 10: official geographic coverage documentation, per-country institution counts, and any first-party statement matching the community's US-only observation.

   • [claimed-docs] “Users select their bank from frequently chosen institutions or by searching more than 12,000 supported banks.”
   • [community] “Curious that they translated it to German based on my phone settings for a product that only supports US banks? (I don't mind that it is US …”
   • [community] “Only available in the US.”
   • [community] “guessing this doesn't work with Canada”

   proof ↗⚑ flag

   Plaid~partialclaimed3/10

   The pack shows only a narrow geography claim (payment-initiation supports '18 European markets') but no overall institution count or country-by-country coverage list that a founder could check against user banks. missing for 10: published total institution count, per-country/region coverage breakdown, and any independent verification of coverage claims.

   • [claimed-docs] “Plaid's European Payments suite enables your users to make real-time payments without manually entering their account details or leaving you…”

   proof ↗⚑ flag

Status

1. ops leadPer-institution health is visible — documented institution statuses, outage or degradation signals, and error codes that distinguish a bank problem from my problem

   weight 2 · round to Plaid
   Stripe Financial Connections~partialclaimed3/10

   Docs show webhook events for refresh completions (balance, ownership, transaction) and a relink API for inactive accounts, which provide some signal that an account/connection has degraded, but there is no documented institution status page, no outage/degradation signal feed, and no error-code taxonomy that distinguishes a bank-side problem from an integration-side problem. Missing for 10: institution health/status dashboard, explicit outage signals, and documented error codes separating bank vs. merchant-side failures.

   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”
   • [claimed-docs] “Sent after an ownership refresh is complete.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”

   proof ↗⚑ flag

   Plaid~partialprobed4/10

   Plaid documents webhooks for Item status changes and SDK-level error handling, and offers a Dashboard MCP server with 'diagnostics tools' for debugging Items, which supports some institution-health visibility. However, there is no evidence of a documented institution-status/error-code taxonomy (e.g., distinguishing bank outages from integration errors) or a public status page for individual institutions. Missing for 10: documented per-institution error code list distinguishing bank vs. client errors, an institution status/outage dashboard or feed, and independent confirmation these diagnostics reliably surface bank-side outages.

   • [claimed-docs] “Plaid sends webhooks to programmatically inform you about changes to Plaid Items or the status of asynchronous processes.”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”
   • [claimed-docs] “The Dashboard MCP server is a remote MCP server hosted by Plaid. It provides Production diagnostics and analytics tools, including tools for…”
   • [probe] “official MCP server documented at https://plaid.com/docs/resources/mcp/”

   proof ↗⚑ flag

Multi product

1. developerOne link session can power multiple data products — auth, balances, transactions, identity — without forcing the user through separate connection flows per product

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections✓fullcommunity8/10

   Docs confirm one Financial Connections session/client_secret lets a user link an account and expose auth, balances, ownership/identity, and transactions data together (docs-1, docs-8/9/10, docs-2/3/4), and a community integrator confirms using the same link for verification, ACH fraud signal, and adjacent Stripe products (comm-6). missing for 10: no explicit first-party statement that all four data products are requested/returned in a single session without re-prompting the user, and one community report notes transactions/other data products were 'coming soon' at beta (comm-8), leaving some ambiguity about full simultaneous availability.

   • [claimed-docs] “You can use one integration to instantly verify bank accounts for ACH payments, reduce underwriting risk with balances data, mitigate fraud …”
   • [claimed-docs] “Access an account’s current and available balances.”
   • [claimed-docs] “Access account owners’ names and mailing addresses.”
   • [claimed-docs] “Access an account’s transaction history.”
   • [claimed-docs] “Collect a bank account for ACH Direct Debit payments while using account data, including balances.”
   • [claimed-docs] “Collect a bank account to use for Connect payouts, and use account data, such as ownership details, with your integration.”
   • [claimed-docs] “Collect user accounts and gain access to account data to build more complex integrations, such as personal finance apps.”
   • [community] “I work at one of the companies that integrated Financial Connections during its beta, moving from Plaid Auth. We use the link to bank accoun…”
   • [community] “By clicking 'Start Now', I try to visit dashboard.stripe.com/financial-connections/application and it redirects to the test dashboard. A lot…”

   proof ↗⚑ flag

   Plaid~partialclaimed5/10

   Plaid's sandbox docs explicitly mention creating an Item with 'initial products' (plural) via a single public_token, implying one Link-created Item can be enabled for multiple products (auth, balance, identity, transactions) at once rather than separate connections. However, the evidence pack never explicitly confirms a single Link session UX flow surfacing multiple products to the end user in one consent step. Missing for 10: an explicit doc/example showing a single Link token configured with products=['auth','balances','transactions','identity'] and the resulting single end-user consent flow, plus independent/hands-on confirmation.

   • [claimed-docs] “you can also create Items in Sandbox via the API, using a special Sandbox-only endpoint, /sandbox/public_token/create. This endpoint allows …”
   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”
   • [claimed-docs] “Auth allows you to request a user's checking, savings, or cash management account and routing number, making it easy for you to initiate cre…”
   • [claimed-docs] “Balance is Plaid's product for receiving real-time balance information. This data is commonly used to tell if an account has sufficient fund…”
   • [claimed-docs] “Plaid's Identity product helps you verify users' identities by accessing information on file with their financial institution.”
   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”

   proof ↗⚑ flag

Quickstart

1. developerGo from signup to my first linked sandbox account fast — self-serve API keys, a runnable quickstart, and client libraries in my language

   weight 2 · round to Plaid
   Stripe Financial Connections~partialprobed6/10

   Docs show a testable sandbox flow (test institutions requiring no real credentials, client_secret-based auth via collectFinancialConnectionsAccounts) and an official CLI, indicating a runnable quickstart path to a first linked sandbox account. However, the pack lacks explicit evidence of self-serve API key issuance or language-specific client library listings for Financial Connections. missing for 10: explicit self-serve API key/dashboard signup evidence, explicit client library/SDK language coverage, and independent hands-on confirmation of quickstart speed.

   • [claimed-docs] “the authentication flow exclusively shows a selection of test institutions managed by Stripe. The client can link accounts from any of these…”
   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [probe] “official CLI documented at https://docs.stripe.com/stripe-cli”
   • [community] “By clicking 'Start Now', I try to visit dashboard.stripe.com/financial-connections/application and it redirects to the test dashboard. A lot…”

   proof ↗⚑ flag

   Plaid~partialprobed7/10

   Docs show self-serve signup via Dashboard for API keys, a runnable Quickstart app, a fully-featured free Sandbox environment supporting all products, and a Node client library with async/await error handling. However, there's no explicit evidence of the breadth of client libraries across multiple languages, no independent hands-on confirmation of quickstart speed/ease, and no OpenAPI spec discoverable via probes. missing for 10: multi-language client library coverage evidence, independent/hands-on time-to-first-linked-account confirmation, public OpenAPI/API reference spec.

   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing... you can create an unlimited number of …”
   • [claimed-docs] “Let's test out running Plaid locally by cloning the Quickstart app. You'll need API keys, which you can receive by signing up in the Dashboa…”
   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing. All Plaid functionality of both the Plai…”
   • [claimed-docs] “you can also create Items in Sandbox via the API, using a special Sandbox-only endpoint, /sandbox/public_token/create. This endpoint allows …”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plaid.com/openapi.json, https://plaid.com/swagger.json, https://plaid.com/api/openapi.json, …”

   proof ↗⚑ flag

Sandbox

1. developerA sandbox with test institutions and documented test credentials lets me exercise linking, data retrieval, and error states end-to-end before touching a real bank account

   weight 3 · round to Plaid
   Stripe Financial Connections✓fullclaimed7/10

   Docs explicitly describe a dedicated testing mode where the authentication flow shows only Stripe-managed test institutions that can be linked without credentials, enabling end-to-end exercise of the linking flow before touching real banks. However, evidence doesn't detail documented test credentials for specific error-state scenarios (e.g., forced failures, specific test account numbers for different data states) or confirm sandbox coverage of balances/transactions/ownership retrieval scenarios. Missing for 10: documented specific test credentials/account numbers for triggering distinct error states, and explicit confirmation that data retrieval (balances/transactions) can be exercised in test mode with corroborating independent developer accounts.

   • [claimed-docs] “the authentication flow exclusively shows a selection of test institutions managed by Stripe. The client can link accounts from any of these…”
   • [claimed-docs] “The client can link accounts from any of these institutions without providing credentials.”

   proof ↗⚑ flag

   Plaid✓fullclaimed9/10

   Plaid's Sandbox docs describe a free, fully-featured test environment supporting all API and Link functionality, unlimited test Items, a special sandbox-only endpoint to create Items with arbitrary institution IDs and test credentials, and SDK error-handling examples for exercising error states end-to-end. This directly matches the story's need to test linking, data retrieval, and error flows before touching real accounts. Missing for 10: independent/hands-on developer corroboration of the sandbox experience beyond first-party docs.

   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing... you can create an unlimited number of …”
   • [claimed-docs] “The Plaid Sandbox is a free and fully-featured environment for application development and testing. All Plaid functionality of both the Plai…”
   • [claimed-docs] “you can also create Items in Sandbox via the API, using a special Sandbox-only endpoint, /sandbox/public_token/create. This endpoint allows …”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”
   • [claimed-docs] “Plaid Link is the client-side component that your users will interact with in order to link their accounts to Plaid and allow you to access …”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Stripe Financial Connections~partialprobed5/10

   Most Financial Connections operations (creating sessions, retrieving balances/ownership/transactions, webhooks, relink) are documented as pure server-side API calls, and Stripe also exposes an MCP server and CLI for agent-driven interaction with the API (docs-11, docs-18, probe-4, probe-5). However, the actual account-linking/authentication step inherently requires the client-side `collectFinancialConnectionsAccounts` hosted flow (docs-6, docs-7) — a consumer-facing UI that cannot be bypassed via pure API calls, so an AI-native user cannot complete the core linking action through API alone. Missing for 10: evidence of a pure-API path to complete bank authentication/consent without the client SDK, and confirmation that all Dashboard-configurable settings are also API-exposed.

   • [claimed-docs] “Use collectFinancialConnectionsAccounts to launch the authentication flow from your client using the client_secret returned by your server”
   • [claimed-docs] “Users select their bank from frequently chosen institutions or by searching more than 12,000 supported banks.”
   • [claimed-docs] “Financial insights for agents | - Agent-powered spending analysis - Balance and transaction monitoring | Link CLI”
   • [claimed-docs] “The Stripe Model Context Protocol (MCP) server provides tools that AI agents can use to interact with the Stripe API and search Stripe’s kno…”
   • [probe] “official MCP server documented at https://docs.stripe.com/mcp”
   • [probe] “official CLI documented at https://docs.stripe.com/stripe-cli”
   • [claimed-docs] “Sent when a customer links a new account. If they link multiple accounts, it emits multiple events (one per account).”
   • [claimed-docs] “Use the relink API to help your user reconnect their inactive account.”

   proof ↗⚑ flag

   Plaid~partialprobed5/10

   Plaid is API-first for core financial data products, and Sandbox Items can be created via API instead of the Dashboard UI (plaid-docs-14), suggesting some UI/API parity. However, the docs explicitly describe Dashboard-only actions like customizing and publishing Link's flow (plaid-docs-11) and signing up for API keys (plaid-docs-10) with no corresponding API endpoint shown, and there's no OpenAPI spec or full endpoint catalog to confirm total parity (plaid-probe-3). Missing for 10: evidence that Dashboard-only settings (Link customization, key management, analytics) have API equivalents, and independent confirmation of full UI/API feature parity.

   • [claimed-docs] “You can customize parts of Link's flow straight from the Dashboard. You can preview your changes in real time and then publish them instantl…”
   • [claimed-docs] “you can also create Items in Sandbox via the API, using a special Sandbox-only endpoint, /sandbox/public_token/create. This endpoint allows …”
   • [claimed-docs] “Let's test out running Plaid locally by cloning the Quickstart app. You'll need API keys, which you can receive by signing up in the Dashboa…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://plaid.com/openapi.json, https://plaid.com/swagger.json, https://plaid.com/api/openapi.json, …”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Stripe Financial Connections—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

   Plaid—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

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

   weight 2 · round drawn
   Stripe Financial Connections—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

   Plaid—none0/10

   Plaid is a closed-source commercial API/SaaS product; its client SDKs (e.g., plaid-node) are open-source wrappers but the core Plaid service/source is not published under an open license, and no evidence shows the product's actual source available for inspection.

   ⚑ flag

Pay by bank

1. developerInitiate a bank payment from a connected account — a documented pay-by-bank or payment-initiation product with its live geographies stated honestly

   weight 2 · round to Plaid
   Stripe Financial Connections~partialcommunity4/10

   Financial Connections lets a linked bank account be used to collect ACH Direct Debit payments (docs-8, docs-16, docs-17, docs-27-29), which is a debit-based bank payment initiation flow, but this is not a full 'pay-by-bank' push-payment product, and there is no documented statement of live geographies — the only geography signal comes from community reports that it is US-only (comm-9, comm-11, comm-12), not honest first-party docs. Missing for 10: explicit documented geography/coverage list, and evidence of true push-payment (real-time transfer) initiation rather than just ACH debit collection.

   • [claimed-docs] “Collect a bank account for ACH Direct Debit payments while using account data, including balances.”
   • [claimed-docs] “instant | Financial Connections only, with no manual entry and microdeposit fallback”
   • [claimed-docs] “Reduce your payment failure rate from closed or inactive accounts - Improve payments conversion by keeping users on session, instead of forc…”
   • [claimed-docs] “Reduce your payment failure rate from closed or inactive accounts”
   • [claimed-docs] “Improve payments conversion by keeping users on session, instead of forcing them to leave your payments flow to locate their accounts and ro…”
   • [claimed-docs] “Save development time by eliminating the need to create a custom bank account collection form”
   • [community] “Curious that they translated it to German based on my phone settings for a product that only supports US banks? (I don't mind that it is US …”
   • [community] “Only available in the US.”
   • [community] “guessing this doesn't work with Canada”

   proof ↗⚑ flag

   Plaid~partialclaimed6/10

   Plaid documents a real Payment Initiation product enabling real-time bank payments across 18 named European markets, which is a fairly honest geography disclosure, but Plaid explicitly does not offer this product in the US (US flows rely on Auth+ACH via third-party rails, not Plaid-initiated payment). missing for 10: explicit US/global payment-initiation coverage or a clear statement of unsupported geographies beyond Europe, independent/hands-on confirmation of the payment-initiation flow working as documented, and clarity on settlement/liability model for developers.

   • [claimed-docs] “Plaid's European Payments suite enables your users to make real-time payments without manually entering their account details or leaving you…”
   • [claimed-docs] “Plaid's European Payments suite enables your users to make real-time payments without manually entering their account details or leaving you…”
   • [claimed-docs] “Auth allows you to request a user's checking, savings, or cash management account and routing number, making it easy for you to initiate cre…”

   proof ↗⚑ flag

Recurring

1. developerRecurring bank payments are supported — variable recurring payments, standing consents, or documented recurring debit flows built on the connection

   weight 2 · round to Stripe Financial Connections
   Stripe Financial Connections~partialcommunity4/10

   Financial Connections explicitly supports collecting a bank account for ACH Direct Debit payments (docs-8, docs-16, docs-17), and ACH Direct Debit mandates are inherently reusable for repeat debits, but the evidence never documents a specific recurring/subscription debit flow, standing consent, or variable recurring payment (VRP) mechanism built on top of the connection. Missing for 10: explicit documentation of mandate reuse for recurring charges, standing consent/authorization language, and any VRP-style flow or recurring-debit API guidance.

   • [claimed-docs] “Collect a bank account for ACH Direct Debit payments while using account data, including balances.”
   • [claimed-docs] “instant | Financial Connections only, with no manual entry and microdeposit fallback”
   • [claimed-docs] “Reduce your payment failure rate from closed or inactive accounts - Improve payments conversion by keeping users on session, instead of forc…”
   • [community] “I work at one of the companies that integrated Financial Connections during its beta, moving from Plaid Auth. We use the link to bank accoun…”

   proof ↗⚑ flag

   Plaid—none0/10

   Plaid's Payment Initiation docs describe single real-time payments across European markets, with no mention of variable recurring payments, standing orders, or documented recurring debit/consent flows; Auth/ACH docs also only describe initiating one-off credits/debits, not recurring mandates.

   • [claimed-docs] “Plaid's European Payments suite enables your users to make real-time payments without manually entering their account details or leaving you…”
   • [claimed-docs] “Plaid's European Payments suite enables your users to make real-time payments without manually entering their account details or leaving you…”
   • [claimed-docs] “Auth allows you to request a user's checking, savings, or cash management account and routing number, making it easy for you to initiate cre…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   No evidence in the pack mentions data residency, regional storage options, or user/customer choice of data location for Financial Connections; comments even note it's US-only, which suggests no regional selection capability. Missing for 10: any documentation of region/residency configuration, data localization options, or EU/other data center choices.

   • [community] “Only available in the US.”
   • [community] “guessing this doesn't work with Canada”

   proof ↗⚑ flag

   Plaid—none0/10

   No evidence of any data residency/region selection controls in Plaid's documentation; the evidence pack covers products, sandbox, MCP server, and payment features but never mentions data storage location choice or regional hosting options.

   ⚑ flag

2. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   No evidence in the pack addresses data retention controls, deletion APIs/mechanisms, or configurable data lifecycle policies for Financial Connections data; docs describe data access (balances, transactions, ownership) and webhooks but not retention/deletion controls for AI-native users. Missing for 10: any documentation of data retention settings, account/data deletion endpoints, or user-controlled data lifecycle management.

   ⚑ flag

   Plaid—none0/10

   No evidence pack item documents any user- or developer-facing mechanism for controlling data retention periods or deleting stored financial data in Plaid; docs cover data collection (Auth, Identity, Transactions, Balance) but not retention/deletion controls. Community commentary even shows a user unsure how to revoke Plaid's access, underscoring the absence of a clear deletion/retention feature.

   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [community] “I gave them access to my bank via coinbase. If I change my bank password would they lose access to my account? If not, what do I need to do …”

   proof ↗⚑ flag

Cashflow

1. finance leadThe platform derives income and cash-flow signals from connected accounts — recurring streams, payroll detection, or documented income verification products built on the same data

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   Financial Connections documents raw data access (balances, transactions, ownership) and encourages building 'fintech products with transactions data' or 'personal finance apps,' but there is no evidence of Stripe itself deriving income/cash-flow signals — no recurring-stream detection, payroll identification, or documented income-verification product built on this data. Community discussion also focuses on account linking reliability and pricing, not income analytics.

   • [claimed-docs] “Access an account’s transaction history.”
   • [claimed-docs] “Collect user accounts and gain access to account data to build more complex integrations, such as personal finance apps.”
   • [claimed-docs] “build new fintech products with transactions data”

   proof ↗⚑ flag

   Plaid—none0/10

   The evidence pack covers Auth, Balance, Identity, Transactions, Payment Initiation and Link, but contains no mention of an Income product, payroll detection, or recurring-stream/cash-flow analytics built on transaction data — the specific capability the story asks about is absent from the pack.

   ⚑ flag

Enrichment

1. developerRaw bank transactions come back enriched — cleaned merchant names, categories, and logos — documented as a capability of the platform, not left as an exercise for me

   weight 2 · round drawn
   Stripe Financial Connections—none0/10

   The docs describe raw transaction history access (docs-4) but never mention any enrichment layer — no cleaned/normalized merchant names, spending categories, or merchant logos are documented anywhere in the evidence pack. Community threads even note the transactions product was still 'Coming Soon' at one point, with no follow-up confirming enrichment features shipped.

   • [claimed-docs] “Access an account’s transaction history.”
   • [claimed-docs] “Collect user accounts and gain access to account data to build more complex integrations, such as personal finance apps.”
   • [community] “By clicking 'Start Now', I try to visit dashboard.stripe.com/financial-connections/application and it redirects to the test dashboard. A lot…”

   proof ↗⚑ flag

   Plaid—none0/10

   While Plaid's Transactions product is documented as returning transaction data, none of the evidence describes enrichment specifics like cleaned merchant names, categories, or logos being a documented feature — only raw transaction retrieval and webhooks are mentioned (plaid-docs-4, plaid-gh-1). Missing for 10: explicit documentation of merchant name cleaning, category taxonomy, and logo/icon fields as part of the Transactions response.

   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”

   proof ↗⚑ flag

Transactions

1. developerPull transaction history for a connected account through the API — paginated, with documented history depth and a sync pattern for fetching only what changed

   weight 3 · round to Plaid
   Stripe Financial Connections~partialcommunity5/10

   Docs confirm access to an account's transaction history (docs-4) and a webhook-driven refresh model (transaction refresh completed events, docs-25) that lets a client know when to pull new data, and community evidence confirms documented depth/cadence limits (180 days history, daily pulls) as a real sync pattern. However, there is no explicit documentation in the pack of the transactions list endpoint's pagination parameters (cursor/starting_after) or a formal delta/sync-token mechanism for fetching only changed transactions. Missing for 10: explicit API pagination documentation for the transactions list endpoint, and a documented incremental-sync/cursor mechanism beyond the refresh webhook.

   • [claimed-docs] “Access an account’s transaction history.”
   • [claimed-docs] “Sent after a transaction refresh is complete.”
   • [claimed-docs] “Sent after a balance refresh is complete.”
   • [community] “The limit to only daily pulls and up to 180 days of historical data is pretty disappointing. Would expect Stripe to push the envelope here..…”

   proof ↗⚑ flag

   Plaid✓fullclaimed8/10

   Plaid's Transactions docs confirm up to 24 months of history and webhook-based updates, and the plaid-node SDK demonstrates the transactionsSync pattern for fetching only changed data, matching the story's pagination/sync/history-depth requirements. missing for 10: no explicit mention of pagination cursor mechanics or rate limits, and no independent/hands-on corroboration of sync behavior beyond the SDK snippet.

   • [claimed-docs] “Retrieve up to 24 months of transaction data and stay up-to-date with webhooks”
   • [github] “try { await plaidClient.transactionsSync(request); } catch (error) { const err = error.response.data; }”
   • [github] “All errors can now be caught using try/catch with async/await or through promise chaining.”

   proof ↗⚑ flag