Skip to content

How Smooth’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score23/100

Agent-ready 37.7 × 0.30 = 11.31

API quality 0.0 × 0.20 = 0.00

Openness 6.0 × 0.20 = 1.20

Built-in AI 61.4 × 0.15 = 9.21

Automation 6.9 × 0.15 = 1.03

(11.31 + 0.00 + 1.20 + 9.21 + 1.03) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 22.75 ÷ 1.00 = 22.8

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready37.7/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://docs.smooth.sh/llms.txtPROBE llms.txt: HTTP 200 at https://docs.smooth.sh/llms.txt # Smooth ## Docs - [Introduction](https://docs.smooth.sh/index.md): Welcome to Smooth - [Quickstart](https://docs.smoo
  • [claimed-docs] https://docs.smooth.sh/cli/other-agents.mdSmooth CLI works with any agent that can run CLI commands.
  • [claimed-docs] https://docs.smooth.sh/cli/claude-code.mdAsk Claude to do something on the web. It will use Smooth automatically.

Run the product headlessly / in CI for automationweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://docs.smooth.shPlug-and-play: Run a task in just 4 lines of code, making it easy to integrate into your workflow.
  • [claimed-docs] https://docs.smooth.sh/quickstart.mdtask = smooth_client.run("Go to google flights and find the cheapest flight from London to Paris today")
  • [claimed-docs] https://docs.smooth.sh/api-reference/introduction.mdThe Smooth API enables programmatic browser automation through REST endpoints. You can run AI-powered tasks, create interactive browser sessions, and extend agent capabilities with custom tools.
  • [claimed-docs] https://docs.smooth.sh/api-reference/polling.mdThe API uses polling rather than webhooks or WebSockets for several reasons: Simplicity - No need to set up webhook endpoints or maintain WebSocket connections
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/list-tasks.mdList all tasks for the authenticated user.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/cancel-task.mdCancel a running task by its ID.
  • [claimed-docs] https://docs.smooth.sh/cli/other-agents.mdSmooth CLI works with any agent that can run CLI commands.
  • [probe] https://docs.smooth.sh/cli/overviewofficial CLI documented at https://docs.smooth.sh/cli/overview

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://docs.smooth.sh/methods/custom-tools.mdCustom tools allow you to give Smooth any arbitrary function as a tool. This is similar to MCP (Model Context Protocol) but without having to deal with servers or additional infrastructure.
  • [claimed-docs] https://docs.smooth.sh/methods/custom-tools.mdCustom tools allow you to give Smooth any arbitrary function as a tool.
  • [claimed-docs] https://docs.smooth.sh/api-reference/custom-tools.mdCustom tools allow you to extend the agent's capabilities by registering functions that it can call during execution. When the agent needs to perform an action that your tool provides, it will pause and wait for you to execute the tool and return the result.

Connect an agent via an official MCP serverweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://docs.smooth.sh/methods/custom-tools.mdCustom tools allow you to give Smooth any arbitrary function as a tool. This is similar to MCP (Model Context Protocol) but without having to deal with servers or additional infrastructure.
  • [claimed-docs] https://docs.smooth.sh/methods/custom-tools.mdCustom tools allow you to give Smooth any arbitrary function as a tool.

Use an official CLIweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://docs.smooth.sh/cli/overview.mdGive your AI agent a browser that actually works
  • [claimed-docs] https://docs.smooth.sh/cli/claude-code.mdAsk Claude to do something on the web. It will use Smooth automatically.
  • [claimed-docs] https://docs.smooth.sh/cli/openclaw.mdAsk your agent to do something on the web. It will use Smooth automatically.
  • [claimed-docs] https://docs.smooth.sh/cli/other-agents.mdSmooth CLI works with any agent that can run CLI commands.
  • [claimed-docs] https://docs.smooth.sh/cli/features/localhost.mdYour agent can access localhost and your local network through a secure tunnel. This is perfect for testing local apps, accessing internal tools, or working with development servers.
  • [claimed-docs] https://docs.smooth.sh/cli/features/live-view.mdEvery session comes with a live view URL where you can watch your agent browse in real-time. You can also take over and interact with the browser yourself.
  • [github] https://github.com/circlemind-ai/smooth-sdkThe Smooth CLI is a browser for AI agents, enabling tools like Claude Code to navigate the web quickly, cheaply, and reliably.
  • [probe] https://docs.smooth.sh/cli/overviewofficial CLI documented at https://docs.smooth.sh/cli/overview

Drive the product through a documented public APIweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://docs.smooth.sh/api-reference/introduction.mdThe Smooth API enables programmatic browser automation through REST endpoints. You can run AI-powered tasks, create interactive browser sessions, and extend agent capabilities with custom tools.
  • [claimed-docs] https://docs.smooth.sh/api-reference/sessions.mdSessions allow you to maintain a persistent browser instance and perform multiple actions sequentially. This is useful for complex workflows like logging in, navigating, and extracting data across multiple pages.
  • [claimed-docs] https://docs.smooth.sh/api-reference/custom-tools.mdCustom tools allow you to extend the agent's capabilities by registering functions that it can call during execution. When the agent needs to perform an action that your tool provides, it will pause and wait for you to execute the tool and return the result.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/list-tasks.mdList all tasks for the authenticated user.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/cancel-task.mdCancel a running task by its ID.
  • [claimed-docs] https://docs.smooth.sh/api-reference/event/send-event.mdSend an event to a running task. This is used for: - **Session actions**: `run_task`, `goto`, `extract`, `evaluate_js`, `close`
  • [claimed-docs] https://docs.smooth.sh/quickstart.mdtask = smooth_client.run("Go to google flights and find the cheapest flight from London to Paris today")
  • [probe] https://docs.smooth.sh/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.smooth.sh/openapi.json, https://docs.smooth.sh/swagger.json, https://docs.smooth.sh/api/openapi.json, https://docs.smooth.sh/.well-known/openapi.json)

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Build against official SDKsweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://docs.smooth.sh/quickstart.mdtask = smooth_client.run("Go to google flights and find the cheapest flight from London to Paris today")
  • [claimed-docs] https://docs.smooth.sh/api-reference/introduction.mdThe Smooth API enables programmatic browser automation through REST endpoints. You can run AI-powered tasks, create interactive browser sessions, and extend agent capabilities with custom tools.
  • [claimed-docs] https://docs.smooth.sh/methods/custom-tools.mdCustom tools allow you to give Smooth any arbitrary function as a tool.
  • [claimed-docs] https://docs.smooth.sh/methods/custom-tools.mdCustom tools allow you to give Smooth any arbitrary function as a tool. This is similar to MCP (Model Context Protocol) but without having to deal with servers or additional infrastructure.
  • [claimed-docs] https://docs.smooth.sh/api-reference/sessions.mdSessions allow you to maintain a persistent browser instance and perform multiple actions sequentially. This is useful for complex workflows like logging in, navigating, and extracting data across multiple pages.
  • [claimed-docs] https://docs.smooth.sh/api-reference/custom-tools.mdCustom tools allow you to extend the agent's capabilities by registering functions that it can call during execution. When the agent needs to perform an action that your tool provides, it will pause and wait for you to execute the tool and return the result.
  • [probe] https://docs.smooth.sh/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.smooth.sh/openapi.json, https://docs.smooth.sh/swagger.json, https://docs.smooth.sh/api/openapi.json, https://docs.smooth.sh/.well-known/openapi.json)
  • [github] https://github.com/circlemind-ai/smooth-sdkThe Smooth CLI is a browser for AI agents, enabling tools like Claude Code to navigate the web quickly, cheaply, and reliably.

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://docs.smooth.sh/api-reference/polling.mdThe API uses polling rather than webhooks or WebSockets for several reasons: Simplicity - No need to set up webhook endpoints or maintain WebSocket connections

Agent-ready = 79.2 ÷ 210 × 100 = 37.7

API quality0.0/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://docs.smooth.sh/api-reference/introduction.mdThe Smooth API enables programmatic browser automation through REST endpoints. You can run AI-powered tasks, create interactive browser sessions, and extend agent capabilities with custom tools.
  • [claimed-docs] https://docs.smooth.sh/api-reference/sessions.mdSessions allow you to maintain a persistent browser instance and perform multiple actions sequentially. This is useful for complex workflows like logging in, navigating, and extracting data across multiple pages.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/list-tasks.mdList all tasks for the authenticated user.
  • [probe] https://docs.smooth.sh/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.smooth.sh/openapi.json, https://docs.smooth.sh/swagger.json, https://docs.smooth.sh/api/openapi.json, https://docs.smooth.sh/.well-known/openapi.json)

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://docs.smooth.sh/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.smooth.sh/openapi.json, https://docs.smooth.sh/swagger.json, https://docs.smooth.sh/api/openapi.json, https://docs.smooth.sh/.well-known/openapi.json)
  • [claimed-docs] https://docs.smooth.sh/api-reference/introduction.mdThe Smooth API enables programmatic browser automation through REST endpoints. You can run AI-powered tasks, create interactive browser sessions, and extend agent capabilities with custom tools.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/list-tasks.mdList all tasks for the authenticated user.

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://docs.smooth.sh/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.smooth.sh/openapi.json, https://docs.smooth.sh/swagger.json, https://docs.smooth.sh/api/openapi.json, https://docs.smooth.sh/.well-known/openapi.json)

API quality = 0.0 ÷ 70 × 100 = 0.0

Openness6.0/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://docs.smooth.sh/api-reference/introduction.mdThe Smooth API enables programmatic browser automation through REST endpoints. You can run AI-powered tasks, create interactive browser sessions, and extend agent capabilities with custom tools.
  • [claimed-docs] https://docs.smooth.sh/cli/features/live-view.mdEvery session comes with a live view URL where you can watch your agent browse in real-time. You can also take over and interact with the browser yourself.
  • [claimed-docs] https://docs.smooth.sh/api-reference/sessions.mdSessions allow you to maintain a persistent browser instance and perform multiple actions sequentially. This is useful for complex workflows like logging in, navigating, and extracting data across multiple pages.
  • [claimed-docs] https://docs.smooth.sh/api-reference/event/send-event.mdSend an event to a running task. This is used for: - **Session actions**: `run_task`, `goto`, `extract`, `evaluate_js`, `close`
  • [claimed-docs] https://docs.smooth.sh/cli/other-agents.mdSmooth CLI works with any agent that can run CLI commands.

Export all of my data in open formats and leaveweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://docs.smooth.sh/features/zero-data-retention.mdZero Data Retention is an enterprise feature that provides enhanced data privacy by allowing you to delete all data associated with completed tasks.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/list-tasks.mdList all tasks for the authenticated user.

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [github] https://github.com/circlemind-ai/smooth-sdkThe Smooth CLI is a browser for AI agents, enabling tools like Claude Code to navigate the web quickly, cheaply, and reliably.
  • [community] https://hn.algolia.com/api/v1/items/46901233I'm unwilling to send my data to a 3rd party that is so new on the scene... Make it self-hostable, the conversation can change
  • [community] https://hn.algolia.com/api/v1/items/46901233Way too expensive, I'll wait for a free/open source browser optimized to be used by agents.

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [community] https://hn.algolia.com/api/v1/items/46901233I'm unwilling to send my data to a 3rd party that is so new on the scene... Make it self-hostable, the conversation can change
  • [community] https://hn.algolia.com/api/v1/items/46901233Way too expensive, I'll wait for a free/open source browser optimized to be used by agents.
  • [claimed-docs] https://docs.smooth.sh/api-reference/introduction.mdThe Smooth API enables programmatic browser automation through REST endpoints. You can run AI-powered tasks, create interactive browser sessions, and extend agent capabilities with custom tools.

Openness = 6.0 ÷ 100 × 100 = 6.0

Built-in AI61.4/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

n/a — not applicable to this product: excluded from numerator and denominator

  • [github] https://github.com/circlemind-ai/smooth-sdkThe Smooth CLI is a browser for AI agents, enabling tools like Claude Code to navigate the web quickly, cheaply, and reliably.
  • [claimed-docs] https://docs.smooth.sh/cli/overview.mdGive your AI agent a browser that actually works
  • [claimed-docs] https://docs.smooth.sh/methods/session-extract.mdExtract structured data from the current page by providing a schema.

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://docs.smooth.sh/quickstart.mdtask = smooth_client.run("Go to google flights and find the cheapest flight from London to Paris today")
  • [claimed-docs] https://docs.smooth.sh/features/live-share.mdWhen running a task, you will receive a `live_url`, which can be used to view the agent actions live.
  • [claimed-docs] https://docs.smooth.sh/features/persistent-sessions.mdLog in once, then reuse that authentication for future tasks.
  • [claimed-docs] https://docs.smooth.sh/api-reference/polling.mdThe API uses polling rather than webhooks or WebSockets for several reasons: Simplicity - No need to set up webhook endpoints or maintain WebSocket connections
  • [claimed-docs] https://docs.smooth.sh/cli/claude-code.mdAsk Claude to do something on the web. It will use Smooth automatically.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/list-tasks.mdList all tasks for the authenticated user.

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max

  • [claimed-docs] https://docs.smooth.sh/quickstart.mdtask = smooth_client.run("Go to google flights and find the cheapest flight from London to Paris today")
  • [claimed-docs] https://docs.smooth.sh/methods/overview.mdSession Workflow — Multi-step execution where you can orchestrate smaller tasks, navigate to URLs, and extract data within a persistent browser session.
  • [claimed-docs] https://docs.smooth.sh/features/live-share.mdWhen running a task, you will receive a `live_url`, which can be used to view the agent actions live.
  • [claimed-docs] https://docs.smooth.sh/cli/claude-code.mdAsk Claude to do something on the web. It will use Smooth automatically.
  • [github] https://github.com/circlemind-ai/smooth-sdkThe Smooth CLI is a browser for AI agents, enabling tools like Claude Code to navigate the web quickly, cheaply, and reliably.
  • [community] https://hn.algolia.com/api/v1/items/45027597I just wrote a complex prompt and it did a good job. How do you do evals or testing of your project?
  • [community] https://hn.algolia.com/api/v1/items/46901233are your evals / comparisons publicly/3rd party reproducible? If it's 'trust me, I did a fair comparison', that's not going to fly today.

Operate the product with natural-language commandsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://docs.smooth.sh/quickstart.mdtask = smooth_client.run("Go to google flights and find the cheapest flight from London to Paris today")
  • [claimed-docs] https://docs.smooth.sh/cli/claude-code.mdAsk Claude to do something on the web. It will use Smooth automatically.
  • [claimed-docs] https://docs.smooth.sh/cli/openclaw.mdAsk your agent to do something on the web. It will use Smooth automatically.
  • [claimed-docs] https://docs.smooth.sh/cli/other-agents.mdSmooth CLI works with any agent that can run CLI commands.
  • [claimed-docs] https://docs.smooth.sh/cli/overview.mdGive your AI agent a browser that actually works
  • [github] https://github.com/circlemind-ai/smooth-sdkThe Smooth CLI is a browser for AI agents, enabling tools like Claude Code to navigate the web quickly, cheaply, and reliably.

Built-in AI = 43.0 ÷ 70 × 100 = 61.4

Automation6.9/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://docs.smooth.sh/methods/overview.mdSession Workflow — Multi-step execution where you can orchestrate smaller tasks, navigate to URLs, and extract data within a persistent browser session.
  • [claimed-docs] https://docs.smooth.sh/methods/session.mdBrowser sessions allow you to run multiple sequential tasks in a single browser instance. This enables you to break complex workflows into smaller, more reliable steps.
  • [claimed-docs] https://docs.smooth.sh/api-reference/sessions.mdSessions allow you to maintain a persistent browser instance and perform multiple actions sequentially. This is useful for complex workflows like logging in, navigating, and extracting data across multiple pages.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/list-tasks.mdList all tasks for the authenticated user.
  • [claimed-docs] https://docs.smooth.sh/api-reference/task/cancel-task.mdCancel a running task by its ID.

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://docs.smooth.sh/api-reference/polling.mdThe API uses polling rather than webhooks or WebSockets for several reasons: Simplicity - No need to set up webhook endpoints or maintain WebSocket connections
  • [claimed-docs] https://docs.smooth.sh/cli/use-cases/monitoring.mdYour agent can check websites on demand, monitor for changes, or gather status updates from various sources.
  • [claimed-docs] https://docs.smooth.sh/api-reference/event/send-event.mdSend an event to a running task. This is used for: - **Session actions**: `run_task`, `goto`, `extract`, `evaluate_js`, `close`

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 4.8 ÷ 70 × 100 = 6.9